'tfl' 방언

TensorFlow Lite 방언.

이 방언은 TensorFlow Lite 작업에 매핑됩니다.

불변:

  • 모든 값은 Tensor 유형입니다(특히 스칼라는 0차원 텐서를 사용하여 표시됨).

작업 정의

tfl.abs (TFL::AbsOp)

절대값 연산자

텐서 x 주어지면 이 작업은 x 에 있는 각 요소의 절대값을 포함하는 텐서를 반환합니다. 예를 들어 x가 입력 요소이고 y가 출력 요소인 경우 이 연산은 \(y = |x|\)계산합니다.

특성: AlwaysSpeculateableImplTrait, QuantizableResult, SameOperandsAndResultShape

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
x 16비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 32비트 부동 소수점 또는 QI8 유형 또는 QI16 유형 값의 텐서

결과:

결과 설명
y 16비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 32비트 부동 소수점 또는 QI8 유형 또는 QI16 유형 값의 텐서

tfl.add (TFL::AddOp)

더하기 연산자

요소별 덧셈 연산.

특성: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성

피연산자:

피연산자 설명
lhs 32비트 부동 또는 16비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서
rhs 32비트 부동 또는 16비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서

결과:

결과 설명
output 32비트 부동 또는 16비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서

tfl.add_n (TFL::AddNOp)

_n 연산자 추가

모든 입력 텐서를 요소별로 추가합니다.

특성: AlwaysSpeculatableImplTrait, Commutative

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), SameOperandsAndResultsScale, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
inputs 모든 유형 값의 텐서

결과:

결과 설명
sum 32비트 부동 소수점 또는 32비트 무부호 정수 값의 텐서

tfl.arg_max (TFL::ArgMaxOp)

ArgMax 연산자

텐서 차원에서 가장 큰 값을 가진 인덱스를 반환합니다.

특성: AlwaysSpeculateableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
output_type ::mlir::속성 파생 속성

피연산자:

피연산자 설명
input 1비트 부호 없는 정수 또는 32비트 부동 소수점 또는 32비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 값의 텐서
dim 32/64비트 무부호 정수 값의 텐서

결과:

결과 설명
output 32/64비트 무부호 정수 값의 텐서

tfl.arg_min (TFL::ArgMinOp)

ArgMin 연산자

텐서 차원에서 가장 작은 값을 가진 인덱스를 반환합니다. a = [1, 10, 26.9, 2.8, 166.32, 62.3] b = tf.math.argmin(입력 = a) c = tf.keras.backend.eval(b)

특성: AlwaysSpeculateableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
output_type ::mlir::속성 파생 속성

피연산자:

피연산자 설명
input 1비트 부호 없는 정수 또는 32비트 부동 소수점 또는 32비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 값의 텐서
dim 32/64비트 무부호 정수 값의 텐서

결과:

결과 설명
output 32/64비트 무부호 정수 값의 텐서

tfl.assign_variable (TFL::AssignVariableOp)

변수에 새 값을 할당합니다.

이 작업에 대한 컨트롤 종속성이 있는 모든 ReadVariableOp는 이 값 또는 변수의 후속 새 값을 반환하도록 보장됩니다.

인터페이스: TflRuntimeVerifyOpInterface

피연산자:

피연산자 설명
resource_id 자원 값의 텐서
value 32비트 부동 소수점 또는 64비트 부동 소수점 또는 1비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 또는 32비트 부호 없는 정수 또는 64비트 부호 없는 정수 또는 QI16 유형의 텐서 또는 32비트 부동 요소가 있는 복합 유형 또는 64비트 부동 요소 값이 있는 복합 유형

tfl.atan2 (TFL::Atan2Op)

Atan2 작업

"atan2" 연산은 인수의 부호를 고려하여 요소별로 y/x의 아크탄젠트를 계산합니다.

특성: AlwaysSpeculatableImplTrait, SameOperandsAndResultElementType, SameOperandsAndResultShape

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
y 32비트 부동 소수점 또는 64비트 부동 소수점 값의 텐서
x 32비트 부동 소수점 또는 64비트 부동 소수점 값의 텐서

결과:

결과 설명
output 32비트 부동 소수점 또는 64비트 부동 소수점 값의 텐서

tfl.average_pool_2d (TFL::AveragePool2DOp)

_Average_pool 2d 연산자

입력에 대해 평균 풀링 작업을 수행합니다.

특성: AlwaysSpeculateableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), SameOperandsAndResultsScale, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
filter_height ::mlir::IntegerAttr 32비트 무부호 정수 속성
filter_width ::mlir::IntegerAttr 32비트 무부호 정수 속성
padding ::mlir::문자열 속성 값이 SAME 또는 VALID인 문자열 속성
stride_h ::mlir::IntegerAttr 32비트 무부호 정수 속성
stride_w ::mlir::IntegerAttr 32비트 무부호 정수 속성
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성

피연산자:

피연산자 설명
input 32비트 float 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서

결과:

결과 설명
output 32비트 float 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서

tfl.basic_lstm (TFL::BasicLSTMOp)

기본 lstm 연산자

기본 LSTM 셀 오퍼레이터.

특성: AlwaysSpeculateableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성
cell_clip ::mlir::FloatAttr 값이 음수가 아닌 32비트 float 속성
proj_clip ::mlir::FloatAttr 값이 음수가 아닌 32비트 float 속성
kernel_type ::mlir::TFL::LSTMKernelTypeAttr 값이 mlir::TFL::LSTMKernelType::BASIC인 lstm_kernel_type

피연산자:

피연산자 설명
data_input 32비트 float 또는 QUI8 유형 값의 텐서
prev_activ_input 32비트 float 또는 QUI8 유형 값의 텐서
weights_input 32비트 float 또는 QUI8 유형 값의 텐서
biases_input 32비트 float 또는 QI32 유형 값의 텐서
prev_state_input 32비트 float 또는 QI16 유형 값의 텐서

결과:

결과 설명
activ_output 모든 유형 값의 2D 텐서
state_output 모든 유형 값의 2D 텐서
concat_temp 모든 유형 값의 2D 텐서
activ_temp 모든 유형 값의 2D 텐서

tfl.batch_matmul (TFL::BatchMatMulOp)

배치 행렬 곱하기 연산자

입력에 대해 일괄 처리된 행렬 곱셈을 수행합니다. TensorFlow BatchMatMulV2의 규칙을 따르고 배치 차원 및 브로드캐스팅에서 알 수 없는 차원을 지원합니다.

Inputs:
  `inputs[0]`: required: input LHS
  `inputs[1]`: required: input RHS
  `adjoint_lhs`: optional: Transpose LHS (default false)
  `adjoint_lhs`: optional: Transpose LHS (default false)

특성: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, DynamicRangeQuantizedOpInterface, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
adj_x ::mlir::부울 속성 부울 속성
adj_y ::mlir::부울 속성 부울 속성
asymmetric_quantize_inputs ::mlir::부울 속성 부울 속성

피연산자:

피연산자 설명
x 32비트 부동 소수점 또는 QI8 유형 또는 QI16 유형 또는 8비트 무부호 정수 값의 텐서
y 32비트 부동 소수점 또는 QI8 유형 또는 QI16 유형 또는 8비트 무부호 정수 값의 텐서

결과:

결과 설명
output 32비트 부동 소수점 또는 QI8 유형 또는 QI16 유형 또는 32비트 무부호 정수 값의 텐서

tfl.batch_to_space_nd (TFL::BatchToSpaceNdOp)

BatchToSpaceNd 연산자

이 작업은 "배치" 차원 0을 공간 차원으로 재구성합니다.

특성: AlwaysSpeculateableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
input 32비트 부동 또는 8비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서
block_shape 32비트 부호 없는 정수 값의 텐서
indices 32비트 부호 없는 정수 값의 텐서

결과:

결과 설명
output 32비트 부동 또는 16비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서

tfl.bidirectional_sequence_lstm (TFL::BidirectionalSequenceLSTMOp)

양방향 시퀀스 lstm 연산자

양방향 lstm은 기본적으로 두 개의 lstm으로, 하나는 앞으로 실행되고 다른 하나는 뒤로 실행됩니다. 그리고 출력은 두 lstms의 연결입니다.

특성: QuantizableResult

인터페이스: DynamicRangeQuantizedOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

속성:

기인하다 MLIR 유형 설명
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성
cell_clip ::mlir::FloatAttr 값이 음수가 아닌 32비트 float 속성
proj_clip ::mlir::FloatAttr 값이 음수가 아닌 32비트 float 속성
merge_outputs ::mlir::부울 속성 부울 속성
time_major ::mlir::부울 속성 부울 속성
asymmetric_quantize_inputs ::mlir::부울 속성 부울 속성

피연산자:

피연산자 설명
input 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
fw_input_to_input_weights 모든 유형 값 또는 없음 유형의 텐서
fw_input_to_forget_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
fw_input_to_cell_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
fw_input_to_output_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
fw_recurrent_to_input_weights 모든 유형 값 또는 없음 유형의 텐서
fw_recurrent_to_forget_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
fw_recurrent_to_cell_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
fw_recurrent_to_output_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
fw_cell_to_input_weights 모든 유형 값 또는 없음 유형의 텐서
fw_cell_to_forget_weights 모든 유형 값 또는 없음 유형의 텐서
fw_cell_to_output_weights 모든 유형 값 또는 없음 유형의 텐서
fw_input_gate_bias 모든 유형 값 또는 없음 유형의 텐서
fw_forget_gate_bias 32비트 부동 소수점 값의 텐서
fw_cell_bias 32비트 부동 소수점 값의 텐서
fw_output_gate_bias 32비트 부동 소수점 값의 텐서
fw_projection_weights 모든 유형 값 또는 없음 유형의 텐서
fw_projection_bias 모든 유형 값 또는 없음 유형의 텐서
bw_input_to_input_weights 모든 유형 값 또는 없음 유형의 텐서
bw_input_to_forget_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
bw_input_to_cell_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
bw_input_to_output_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
bw_recurrent_to_input_weights 모든 유형 값 또는 없음 유형의 텐서
bw_recurrent_to_forget_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
bw_recurrent_to_cell_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
bw_recurrent_to_output_weights 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서
bw_cell_to_input_weights 모든 유형 값 또는 없음 유형의 텐서
bw_cell_to_forget_weights 모든 유형 값 또는 없음 유형의 텐서
bw_cell_to_output_weights 모든 유형 값 또는 없음 유형의 텐서
bw_input_gate_bias 모든 유형 값 또는 없음 유형의 텐서
bw_forget_gate_bias 32비트 부동 소수점 값의 텐서
bw_cell_bias 32비트 부동 소수점 값의 텐서
bw_output_gate_bias 32비트 부동 소수점 값의 텐서
bw_projection_weights 모든 유형 값 또는 없음 유형의 텐서
bw_projection_bias 모든 유형 값 또는 없음 유형의 텐서
fw_input_activation_state 상태 저장 텐서
fw_input_cell_state 상태 저장 텐서
bw_input_activation_state 상태 저장 텐서
bw_input_cell_state 상태 저장 텐서
aux_input 모든 유형 값 또는 없음 유형의 텐서
fw_aux_input_to_input_weights 모든 유형 값 또는 없음 유형의 텐서
fw_aux_input_to_forget_weights 모든 유형 값 또는 없음 유형의 텐서
fw_aux_input_to_cell_weights 모든 유형 값 또는 없음 유형의 텐서
fw_aux_input_to_output_weights 모든 유형 값 또는 없음 유형의 텐서
bw_aux_input_to_input_weights 모든 유형 값 또는 없음 유형의 텐서
bw_aux_input_to_forget_weights 모든 유형 값 또는 없음 유형의 텐서
bw_aux_input_to_cell_weights 모든 유형 값 또는 없음 유형의 텐서
bw_aux_input_to_output_weights 모든 유형 값 또는 없음 유형의 텐서

결과:

결과 설명
fw_output 모든 유형 값의 텐서
bw_output 모든 유형 값의 텐서

tfl.bitcast (TFL::BitcastOp)

비트캐스트 연산자

한 유형에서 다른 유형으로 텐서를 비트캐스팅합니다.

특성: AlwaysSpeculatableImplTrait

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
input 모든 유형 값의 텐서

결과:

결과 설명
output 모든 유형 값의 텐서

tfl.bitwise_xor (TFL::BitwiseXorOp)

비트별 Xor 연산자

Elementwise는 lhsrhs 의 비트별 XOR을 계산합니다.

특성: AlwaysSpeculatableImplTrait, Commutative, SameOperandsAndResultElementType

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
lhs 8비트 무부호 정수 또는 8비트 무부호 정수 또는 16비트 무부호 정수 또는 16비트 무부호 정수 또는 32비트 무부호 정수 또는 32비트 무부호 정수 값의 텐서
rhs 8비트 무부호 정수 또는 8비트 무부호 정수 또는 16비트 무부호 정수 또는 16비트 무부호 정수 또는 32비트 무부호 정수 또는 32비트 무부호 정수 값의 텐서

결과:

결과 설명
output 8비트 무부호 정수 또는 8비트 무부호 정수 또는 16비트 무부호 정수 또는 16비트 무부호 정수 또는 32비트 무부호 정수 또는 32비트 무부호 정수 값의 텐서

tfl.broadcast_args (TFL::BroadcastArgsOp)

브로드캐스트로 s0 op s1의 모양을 반환합니다.

모양을 나타내는 텐서인 s0s1 주어지면 브로드캐스트된 모양인 r0 계산합니다. s0 , s1r0 은 모두 정수 벡터입니다.

특성: AlwaysSpeculatableImplTrait

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
s0 32/64비트 무부호 정수 값의 텐서
s1 32/64비트 무부호 정수 값의 텐서

결과:

결과 설명
r0 32/64비트 무부호 정수 값의 텐서

tfl.broadcast_to (TFL::BroadcastToOp)

호환되는 모양에 대한 배열을 브로드캐스트합니다.

브로드캐스팅은 산술 연산을 위해 호환되는 모양을 갖도록 배열을 만드는 프로세스입니다. 두 모양은 각 차원 쌍에 대해 같거나 그 중 하나가 하나인 경우 호환됩니다. Tensor를 셰이프에 브로드캐스트하려고 할 때 Tensor는 후행 차원에서 시작하여 앞으로 작업합니다.

예를 들어,

x = tf.constant([1, 2, 3]) y = tf.broadcast_to(x, [3, 3]) print(y) tf.Tensor( [[1 2 3] [1 2 3] [1 2 3]], 모양=(3, 3), dtype=int32)

위의 예에서 [1, 3] 모양의 입력 Tensor는 [3, 3] 모양의 출력 Tensor로 브로드캐스팅됩니다.

텐서에 스칼라를 곱하는 것과 같은 브로드캐스팅 작업을 수행할 때 브로드캐스팅된 텐서는 절대 구체화되지 않으므로 브로드캐스팅은 (보통) 시간적 또는 공간적 이점을 제공합니다.

그러나 broadcast_to 에는 그러한 이점이 없습니다. 새로 생성된 텐서는 브로드캐스트된 모양의 전체 메모리를 사용합니다. (그래프 컨텍스트에서 broadcast_to 후속 작업에 융합된 다음 최적화될 수 있습니다.)

특성: AlwaysSpeculateableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
input 32비트 부동 또는 32비트 부호 없는 정수 또는 1비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 8비트 부호 없는 정수 또는 QUI8 유형 또는 16비트 부호 없는 정수 또는 QI16 유형 또는 64비트 부호 없는 텐서 정수 또는 32비트 부동 요소 값이 있는 복합 유형
shape 32/64비트 무부호 정수 값의 텐서

결과:

결과 설명
output 32비트 부동 또는 32비트 부호 없는 정수 또는 1비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 8비트 부호 없는 정수 또는 QUI8 유형 또는 16비트 부호 없는 정수 또는 QI16 유형 또는 64비트 부호 없는 텐서 정수 또는 32비트 부동 요소 값이 있는 복합 유형

tfl.bucketize (TFL::BucketizeOp)

'경계'를 기준으로 '입력'을 버킷화합니다.

예:

입력이 boundaries = [0, 10, 100] 이고 input = [[-5, 10000][150, 10][5, 100]] 경우 출력은 output = [[0, 3][3, 2][1, 3]] .

특성: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
boundaries ::mlir::ArrayAttr 32비트 부동 배열 속성

피연산자:

피연산자 설명
input 32비트 부동 소수점 또는 64비트 부동 소수점 또는 32비트 무부호 정수 또는 64비트 무부호 정수 값의 텐서

결과:

결과 설명
output 32비트 부호 없는 정수 값의 텐서

tfl.call_once (TFL::CallOnceOp)

초기화 함수 호출

이 작업은 tf 저장된 모델 방언의 세션 초기화 프로그램에 대해 지정된 초기화 함수를 호출합니다.

인터페이스: TflRuntimeVerifyOpInterface

속성:

기인하다 MLIR 유형 설명
session_init_function ::mlir::문자열 속성 문자열 속성

tfl.cast (TFL::CastOp)

캐스트 연산자

입력 유형에서 출력 유형으로 입력을 캐스트합니다.

특성: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
input 16비트 부동 소수점 또는 32비트 부동 소수점 또는 64비트 부동 소수점 또는 1비트 부호 없는 정수 또는 16비트 부호 없는 정수 또는 16비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트의 텐서 부호 없는 정수 또는 TFLite quint8 유형 또는 8비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 32비트 부동 요소 값이 있는 복합 유형

결과:

결과 설명
output 16비트 부동 소수점 또는 32비트 부동 소수점 또는 64비트 부동 소수점 또는 1비트 부호 없는 정수 또는 16비트 부호 없는 정수 또는 16비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트의 텐서 부호 없는 정수 또는 TFLite quint8 유형 또는 8비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 32비트 부동 요소 값이 있는 복합 유형

tfl.ceil (TFL::CeilOp)

셀 오퍼레이터

입력의 요소별 셀 값을 반환합니다.

특성: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

인터페이스: 조건부 추측 가능, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
x 32비트 부동 소수점 값의 텐서

결과:

결과 설명
y 32비트 부동 소수점 값의 텐서

tfl.complex_abs (TFL::ComplexAbsOp)

텐서의 복소수 절댓값을 계산합니다.

복소수의 텐서 x 주어지면 이 연산은 x 에 있는 각 요소의 절대값인 float 또는 double 유형의 텐서를 반환합니다. x 의 모든 요소는 \(a + bj\)형식의 복소수여야 합니다. 절대값은 \( \sqrt{a^2 + b^2}\)으로 계산됩니다.

특성: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
input 32비트 부동 요소가 있는 복합 유형 또는 64비트 부동 요소 값이 있는 복합 유형의 텐서

결과:

결과 설명
output 32비트 부동 소수점 또는 64비트 부동 소수점 값의 텐서

tfl.concatenation (TFL::연결Op)

연결 연산자

한 차원을 따라 텐서를 연결합니다.

특성: AlwaysSpeculateableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
axis ::mlir::IntegerAttr 32비트 무부호 정수 속성
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성

피연산자:

피연산자 설명
values 모든 유형 값의 텐서

결과:

결과 설명
output 32비트 부동 또는 64비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 16비트 부호 없는 정수 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 또는 8비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 1의 텐서 -bit 무부호 정수 값

tfl.control_node (TFL::ControlNodeOp)

_ TFL.control_node 작업은 제어 에지를 연결하기 위해 단일 블록 작업을 래핑합니다. _

영역을 래핑하고 컨트롤 종속성을 연결하는 데 사용됩니다. 일반적으로 이는 고정된 작업 순서(예: 재물질화)에 의존하는 최적화를 활성화하기 위해 플랫 버퍼 모델을 내보내기 전 마지막 단계 중 하나에서 발생합니다. 플랫 버퍼 내보내기는 래핑된 영역을 풀고 생성된 모델에 메타데이터로 주석을 추가합니다. 모든 런타임 재정렬은 제어 종속성에 의해 지정된 순서를 존중합니다.

특성: HasParent mlir::func::FuncOp , RecursiveMemoryEffects, SingleBlockImplicitTerminator

피연산자:

피연산자 설명
controlInputs 제어

결과:

결과 설명
outputs 모든 유형 값의 텐서
control 제어

tfl.conv_2d (TFL::Conv2DOp)

컨볼루션 연산자

입력에 대해 컨볼루션 연산을 수행합니다.

입력: inputs[0] : 필수: 입력 활성화 텐서 inputs[1] : 필수: 필터 가중치 텐서 inputs[2] : 선택 사항: 바이어스 텐서

특성: AlwaysSpeculatableImplTrait, QuantizableResult, quant::AccumulatorUniformScale<2, 0, 1>, quant::AffineOpCoefficient<0, 1>

인터페이스: AffineQuantizedOpInterface, ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, InferTypeOpInterface, NoMemoryEffect(MemoryEffectOpInterface), TFL_SparseOp, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
dilation_h_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
dilation_w_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성
padding ::mlir::문자열 속성 값이 SAME 또는 VALID인 문자열 속성
stride_h ::mlir::IntegerAttr 32비트 무부호 정수 속성
stride_w ::mlir::IntegerAttr 32비트 무부호 정수 속성

피연산자:

피연산자 설명
input 32비트 float 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서
filter 32비트 float 또는 QI4 유형 또는 QI8 유형 또는 QUI8 유형 값의 텐서
bias 모든 유형 값 또는 없음 유형의 텐서

결과:

결과 설명
output 32비트 float 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서

tfl.conv_3d (TFL::Conv3DOp)

컨볼루션 3D 연산자

3D 입력에서 컨볼루션 연산을 수행합니다. 입력: inputs[0] : 필수: 입력 활성화 텐서 inputs[1] : 필수: 필터 가중치 텐서 inputs[2] : 선택 사항: 바이어스 텐서

특성: AlwaysSpeculatableImplTrait, quant::AccumulatorUniformScale<2, 0, 1>

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
dilation_d_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
dilation_h_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
dilation_w_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성
padding ::mlir::문자열 속성 값이 SAME 또는 VALID인 문자열 속성
stride_d ::mlir::IntegerAttr 32비트 무부호 정수 속성
stride_h ::mlir::IntegerAttr 32비트 무부호 정수 속성
stride_w ::mlir::IntegerAttr 32비트 무부호 정수 속성

피연산자:

피연산자 설명
input 32비트 부동 소수점 값의 텐서
filter 32비트 부동 소수점 값의 텐서
bias 모든 유형 값 또는 없음 유형의 텐서

결과:

결과 설명
output 32비트 부동 소수점 값의 텐서

tfl.conv_3d_transpose (TFL::Conv3DTransposeOp)

Transposed Convolution 3D 연산자

3D 입력에서 Transposed Convolution 작업을 수행합니다. 입력: inputs[0] : 필수: 출력 텐서의 모양 inputs[1] : 필수: 필터 가중치 텐서 inputs[2] : 필수: 입력 활성화 텐서 inputs[3] : 선택 사항: 바이어스 텐서

특성: AlwaysSpeculatableImplTrait, quant::AccumulatorUniformScale<2, 0, 1>

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
dilation_d_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
dilation_h_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
dilation_w_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성
padding ::mlir::문자열 속성 값이 SAME 또는 VALID인 문자열 속성
stride_d ::mlir::IntegerAttr 32비트 무부호 정수 속성
stride_h ::mlir::IntegerAttr 32비트 무부호 정수 속성
stride_w ::mlir::IntegerAttr 32비트 무부호 정수 속성

피연산자:

피연산자 설명
output_shape 32비트 부호 없는 정수 값의 텐서
filter 32비트 부동 소수점 값의 텐서
input 32비트 부동 소수점 값의 텐서
bias 모든 유형 값 또는 없음 유형의 텐서

결과:

결과 설명
output 32비트 부동 소수점 값의 텐서

tfl.cos (TFL::CosOp)

코사인 연산자

입력의 요소별 코사인을 계산합니다.

특성: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

인터페이스: 조건부 추측 가능, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
x 32비트 부동 소수점 값의 텐서

결과:

결과 설명
y 32비트 부동 소수점 값의 텐서

tfl.cumsum (TFL::CumsumOp)

누적 연산자

축을 따라 텐서 x의 누적 합계를 계산합니다.

특성: AlwaysSpeculatableImplTrait

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
exclusive ::mlir::부울 속성 부울 속성
reverse ::mlir::부울 속성 부울 속성

피연산자:

피연산자 설명
input 32비트 부동 소수점 또는 32비트 무부호 정수 또는 64비트 무부호 정수 값의 텐서
axis 32비트 부호 없는 정수 값의 텐서

결과:

결과 설명
output 32비트 부동 소수점 또는 32비트 무부호 정수 또는 64비트 무부호 정수 값의 텐서

tfl.custom (TFL::CustomOp)

맞춤 작업

모든 TFLite 사용자 지정 작업을 위한 일반 작업입니다.

입력: 원래 작업의 입력 목록입니다. custom_code: 플랫 버퍼의 operator_codes.custom_code에 해당하는 이 작업이 정확히 무엇인지 식별하는 데 사용되는 문자열입니다. custom_option: op 속성을 바이트 방식으로 저장하기 위한 홀더. 출력: 원래 작업의 출력 목록입니다.

인터페이스: TflRuntimeVerifyOpInterface

속성:

기인하다 MLIR 유형 설명
custom_code ::mlir::문자열 속성 문자열 속성
custom_option ::mlir::TFL::ConstBytesAttr 컴파일된 바이트의 문자열 속성 표현

피연산자:

피연산자 설명
input 모든 유형 값 또는 없음 유형의 텐서

결과:

결과 설명
output 모든 유형 값의 텐서

tfl.custom_tf (TFL::CustomTfOp)

TF 커스텀 작업을 위한 래퍼 작업.

Custom TF op 주변의 wrapper op. 여기에는 custom_opdefs를 사용하여 정의된 작업 또는 TF 방언으로 정의되지 않은 연결된 작업이 포함됩니다. 이 작업은 사용자 지정 작업을 영역 내부에 래핑합니다. 참고 #1, 이 작업에는 CustomOp를 사용하여 정의된 TF Lite 사용자 지정 작업이 포함되지 않습니다. 참고 #2, 이 작업은 변환기 내부의 내부 표현일 뿐이며 모델을 Flatbuffer로 내보낼 때 노출/내보내지 않습니다.

특성: IsolatedFromAbove, RecursiveMemoryEffects, SingleBlockImplicitTerminator

인터페이스: InferTypeOpInterface, TflRuntimeVerifyOpInterface

피연산자:

피연산자 설명
input 모든 유형 값 또는 없음 유형의 텐서

결과:

결과 설명
output 모든 유형 값의 텐서

tfl.densify (TFL::DensifyOp)

조밀화 연산자

희소 텐서를 고밀도 형식으로 변환합니다.

특성: AlwaysSpeculatableImplTrait

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
input 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서

결과:

결과 설명
output 32비트 부동 소수점 또는 8비트 무부호 정수 값의 텐서

tfl.depth_to_space (TFL::DepthToSpaceOp)

DepthToSpace 연산자

데이터를 깊이에서 공간 데이터 블록으로 재정렬합니다. 이것은 SpaceToDepth의 역 변환입니다. 보다 구체적으로, 이 작업은 depth 차원의 값이 공간 블록에서 heightwidth 차원으로 이동되는 입력 텐서의 복사본을 출력합니다. attr block_size 입력 블록 크기와 데이터 이동 방법을 나타냅니다.

특성: AlwaysSpeculateableImplTrait, QuantizableResult

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
block_size ::mlir::IntegerAttr 값이 양수인 32비트 부호 없는 정수 속성

피연산자:

피연산자 설명
input 32비트 부동 또는 8비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트 부호 없는 정수 또는 TFLite quint8 유형 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 값의 텐서

결과:

결과 설명
output 32비트 부동 또는 8비트 부호 없는 정수 또는 32비트 부호 없는 정수 또는 64비트 부호 없는 정수 또는 TFLite quint8 유형 또는 8비트 부호 없는 정수 또는 QI8 유형 또는 QUI8 유형 값의 텐서

tfl.depthwise_conv_2d (TFL::DepthwiseConv2DOp)

깊이 분리 가능한 컨볼루션 연산자

입력에 대해 컨볼루션 연산을 수행합니다.

입력: inputs[0] : 필수: 입력 활성화 텐서 inputs[1] : 필수: 필터 가중치 텐서 inputs[2] : 선택 사항: 바이어스 텐서

특성: AlwaysSpeculatableImplTrait, QuantizableResult, quant::AccumulatorUniformScale<2, 0, 1>, quant::AffineOpCoefficient<3, 1>

인터페이스: AffineQuantizedOpInterface, ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect(MemoryEffectOpInterface), TFL_SparseOp, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
dilation_h_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
dilation_w_factor ::mlir::IntegerAttr 32비트 무부호 정수 속성
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성
padding ::mlir::문자열 속성 값이 SAME 또는 VALID인 문자열 속성
stride_h ::mlir::IntegerAttr 32비트 무부호 정수 속성
stride_w ::mlir::IntegerAttr 32비트 무부호 정수 속성
depth_multiplier ::mlir::IntegerAttr 32비트 무부호 정수 속성

피연산자:

피연산자 설명
input 32비트 float 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서
filter 32비트 float 또는 QI4 유형 또는 QI8 유형 또는 QUI8 유형 값의 텐서
bias 모든 유형 값 또는 없음 유형의 텐서

결과:

결과 설명
output 32비트 float 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 값의 텐서

tfl.dequantize (TFL::DequantizeOp)

역양자화 연산자

양자화 매개변수에 따라 양자화된 정수 배열을 부동 소수점으로 변환합니다.

인터페이스: NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
input QI4 유형 또는 QI8 유형 또는 QUI8 유형 또는 QI16 유형 또는 16비트 부동 소수점 값의 텐서

결과:

결과 설명
output 32비트 부동 소수점 값의 텐서

tfl.div (TFL::DivOp)

나눗셈 연산자

요소별 나눗셈 연산.

특성: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, ResultsBroadcastableShape

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

속성:

기인하다 MLIR 유형 설명
fused_activation_function ::mlir::문자열 속성 값이 NONE, RELU, RELU_N1_TO_1, RELU6, TANH 또는 SIGN_BIT인 문자열 속성

피연산자:

피연산자 설명
lhs 32비트 부동 소수점 또는 32비트 부호 없는 정수 또는 QUI8 유형 값의 텐서
rhs 32비트 부동 소수점 또는 32비트 부호 없는 정수 또는 QUI8 유형 값의 텐서

결과:

결과 설명
output 32비트 부동 소수점 또는 32비트 부호 없는 정수 또는 QUI8 유형 값의 텐서

tfl.dynamic_update_slice (TFL::DynamicUpdateSliceOp)

DynamicUpdateSlice.

XLA DynamicUpdateSlice와 동일한 시맨틱을 갖는 DynamicUpdateSlice op. start_indices에서 슬라이스 업데이트를 덮어쓰는 입력 배열 피연산자의 값인 결과를 생성합니다.

https://www.tensorflow.org/xla/operation_semantics#dynamicupdateslice 참조

특성: AlwaysSpeculatableImplTrait

인터페이스: 조건부 추측 가능, NoMemoryEffect(MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

효과: MemoryEffects::Effect{}

피연산자:

피연산자 설명
operand 1비트 무부호 정수 또는 8비트 무부호 정수 또는 32비트 무부호 정수 또는 64비트 무부호 정수 또는 32비트 부동 소수점 값의 텐서
update 1비트 무부호 정수 또는 8비트 무부호 정수 또는 32비트 무부호 정수 또는 64비트 무부호 정수 또는 32비트 부동 소수점 값의 텐서
start_indices 32비트 부호 없는 정수 값의 텐서

결과:

결과 설명
output 1비트 무부호 정수 또는 8비트 무부호 정수 또는 32비트 무부호 정수 또는 64비트 무부호 정수 또는 32비트 부동 소수점 값의 텐서

tfl.elu (TFL::EluOp)

지수 선형 단위 연산자

Computes the exponential linear f(x) -> exp(x) - 1 for x < 0, x for x >= 0. element-wise.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or 8-bit signless integer values

Results:

Result 설명
y tensor of 32-bit float or 8-bit signless integer values

tfl.embedding_lookup (TFL::EmbeddingLookupOp)

Embedding lookup operator

Looks up ids in a list of embedding tensors.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lookup tensor of 32-bit signless integer values
value tensor of 32-bit float or 8-bit signless integer or 8-bit unsigned integer values

Results:

Result 설명
output tensor of 32-bit float or 8-bit signless integer or 8-bit unsigned integer values

tfl.equal (TFL::EqualOp)

Equal operator

Returns the truth element of x == y element-wise

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 1-bit signless integer or 32-bit float or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or 8-bit unsigned integer or TFLite string type values
y tensor of 1-bit signless integer or 32-bit float or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or 8-bit unsigned integer or TFLite string type values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.exp (TFL::ExpOp)

Natural exponentiation operator

Performs element-wise natural exponentiation operation on input.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or QI8 type or QI16 type values

Results:

Result 설명
y tensor of 32-bit float or QI8 type or QI16 type values

tfl.expand_dims (TFL::ExpandDimsOp)

Inserts a dimension of 1 into a tensor's shape.

Given a tensor input , this operation inserts a dimension of 1 at the dimension index axis of input 's shape. The dimension index axis starts at zero; if you specify a negative number for axis it is counted backward from the end.

This operation is useful if you want to add a batch dimension to a single element. For example, if you have a single image of shape [height, width, channels] , you can make it a batch of 1 image with expand_dims(image, 0) , which will make the shape [1, height, width, channels] .

Other examples:

# 't' is a tensor of shape [2]
shape(expand_dims(t, 0)) ==> [1, 2]
shape(expand_dims(t, 1)) ==> [2, 1]
shape(expand_dims(t, -1)) ==> [2, 1]

# 't2' is a tensor of shape [2, 3, 5]
shape(expand_dims(t2, 0)) ==> [1, 2, 3, 5]
shape(expand_dims(t2, 2)) ==> [2, 3, 1, 5]
shape(expand_dims(t2, 3)) ==> [2, 3, 5, 1]

This operation requires that:

-1-input.dims() <= dim <= input.dims()

This operation is related to squeeze() , which removes dimensions of size 1.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of any type values
dim tensor of 32/64-bit signless integer values

Results:

Result 설명
output tensor of any type values

tfl.external_const (TFL::ExternalConstOp)

External const op.

External const op holds a buffer_index which points to a constant in the flatbuffer.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
buffer_index ::mlir::IntegerAttr 32-bit signless integer attribute

Results:

Result 설명
output tensor of any type values

tfl.fake_quant (TFL::FakeQuantOp)

FakeQuant operator

Fake-quantize the 'inputs' tensor of type float via float scalars min and max to 'outputs' tensor of same shape as inputs.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
min ::mlir::FloatAttr 32-bit float attribute
max ::mlir::FloatAttr 32-bit float attribute
num_bits ::mlir::IntegerAttr 32-bit signless integer attribute whose minimum value is 2 whose maximum value is 16
narrow_range ::mlir::BoolAttr bool attribute whose value is false

Operands:

Operand 설명
input tensor of 32-bit float values

Results:

Result 설명
output tensor of 32-bit float values

tfl.fill (TFL::FillOp)

Fill the tensor with given value.

Fill the tensor with given value.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
dims tensor of 32/64-bit signless integer values
input tensor of 32-bit float or 16-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or QI8 type or QI16 type or TFLite string type values

Results:

Result 설명
result tensor of 32-bit float or 16-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or QI8 type or QI16 type or TFLite string type values

tfl.floor (TFL::FloorOp)

Floor operator

Returns element-wise floor value of the input.

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float values

Results:

Result 설명
y tensor of 32-bit float values

tfl.floor_div (TFL::FloorDivOp)

Floor div operator

Element-wise floor div operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer values
rhs tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer values

tfl.floor_mod (TFL::FloorModOp)

Division reminder

Element-wise division reminder operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit float values
rhs tensor of 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit float values

Results:

Result 설명
output tensor of 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit float values

tfl.fully_connected (TFL::FullyConnectedOp)

Fully connected op

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, quant::AccumulatorUniformScale<2, 0, 1>, quant::AffineOpCoefficient<-1, 1>

Interfaces: AffineQuantizedOpInterface, ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TFL_SparseOp, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
weights_format ::mlir::StringAttr string attribute whose value is DEFAULT, or SHUFFLED4x16INT8
keep_num_dims ::mlir::BoolAttr bool attribute
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or QUI16 type values
filter tensor of 32-bit float or QI4 type or QI8 type or QUI8 type or QI16 type values
bias tensor of any type values or none type

Results:

Result 설명
output tensor of any type values

tfl.gather (TFL::GatherOp)

Gather operator

Gather slices from params axis axis according to indices .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
axis ::mlir::IntegerAttr 32-bit signless integer attribute
batch_dims ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand 설명
params tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or TFLite string type or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values
indices tensor of 16-bit signless integer or 32-bit signless integer or 64-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or TFLite string type or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values

tfl.gather_nd (TFL::GatherNdOp)

_Gather nd operator

Gather slices from params into a Tensor with shape specified by indices .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
params tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 64-bit signless integer or 32-bit signless integer or 8-bit unsigned integer or TFLite string type values
indices tensor of 16-bit signless integer or 32-bit signless integer or 64-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 64-bit signless integer or 32-bit signless integer or 8-bit unsigned integer or TFLite string type values

tfl.gelu (TFL::GeluOp)

GELU activation function.

Computes GELU activation function element-wise.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
approximate ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or QI8 type or QUI8 type values

Results:

Result 설명
output tensor of 32-bit float or QI8 type or QUI8 type values

tfl.greater (TFL::GreaterOp)

Greater operator

Element-wise greater operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.greater_equal (TFL::GreaterEqualOp)

_Greater equal operator

Element-wise greater_equal operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type values
rhs tensor of 32-bit float or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.hard_swish (TFL::HardSwishOp)

Hardswish activation function.

Computes hard-swish activation function f(x) -> (x * relu6(x+3))/6 element-wise.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or QUI8 type or QI8 type values

Results:

Result 설명
output tensor of 32-bit float or QUI8 type or QI8 type values

tfl.hashtable (TFL::HashtableOp)

Creates a non-initialized hash table.

This op creates a hash table, specifying the type of its keys and values. Before using the table you will have to initialize it. After initialization the table will be immutable.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
table_id ::mlir::IntegerAttr 32-bit signless integer attribute
key_dtype ::mlir::TypeAttr any type attribute
value_dtype ::mlir::TypeAttr any type attribute

Results:

Result 설명
out tensor of resource values

tfl.hashtable_find (TFL::HashtableFindOp)

Looks up keys in a table, outputs the corresponding values.

The tensor keys must of the same type as the keys of the table. The output values is of the type of the table values.

The scalar default_value is the value output for keys not present in the table. It must also be of the same type as the table values.

Interfaces: TflRuntimeVerifyOpInterface

Operands:

Operand 설명
hash_table tensor of resource values
keys tensor of 32-bit signless integer or TFLite string type or 64-bit signless integer values
default_value tensor of 32-bit float or 32-bit signless integer or TFLite string type or 64-bit signless integer values

Results:

Result 설명
out tensor of 32-bit float or 32-bit signless integer or TFLite string type or 64-bit signless integer values

tfl.hashtable_import (TFL::HashtableImportOp)

_ Replaces the contents of the table with the specified keys and values. _

The tensor keys must be of the same type as the keys of the table. The tensor values must be of the type of the table values.

Interfaces: TflRuntimeVerifyOpInterface

Operands:

Operand 설명
hash_table tensor of resource values
keys tensor of 32-bit signless integer or TFLite string type or 64-bit signless integer values
values tensor of 32-bit float or 32-bit signless integer or TFLite string type or 64-bit signless integer values

tfl.hashtable_size (TFL::HashtableSizeOp)

Computes the number of elements in the given table.

Interfaces: TflRuntimeVerifyOpInterface

Operands:

Operand 설명
hash_table tensor of resource values

Results:

Result 설명
out tensor of 64-bit signless integer values

tfl.if (TFL::IfOp)

If-then-else operation

The tfl.if operation represents an if-then-else construct for conditionally executing two regions of code. The operand to an if operation is a boolean value. For example:

tfl.if %b  {
  ...
} else {
  ...
}

tfl.if may also return results that are defined in its regions. The values defined are determined by which execution path is taken.

Example:

%x, %y = tfl.if %b -> (tensor<f32>, tensor<f32>) {
  %x_true = ...
  %y_true = ...
  tfl.yield %x_true, %y_true : tensor<f32>, tensor<f32>
} else {
  %x_false = ...
  %y_false = ...
  tfl.yield %x_false, %y_false : tensor<f32>, tensor<f32>
}

tfl.if regions are always terminated with "tfl.yield". If "tfl.if" defines no values, the "tfl.yield" can be left out, and will be inserted implicitly. Otherwise, it must be explicit. Also, if "tfl.if" defines one or more values, the 'else' block cannot be omitted.

Example:

tfl.if %b  {
  ...
}

Traits: NoRegionArguments, RecursiveMemoryEffects, SingleBlockImplicitTerminator

Interfaces: RegionBranchOpInterface, TflRuntimeVerifyOpInterface

Operands:

Operand 설명
cond tensor of 1-bit signless integer values

Results:

Result 설명
results tensor of any type values

tfl.imag (TFL::ImagOp)

Returns the imaginary part of a complex number.

Given a tensor input of complex numbers, this operation returns a tensor of type float that is the imaginary part of each element in input . All elements in input must be complex numbers of the form \(a + bj\), where a is the real part and b is the imaginary part returned by this operation.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of complex type with 32-bit float elements or complex type with 64-bit float elements values

Results:

Result 설명
output tensor of 32-bit float or 64-bit float values

tfl.l2_normalization (TFL::L2NormalizationOp)

L2 Normalize Operator

L2Normalization Op

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand 설명
input tensor of 32-bit float or QUI8 type or QI8 type or QUI16 type or QI16 type or 8-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or QUI8 type or QI8 type or QUI16 type or QI16 type or 8-bit signless integer values

tfl.leaky_relu (TFL::LeakyReluOp)

Leaky Relu operator

Element-wise Leaky ReLU operator x -> x >= 0 ? x : (alpha * x)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
alpha ::mlir::FloatAttr 32-bit float attribute

Operands:

Operand 설명
input tensor of 32-bit float or QUI8 type or QI8 type or TFLite quint8 type or QI16 type values

Results:

Result 설명
output tensor of 32-bit float or QUI8 type or QI8 type or TFLite quint8 type or QI16 type values

tfl.less (TFL::LessOp)

Less operator

Element-wise less operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type values
rhs tensor of 32-bit float or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.less_equal (TFL::LessEqualOp)

_Less equal operator

Element-wise less_equal operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.local_response_normalization (TFL::LocalResponseNormalizationOp)

Local Response Normalization.

The 4-D input tensor is treated as a 3-D array of 1-D vectors (along the last dimension), and each vector is normalized independently. Within a given vector, each component is divided by the weighted, squared sum of inputs within depth_radius . In detail,

sqr_sum[a, b, c, d] =
    sum(input[a, b, c, d - depth_radius : d + depth_radius + 1] ** 2)
output = input / (bias + alpha * sqr_sum) ** beta

For details, see Krizhevsky et al., ImageNet classification with deep convolutional neural networks (NIPS 2012) .

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
radius ::mlir::IntegerAttr 32-bit signless integer attribute
bias ::mlir::FloatAttr 32-bit float attribute
alpha ::mlir::FloatAttr 32-bit float attribute
beta ::mlir::FloatAttr 32-bit float attribute

Operands:

Operand 설명
input tensor of 32-bit float values

Results:

Result 설명
output tensor of 32-bit float values

tfl.log (TFL::LogOp)

Natural logarithm operator

Performs element-wise natural logarithm operation on input.

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float values

Results:

Result 설명
y tensor of 32-bit float values

tfl.log_softmax (TFL::LogSoftmaxOp)

Log softmax operator

Computes element-wise log softmax activations with the following formula

input - log(reduce_sum(exp(input), dim))

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or QUI8 type or QI8 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or QUI8 type or QI8 type or TFLite quint8 type values

tfl.logical_and (TFL::LogicalAndOp)

Logical AND operator

Element-wise logical AND operation.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 1-bit signless integer values
rhs tensor of 1-bit signless integer values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.logical_not (TFL::LogicalNotOp)

Logical NOT operator

Element-wise logical NOT operation.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 1-bit signless integer values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.logical_or (TFL::LogicalOrOp)

Logical OR operator

Element-wise logical OR operation.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 1-bit signless integer values
rhs tensor of 1-bit signless integer values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.logistic (TFL::LogisticOp)

Logistic operator

Computes element-wise Sigmoid of input

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result 설명
y tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.lstm (TFL::LSTMOp)

The full lstm operator

Long short-term memory unit (LSTM) recurrent network layer. The default non-peephole implementation is based on: http://deeplearning.cs.cmu.edu/pdfs/Hochreiter97_lstm.pdf S. Hochreiter and J. Schmidhuber. 'Long Short-Term Memory'. Neural Computation, 9(8):1735-1780, 1997. The peephole implementation is based on: https://research.google.com/pubs/archive/43905.pdf Hasim Sak, Andrew Senior, and Francoise Beaufays. 'Long short-term memory recurrent neural network architectures for large scale acoustic modeling.' INTERSPEECH, 2014. The coupling of input and forget gate (CIFG) is based on: http://arxiv.org/pdf/1503.04069.pdf Greff et al. 'LSTM: A Search Space Odyssey' The layer normalization is based on: https://arxiv.org/pdf/1607.06450.pdf Ba et al. 'Layer Normalization'

Traits: QuantizableResult

Interfaces: DynamicRangeQuantizedOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
cell_clip ::mlir::FloatAttr 32-bit float attribute whose value is non-negative
proj_clip ::mlir::FloatAttr 32-bit float attribute whose value is non-negative
kernel_type ::mlir::TFL::LSTMKernelTypeAttr lstm_kernel_type whose value is mlir::TFL::LSTMKernelType::FULL
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute
input_to_input_intermediate ::mlir::TypeAttr any type attribute
input_to_forget_intermediate ::mlir::TypeAttr any type attribute
input_to_cell_intermediate ::mlir::TypeAttr any type attribute
input_to_output_intermediate ::mlir::TypeAttr any type attribute
effective_hidden_scale_intermediate ::mlir::TypeAttr any type attribute

Operands:

Operand 설명
input tensor of 32-bit float or QI8 type or QI16 type values
input_to_input_weights tensor of any type values or none type
input_to_forget_weights tensor of 32-bit float or QI8 type values
input_to_cell_weights tensor of 32-bit float or QI8 type values
input_to_output_weights tensor of 32-bit float or QI8 type values
recurrent_to_input_weights tensor of any type values or none type
recurrent_to_forget_weights tensor of 32-bit float or QI8 type values
recurrent_to_cell_weights tensor of 32-bit float or QI8 type values
recurrent_to_output_weights tensor of 32-bit float or QI8 type values
cell_to_input_weights tensor of any type values or none type
cell_to_forget_weights tensor of any type values or none type
cell_to_output_weights tensor of any type values or none type
input_gate_bias tensor of any type values or none type
forget_gate_bias tensor of 32-bit float or QI32 type values
cell_bias tensor of 32-bit float or QI32 type values
output_gate_bias tensor of 32-bit float or QI32 type values
projection_weights tensor of any type values or none type
projection_bias tensor of any type values or none type
input_activation_state stateful tensor
input_cell_state stateful tensor
input_layer_norm_coefficients tensor of any type values or none type
forget_layer_norm_coefficients tensor of any type values or none type
cell_layer_norm_coefficients tensor of any type values or none type
output_layer_norm_coefficients tensor of any type values or none type

Results:

Result 설명
output tensor of any type values

tfl.matrix_diag (TFL::MatrixDiagOp)

_ Returns a tensor with the provided diagonal and everything else padded with zeros. _

Given a diagonal, returns a tensor with the diagonal and everything else padded with zeros. Assume diagonal has k dimensions [I, J, K, ..., N] , then the output is a tensor of rank k+1 with dimensions [I, J, K, ..., N, N] where: output[i, j, k, ..., m, n] = 1{m=n} * diagonal[i, j, k, ..., n].

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
diagonal tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QUI8 type or QI8 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QUI8 type or QI8 type or TFLite quint8 type values

tfl.matrix_set_diag (TFL::MatrixSetDiagOp)

_ Returns a batched matrix tensor with new batched diagonal values. _

Given input and diagonal , this operation returns a tensor with the same shape and values as input , except for the main diagonal of the innermost matrices. These will be overwritten by the values in diagonal .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QI16 type or QUI8 type or TFLite quint8 type values
diagonal tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QI16 type or QUI8 type or TFLite quint8 type values

Results:

Result 설명
result tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QI16 type or QUI8 type or TFLite quint8 type values

tfl.max_pool_2d (TFL::MaxPool2DOp)

Max Pool 2D op

Performs max pool 2D on input.

Inputs: inputs[0] : required: the input tensor

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
padding ::mlir::StringAttr string attribute whose value is SAME, or VALID
stride_w ::mlir::IntegerAttr 32-bit signless integer attribute
stride_h ::mlir::IntegerAttr 32-bit signless integer attribute
filter_width ::mlir::IntegerAttr 32-bit signless integer attribute
filter_height ::mlir::IntegerAttr 32-bit signless integer attribute
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand 설명
input tensor of 32-bit float or QUI8 type or QI8 type or QI16 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or QUI8 type or QI8 type or QI16 type or TFLite quint8 type values

tfl.maximum (TFL::MaximumOp)

Max operator

Element-wise max operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values
rhs tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values

Results:

Result 설명
max tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values

tfl.mean (TFL::MeanOp)

Mean operator

Computes the mean of elements across dimensions of a tensor. Reduces input_tensor along the dimensions given in axis. Unless keepdims is true, the rank of the tensor is reduced by 1 for each entry in axis. If keepdims is true, the reduced dimensions are retained with length 1.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or 8-bit unsigned integer or QI16 type values
axis tensor of 32-bit signless integer or 64-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or 8-bit unsigned integer or QI16 type values

tfl.minimum (TFL::MinimumOp)

Min operator

Element-wise min operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values
rhs tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values

Results:

Result 설명
min tensor of 32-bit float or 32/64-bit signless integer or QI8 type or QUI8 type or QI16 type values

tfl.mirror_pad (TFL::MirrorPadOp)

MirrorPad Operator. Pads a tensor with mirrored values.

This operation pads a input with mirrored values according to the paddings you specify. paddings is an integer tensor with shape [n, 2], where n is the rank of input. For each dimension D of input, paddings[D, 0] indicates how many values to add before the contents of input in that dimension, and paddings[D, 1] indicates how many values to add after the contents of input in that dimension.

Both paddings[D, 0] and paddings[D, 1] must be no greater than input.dim_size(D) (or input.dim_size(D) - 1) if copy_border is true (if false, respectively).

The padded size of each dimension D of the output is:

paddings(D, 0) + input.dim_size(D) + paddings(D, 1)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
mode ::mlir::TFL::MirrorPaddingTypeAttr mirror_pad_enum

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values
pad tensor of 32-bit signless integer or 64-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values

tfl.mul (TFL::MulOp)

Multiplication operator

Element-wise multiplication operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand 설명
lhs tensor of 32-bit float or 32-bit signless integer or 32-bit unsigned integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or 16-bit signless integer or complex type with 32-bit float elements values
rhs tensor of 32-bit float or 32-bit signless integer or 32-bit unsigned integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or 16-bit signless integer or complex type with 32-bit float elements values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 32-bit unsigned integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type or 16-bit signless integer or complex type with 32-bit float elements values

tfl.multinomial (TFL::MultinomialOp)

Draws samples from a categorical distribution.

The generated values will have a categorical distribution based on the logits or unnormalized log-probabilities provided for all classes.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
seed ::mlir::IntegerAttr 64-bit signless integer attribute
seed2 ::mlir::IntegerAttr 64-bit signless integer attribute

Operands:

Operand 설명
logits tensor of 32-bit float values
num_samples tensor of 32-bit signless integer values

Results:

Result 설명
out tensor of 32-bit signless integer or 64-bit signless integer values

tfl.neg (TFL::NegOp)

Negation operator

Computes element-wise negation of input

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer values

Results:

Result 설명
y tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer values

tfl.no_value (TFL::NoValueOp)

Constant representing no value.

No value constant op.

Traits: AlwaysSpeculatableImplTrait, ConstantLike

Interfaces: ConditionallySpeculatable, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface)

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
value ::mlir::UnitAttr unit attribute

Results:

Result 설명
none_val none type

tfl.non_max_suppression_v4 (TFL::NonMaxSuppressionV4Op)

_ Greedily selects a subset of bounding boxes in descending order of score, _

pruning away boxes that have high intersection-over-union (IOU) overlap with previously selected boxes. Bounding boxes with score less than score_threshold are removed. Bounding boxes are supplied as [y1, x1, y2, x2], where (y1, x1) and (y2, x2) are the coordinates of any diagonal pair of box corners and the coordinates can be provided as normalized (ie, lying in the interval [0, 1]) or absolute. Note that this algorithm is agnostic to where the origin is in the coordinate system and more generally is invariant to orthogonal transformations and translations of the coordinate system; thus translating or reflections of the coordinate system result in the same boxes being selected by the algorithm. The output of this operation is a set of integers indexing into the input collection of bounding boxes representing the selected boxes. The bounding box coordinates corresponding to the selected indices can then be obtained using the tf.gather operation . For example: selected_indices = tf.image.non_max_suppression_v2( boxes, scores, max_output_size, iou_threshold, score_threshold) selected_boxes = tf.gather(boxes, selected_indices)

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
boxes tensor of 32-bit float values
scores tensor of 32-bit float values
max_output_size tensor of 32-bit signless integer values
iou_threshold tensor of 32-bit float values
score_threshold tensor of 32-bit float values

Results:

Result 설명
selected_indices tensor of 32-bit signless integer values
valid_outputs tensor of 32-bit signless integer values

tfl.non_max_suppression_v5 (TFL::NonMaxSuppressionV5Op)

_ Greedily selects a subset of bounding boxes in descending order of score, _

pruning away boxes that have high intersection-over-union (IOU) overlap with previously selected boxes. Bounding boxes with score less than score_threshold are removed. Bounding boxes are supplied as [y1, x1, y2, x2], where (y1, x1) and (y2, x2) are the coordinates of any diagonal pair of box corners and the coordinates can be provided as normalized (ie, lying in the interval [0, 1]) or absolute. Note that this algorithm is agnostic to where the origin is in the coordinate system and more generally is invariant to orthogonal transformations and translations of the coordinate system; thus translating or reflections of the coordinate system result in the same boxes being selected by the algorithm. The output of this operation is a set of integers indexing into the input collection of bounding boxes representing the selected boxes. The bounding box coordinates corresponding to the selected indices can then be obtained using the tf.gather operation . For example: selected_indices = tf.image.non_max_suppression_v2( boxes, scores, max_output_size, iou_threshold, score_threshold) selected_boxes = tf.gather(boxes, selected_indices) This op also supports a Soft-NMS (with Gaussian weighting) mode (cf Bodla et al, https://arxiv.org/abs/1704.04503 ) where boxes reduce the score of other overlapping boxes instead of directly causing them to be pruned. To enable this Soft-NMS mode, set the soft_nms_sigma parameter to be larger than 0.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
boxes tensor of 32-bit float values
scores tensor of 32-bit float values
max_output_size tensor of 32-bit signless integer values
iou_threshold tensor of 32-bit float values
score_threshold tensor of 32-bit float values
soft_nms_sigma tensor of 32-bit float values

Results:

Result 설명
selected_indices tensor of 32-bit signless integer values
selected_scores tensor of 32-bit float values
valid_outputs tensor of 32-bit signless integer values

tfl.not_equal (TFL::NotEqualOp)

_Not equal operator

Element-wise not_equal operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, Commutative, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 1-bit signless integer or 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type or TFLite string type values
rhs tensor of 1-bit signless integer or 32-bit float or 32-bit signless integer or 64-bit signless integer or QUI8 type or QI8 type or TFLite quint8 type or TFLite string type values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.NumericVerify (TFL::NumericVerifyOp)

Verifies the numericals of the two operands

The NumericVerify op is a debugging op to verify the numericals of the two activations. It is a custom op in TFLite. If log_if_failed is true, the NumericVerify op calculates statistics on differences between float and quantized activations, output logs, set differences to the output tensors, and throws an error if errors above tolerance exist. If log_if_failed = false, then it doesn't care about errors.

Traits: QuantizableResult, SameOperandsShape

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
tolerance ::mlir::FloatAttr 32-bit float attribute
log_if_failed ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of QI8 type or QUI8 type or QI16 type or 16-bit float or TFLite quint8 type values
ref tensor of 32-bit float values

Results:

Result 설명
output tensor of 32-bit float values

tfl.one_hot (TFL::OneHotOp)

OneHot operator

Returns a one-hot tensor.The locations represented by indices in indices take value on_value , while all other locations take value off_value .

If the input indices is rank N , the output will have rank N+1 , The new axis is created at dimension axis (default: the new axis is appended at the end).

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
axis ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand 설명
indices tensor of 32-bit signless integer or 64-bit signless integer values
depth tensor of 32-bit signless integer values
on_value tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or 8-bit signless integer or 8-bit unsigned integer values
off_value tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or 8-bit signless integer or 8-bit unsigned integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 1-bit signless integer or 8-bit signless integer or 8-bit unsigned integer values

tfl.pack (TFL::PackOp)

Packs a list of tensors along a dimension into one tensor

Packs a list of values_count rank- R tensors into one rank- (R+1) tensor.

Packs the values_count tensors in values into a tensor with rank one higher than each tensor in values , by packing them along the axis dimension.

Given a list of tensors of shape (A, B, C) ;

if axis == 0 then the output tensor will have the shape (N, A, B, C) . if axis == 1 then the output tensor will have the shape (A, N, B, C) . Etc.

For example:

# 'x' is [1, 4]
# 'y' is [2, 5]
# 'z' is [3, 6]
pack([x, y, z]) => [[1, 4], [2, 5], [3, 6]]  # Pack along first dim.
pack([x, y, z], axis=1) => [[1, 2, 3], [4, 5, 6]]

This is the opposite of unpack .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
values_count ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive
axis ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand 설명
values tensor of any type values

Results:

Result 설명
output tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or 32-bit unsigned integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.pad (TFL::PadOp)

Padding operator

This operation pads a input with zeros according to the paddings you specify. paddings is an integer tensor with shape [Dn, 2] , where n is the rank of input . For each dimension D of input , paddings[D, 0] indicates how many zeros to add before the contents of input in that dimension, and paddings[D, 1] indicates how many zeros to add after the contents of input in that dimension.

The padded size of each dimension D of the output is:

paddings(D, 0) + input.dim_size(D) + paddings(D, 1)

For example:

# 't' is [[1, 1], [2, 2]]
# 'paddings' is [[1, 1], [2, 2]]
# rank of 't' is 2
pad(t, paddings) ==> [[0, 0, 0, 0, 0, 0]
                      [0, 0, 1, 1, 0, 0]
                      [0, 0, 2, 2, 0, 0]
                      [0, 0, 0, 0, 0, 0]]

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
padding tensor of 32/64-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.padv2 (TFL::PadV2Op)

Padding operator v2

This operation pads a input according to the paddings and constant_values you specify. paddings is an integer tensor with shape [Dn, 2] , where n is the rank of input . For each dimension D of input , paddings[D, 0] indicates how many zeros to add before the contents of input in that dimension, and paddings[D, 1] indicates how many zeros to add after the contents of input in that dimension. constant_values is a scalar tensor of the same type as input that indicates the value to use for padding input .

The padded size of each dimension D of the output is:

paddings(D, 0) + input.dim_size(D) + paddings(D, 1)

For example:

# 't' is [[1, 1], [2, 2]]
# 'paddings' is [[1, 1], [2, 2]]
# rank of 't' is 2
pad(t, paddings) ==> [[0, 0, 0, 0, 0, 0]
                      [0, 0, 1, 1, 0, 0]
                      [0, 0, 2, 2, 0, 0]
                      [0, 0, 0, 0, 0, 0]]

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type values
padding tensor of 32/64-bit signless integer values
constant_values tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type values

tfl.poly_call (TFL::PolyCallOp)

Poly call

Have multiple function bodies for the same computation. This allows a program compiler/interpreter to choose one of the available options to execute the program based on which one is most suitable for the target backend.

input: A list of input tensors whose types are T. output: A list of output tensors whose types are T.

call: Multiple regions, each of which encapsulates the same semantic computation but in different forms.

Traits: SingleBlockImplicitTerminator

Interfaces: RegionBranchOpInterface

Operands:

Operand 설명
input tensor of any type values

Results:

Result 설명
output tensor of any type values

tfl.pow (TFL::PowOp)

Power operator

Element-wise power operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 32-bit signless integer values
rhs tensor of 32-bit float or 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer values

tfl.prelu (TFL::PReluOp)

Parameterized Relu operator

Parameterized Relu operator x -> x >= 0 ? x : (alpha * x) where alpha is a trainable tensor. input and alpha should be the same size as input or be broadcastable.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape, quant::AffineOpCoefficient<-1, 1>

Interfaces: AffineQuantizedOpInterface, ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type values
alpha tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type values

tfl.pseudo_const (TFL::ConstOp)

Constant pseudo op.

Represents a constant value in TensorFlow Lite dialect. This is not an actual operation and it will be lowered to buffer instead.

The op is allowed to have all the same type of attributes as tf.Const does (eg, opaque TF attributes are allowed).

Traits: AlwaysSpeculatableImplTrait, ConstantLike, FirstAttrDerivedResultType, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
value ::mlir::ElementsAttr constant vector/tensor attribute

Results:

Result 설명
output tensor of any type values

tfl.pseudo_qconst (TFL::QConstOp)

Quantized constant pseudo op

Represents a quantized constant value in TensorFlow Lite dialect. This is not an actual operation and it will be lowered to buffer instead. The quantization parameters are stored as a type attribute in this constant.

Traits: AlwaysSpeculatableImplTrait, FirstAttrDerivedResultType

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface)

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
qtype ::mlir::TypeAttr Tensor type attribute
value ::mlir::ElementsAttr constant vector/tensor attribute

Results:

Result 설명
output tensor of QUI8 type or QI8 type or QI16 type or QUI16 type or TFLite quint8 type values

tfl.pseudo_sparse_const (TFL::SparseConstOp)

Sparse constant pseudo op.

Represents a sparse constant value in TensorFlow Lite dialect. This is not an actual operation and it will be lowered to buffer instead.

Traits: AlwaysSpeculatableImplTrait, FirstAttrDerivedResultType, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
value ::mlir::ElementsAttr constant vector/tensor attribute
s_param ::mlir::TFL::SparsityParameterAttr Sparsity parameter.
compressed_data ::mlir::ElementsAttr constant vector/tensor attribute

Results:

Result 설명
output tensor of any type values

tfl.pseudo_sparse_qconst (TFL::SparseQConstOp)

Sparse quantized constant pseudo op

Represents a sparse quantized constant value in TensorFlow Lite dialect. This is not an actual operation and it will be lowered to buffer instead. The quantization parameters are stored as a type attribute in this constant.

Traits: AlwaysSpeculatableImplTrait, FirstAttrDerivedResultType

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
qtype ::mlir::TypeAttr Tensor type attribute
value ::mlir::ElementsAttr constant vector/tensor attribute
s_param ::mlir::TFL::SparsityParameterAttr Sparsity parameter.
compressed_data ::mlir::ElementsAttr constant vector/tensor attribute

Results:

Result 설명
output tensor of QUI8 type or QI8 type or QI16 type or QUI16 type or TFLite quint8 type values

tfl.quantize (TFL::QuantizeOp)

Quantize operator

Converts floating point tensors to quantized integer tensors according to the quantization parameters defined in the type attribute.

Traits: FirstAttrDerivedResultType, SameOperandsAndResultShape

Interfaces: NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
qtype ::mlir::TypeAttr Tensor type attribute

Operands:

Operand 설명
input tensor of 32-bit float or QI4 type or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result 설명
output tensor of QI4 type or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.random_standard_normal (TFL::RandomStandardNormalOp)

Outputs random values from a normal distribution.

The generated values will have mean 0 and standard deviation 1.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
seed ::mlir::IntegerAttr 64-bit signless integer attribute
seed2 ::mlir::IntegerAttr 64-bit signless integer attribute

Operands:

Operand 설명
shape tensor of 32-bit signless integer values

Results:

Result 설명
out tensor of 32-bit float values

tfl.random_uniform (TFL::RandomUniformOp)

Outputs random values from a uniform distribution.

The generated values follow a uniform distribution in the range [0, 1) . The lower bound 0 is included in the range, while the upper bound 1 is excluded.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
seed ::mlir::IntegerAttr 64-bit signless integer attribute
seed2 ::mlir::IntegerAttr 64-bit signless integer attribute

Operands:

Operand 설명
shape tensor of 32-bit signless integer values

Results:

Result 설명
out tensor of 32-bit float values

tfl.range (TFL::RangeOp)

Range operator

Returns a 1D tensor defined by a sequence from start to limit with a given delta .

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
start tensor of 32-bit signless integer or 32-bit float or 64-bit signless integer values
limit tensor of 32-bit signless integer or 32-bit float or 64-bit signless integer values
delta tensor of 32-bit signless integer or 32-bit float or 64-bit signless integer values

Results:

Result 설명
result tensor of 32-bit signless integer or 32-bit float or 64-bit signless integer values

tfl.rank (TFL::RankOp)

Rank operator.

Returns the rank of a tensor.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of any type values

Results:

Result 설명
output tensor of any integer type

tfl.read_variable (TFL::ReadVariableOp)

Reads variable value.

Read variable data identified by 'resource_id'.

Interfaces: TflRuntimeVerifyOpInterface

Operands:

Operand 설명
resource_id tensor of resource values

Results:

Result 설명
result tensor of 32-bit float or 64-bit float or 1-bit signless integer or 8-bit unsigned integer or 8-bit signless integer or QI8 type or QUI8 type or 32-bit signless integer or 64-bit signless integer or QI16 type or complex type with 32-bit float elements or complex type with 64-bit float elements values

tfl.real (TFL::RealOp)

Returns the real part of a complex number.

Given a tensor input of complex numbers, this operation returns a tensor of type float that is the real part of each element in input . All elements in input must be complex numbers of the form \(a + bj\), where a is the real part returned by this operation and b is the imaginary part.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of complex type with 32-bit float elements or complex type with 64-bit float elements values

Results:

Result 설명
output tensor of 32-bit float or 64-bit float values

tfl.reduce_all (TFL::ReduceAllOp)

_ Computes the "logical and" of elements across dimensions of a tensor. _

Reduces input along the dimensions given in axis . Unless keep_dims is true, the rank of the tensor is reduced by 1 for each entry in axis . If keep_dims is true, the reduced dimensions are retained with length 1.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 1-bit signless integer values
reduction_indices tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.reduce_any (TFL::ReduceAnyOp)

_ Computes the "logical or" of elements across dimensions of a tensor. _

Reduces input along the dimensions given in axis . Unless keep_dims is true, the rank of the tensor is reduced by 1 for each entry in axis . If keep_dims is true, the reduced dimensions are retained with length 1.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 1-bit signless integer values
reduction_indices tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 1-bit signless integer values

tfl.reduce_max (TFL::ReduceMaxOp)

Max-reduction operator

Computes the max reduction along the specified axes

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
axes tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.reduce_min (TFL::ReduceMinOp)

Min-reduction operator

Computes the min reduction along the specified axes

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
axes tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.reduce_prod (TFL::ReduceProdOp)

Prod-reduction operator

Computes the product along the specified axes

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
axes tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.relu (TFL::ReluOp)

Relu operator

Element-wise Relu operator x -> max(0, x)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or QUI8 type or QI8 type or QI16 type values

Results:

Result 설명
y tensor of 32-bit float or QUI8 type or QI8 type or QI16 type values

tfl.relu6 (TFL::Relu6Op)

Relu6 operator

Element-wise Relu6 operator x -> max(0, min(6, x))

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or QUI8 type or QI8 type values

Results:

Result 설명
y tensor of 32-bit float or QUI8 type or QI8 type values

tfl.relu_0_to_1 (TFL::Relu0To1Op)

Relu0To1 operator

Element-wise Relu0To1 operator x -> max(0, min(1, x))

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or QUI8 type or QI8 type values

Results:

Result 설명
y tensor of 32-bit float or QUI8 type or QI8 type values

tfl.relu_n1_to_1 (TFL::Relu1Op)

Relu1 operator

Element-wise Relu1 operator x -> max(-1, min(1, x))

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or QUI8 type or QI8 type values

Results:

Result 설명
y tensor of 32-bit float or QUI8 type or QI8 type values

tfl.reshape (TFL::ReshapeOp)

Reshape operator

Produces a tensor with the same values but different static shape defined by the output type.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of any type values
shape tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of any type values

tfl.resize_bilinear (TFL::ResizeBilinearOp)

ResizeBilinear Op

Resize images to size using bilinear interpolation.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
align_corners ::mlir::BoolAttr bool attribute
half_pixel_centers ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or TFLite quint8 type or QUI8 type or QI8 type or QI16 type values
size tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or TFLite quint8 type or QUI8 type or QI8 type or QI16 type values

tfl.resize_nearest_neighbor (TFL::ResizeNearestNeighborOp)

ResizeNearestNeighbor Op

Resize images to size using nearest neighbor interpolation.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
align_corners ::mlir::BoolAttr bool attribute
half_pixel_centers ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or TFLite quint8 type or QUI8 type or QI8 type or QI16 type values
size tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or TFLite quint8 type or QUI8 type or QI8 type or QI16 type values

tfl.reverse_sequence (TFL::ReverseSequenceOp)

Reverses variable length slices.

This op first slices input along the dimension batch_dim , and for each slice i , reverses the first seq_lengths[i] elements along the dimension seq_dim .

The elements of seq_lengths must obey seq_lengths[i] <= input.dims[seq_dim] , and seq_lengths must be a vector of length input.dims[batch_dim] .

The output slice i along dimension batch_dim is then given by input slice i , with the first seq_lengths[i] slices along dimension seq_dim reversed.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
seq_dim ::mlir::IntegerAttr 32-bit signless integer attribute whose value is non-negative
batch_dim ::mlir::IntegerAttr 32-bit signless integer attribute whose value is non-negative

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI16 type or QUI8 type or TFLite quint8 type values
seq_lengths tensor of 32/64-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI16 type or QUI8 type or TFLite quint8 type values

tfl.reverse_v2 (TFL::ReverseV2Op)

ReverseV2 Operator

Reverses specific dimensions of a tensor.

Given a tensor, and a int32/int64 tensor axis representing the set of dimensions of tensor to reverse. This operation reverses each dimension i for which there exists j st axis[j] == i.

Args: tensor: A Tensor. Must be one of the following types: uint8, int8, int16, int32, int64, float32, bool Up to 8-D.

axis: A Tensor. Must be one of the following types: int32, int64. with only 1 element which is the axis index. TODO: Add support for multiple elements.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 8-bit unsigned integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI16 type or QUI8 type or QI8 type or TFLite quint8 type or 1-bit signless integer values
axis tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 8-bit unsigned integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or QI16 type or QUI8 type or QI8 type or TFLite quint8 type or 1-bit signless integer values

tfl.rfft2d (TFL::RFFT2dOp)

2D real-valued fast Fourier transform.

Computes the 2-dimensional discrete Fourier transform of a real-valued signal over the inner-most 2 dimensions of input .

Since the DFT of a real signal is Hermitian-symmetric, RFFT2D only returns the fft_length / 2 + 1 unique components of the FFT for the inner-most dimension of output : the zero-frequency term, followed by the fft_length / 2 positive-frequency terms.

Along each axis RFFT2D is computed on, if fft_length is smaller than the corresponding dimension of input , the dimension is cropped. If it is larger, the dimension is padded with zeros.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float values
fft_length tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of complex type with 32-bit float elements values

tfl.right_shift (TFL::RightShiftOp)

Right Shift operator

Elementwise computes the bitwise right-shift of lhs by rhs .

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultElementType

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 8-bit signless integer or 8-bit unsigned integer or 16-bit signless integer or 16-bit unsigned integer or 32-bit signless integer or 32-bit unsigned integer values
rhs tensor of 8-bit signless integer or 8-bit unsigned integer or 16-bit signless integer or 16-bit unsigned integer or 32-bit signless integer or 32-bit unsigned integer values

Results:

Result 설명
output tensor of 8-bit signless integer or 8-bit unsigned integer or 16-bit signless integer or 16-bit unsigned integer or 32-bit signless integer or 32-bit unsigned integer values

tfl.round (TFL::RoundOp)

Round operator

Rounds the values of a tensor to the nearest integer, element-wise.

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float values

Results:

Result 설명
y tensor of 32-bit float values

tfl.rsqrt (TFL::RsqrtOp)

Reciprocal of square root operator

Computes element-wise reverse square root of input

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or QI8 type or QI16 type values

Results:

Result 설명
y tensor of 32-bit float or QI8 type or QI16 type values

tfl.scatter_nd (TFL::ScatterNdOp)

_Scatter nd operator

Scatter updates into a new tensor according to indices

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
indices tensor of 32-bit signless integer values
updates tensor of 32-bit float or 8-bit signless integer or 64-bit signless integer or 32-bit signless integer or 8-bit unsigned integer or 1-bit signless integer values
shape 1D tensor of any type values

Results:

Result 설명
output tensor of 32-bit float or 8-bit signless integer or 64-bit signless integer or 32-bit signless integer or 8-bit unsigned integer or 1-bit signless integer values

tfl.segment_sum (TFL::SegmentSumOp)

SegmentSum operator

Computes the sum along segments of a tensor.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer values

tfl.select (TFL::SelectOp)

Select operator

Select values of 'x' if the corresponding value of 'condition' is true or the value of 'y' if false. There are valid condition input sizes:

  1. Either the same shape (in which case the select is elementwise), or
  2. condition must be Rank 1 and match over the first dimension.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
condition tensor of 1-bit signless integer values
x tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit unsigned integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values
y tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit unsigned integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit unsigned integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.select_v2 (TFL::SelectV2Op)

SelectV2 operator

Select values of 'x' if the corresponding value of 'condition' is true or the value of 'y' if false. There are valid condition input sizes:

  1. Either the same shape (in which case the select is elementwise), or
  2. Broadcastable shapes between 'condition', 'x' and 'y'.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
condition tensor of 1-bit signless integer values
x tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit unsigned integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values
y tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit unsigned integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 32-bit unsigned integer or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.shape (TFL::ShapeOp)

Shape operator

Returns the shape of a tensor.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
out_type ::mlir::Attribute derived attribute

Operands:

Operand 설명
input tensor of any type values

Results:

Result 설명
output tensor of 32-bit signless integer or 64-bit signless integer values

tfl.sign (TFL::SignOp)

Sign operation

Returns NaN if x is NaN, 0 if x is 0, -1 if x < 0 and 1 if x > 0.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultElementType, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float or 64-bit float or 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 64-bit float or 32-bit signless integer values

tfl.sin (TFL::SinOp)

Sine operator

Computes element-wise Sine of input

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float values

Results:

Result 설명
y tensor of 32-bit float values

tfl.slice (TFL::SliceOp)

Return a slice from 'input'.

The output tensor is a tensor with dimensions described by 'size' whose values are extracted from 'input' starting at the offsets in 'begin'.

begin is zero-based; size is one-based. If size[i] is -1, all remaining elements in dimension i are included in the slice. In other words, this is equivalent to setting: size[i] = input.dim_size(i) - begin[i]

Requirements : 0 <= begin[i] <= begin[i] + size[i] <= Di for i in [0, n)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 32-bit unsigned integer or 1-bit signless integer or TFLite string type or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
begin tensor of 32/64-bit signless integer values
size tensor of 32/64-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 32-bit unsigned integer or 1-bit signless integer or TFLite string type or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.softmax (TFL::SoftmaxOp)

Softmax operator

Computes element-wise softmax activations with the following formula

exp(input) / tf.reduce_sum(exp(input * beta), dim)

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
beta ::mlir::FloatAttr 32-bit float attribute

Operands:

Operand 설명
input tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

Results:

Result 설명
output tensor of 32-bit float or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.space_to_batch_nd (TFL::SpaceToBatchNdOp)

SpaceToBatchNd operator

This operation reshapes space dimensions into the "batch" dimension 0

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
block_shape tensor of 32-bit signless integer values
paddings tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.space_to_depth (TFL::SpaceToDepthOp)

SpaceToDepth operator

Rearranges blocks of spatial data, into depth. More specifically, this op outputs a copy of the input tensor where values from the height and width dimensions are moved to the depth dimension. block_size indicates the input block size.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
block_size ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type values

tfl.sparse_to_dense (TFL::SparseToDenseOp)

Converts a sparse representation into a dense tensor.

Builds an array dense with shape output_shape such that

# If sparse_indices is scalar
dense[i] = (i == sparse_indices ? sparse_values : default_value)

# If sparse_indices is a vector, then for each i
dense[sparse_indices[i]] = sparse_values[i]

# If sparse_indices is an n by d matrix, then for each i in [0, n)
dense[sparse_indices[i][0], ..., sparse_indices[i][d-1]] = sparse_values[i]

All other values in dense are set to default_value . If sparse_values is a scalar, all sparse indices are set to this single value.

Indices should be sorted in lexicographic order, and indices must not contain any repeats. If validate_indices is true, these properties are checked during execution.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
sparse_indices tensor of 32/64-bit signless integer values
output_shape tensor of 32/64-bit signless integer values
sparse_values tensor of 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or TFLite quint8 type or 32-bit float values
default_value tensor of 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or TFLite quint8 type or 32-bit float values

Results:

Result 설명
dense tensor of 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or TFLite quint8 type or 32-bit float values

tfl.split (TFL::SplitOp)

Splits a tensor into num_split tensors along one dimension.

Splits the value tensor along split_dim into a number of sub-tensors with same shape as the original one, except for split_dim . Same as tf.Split.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
num_splits ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive

Operands:

Operand 설명
split_dim tensor of 32-bit signless integer values
value tensor of 32-bit float or 16-bit signless integer or 32-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values

Results:

Result 설명
outputs tensor of any type values

tfl.split_v (TFL::SplitVOp)

Splits a tensor into num_split tensors along one dimension.

Splits the value tensor along split_dim into a number of sub-tensors with same shape as the original one, except for split_dim . The grouping of the resultant sub-tensors is decided by size-splits . Same as tf.SplitV.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
num_splits ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive

Operands:

Operand 설명
value tensor of 32-bit float or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or QI16 type values
size_splits 1D tensor of 32-bit signless integer values
split_dim 0D tensor of 32-bit signless integer values

Results:

Result 설명
outputs tensor of any type values

tfl.sqrt (TFL::SqrtOp)

Square root operator

Computes element-wise Square root of input

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float values

Results:

Result 설명
y tensor of 32-bit float values

tfl.square (TFL::SquareOp)

Square operator

Computes element-wise Square of input

Traits: AlwaysSpeculatableImplTrait, InferTensorType, TF::SameOperandsAndResultTypeResolveRef

Interfaces: ConditionallySpeculatable, InferShapedTypeOpInterface, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
x tensor of 32-bit float values

Results:

Result 설명
y tensor of 32-bit float values

tfl.squared_difference (TFL::SquaredDifferenceOp)

Squared difference operator

Element-wise squared difference operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
lhs tensor of 32-bit float or 32-bit signless integer or QI8 type values
rhs tensor of 32-bit float or 32-bit signless integer or QI8 type values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or QI8 type values

tfl.squeeze (TFL::SqueezeOp)

Removes dimensions of size 1 from the shape of a tensor.

Given a tensor input , this operation returns a tensor of the same type with all dimensions of size 1 removed. If you don't want to remove all size 1 dimensions, you can remove specific size 1 dimensions by specifying squeeze_dims .

For example:

# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
shape(squeeze(t)) ==> [2, 3]

Or, to remove specific size 1 dimensions:

# 't' is a tensor of shape [1, 2, 1, 3, 1, 1]
shape(squeeze(t, [2, 4])) ==> [1, 2, 3, 1]

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
squeeze_dims ::mlir::ArrayAttr 64-bit integer array attribute whose size is at most 8

Operands:

Operand 설명
input tensor of any type values

Results:

Result 설명
output tensor of any type values

tfl.strided_slice (TFL::StridedSliceOp)

StridedSlice Op

Return a strided slice from input .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
begin_mask ::mlir::IntegerAttr 32-bit signless integer attribute
end_mask ::mlir::IntegerAttr 32-bit signless integer attribute
ellipsis_mask ::mlir::IntegerAttr 32-bit signless integer attribute
new_axis_mask ::mlir::IntegerAttr 32-bit signless integer attribute
shrink_axis_mask ::mlir::IntegerAttr 32-bit signless integer attribute
offset ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 32-bit unsigned integer or QI8 type or QUI8 type or 1-bit signless integer or 16-bit signless integer or QI16 type or TFLite quint8 type or TFLite string type values
begin tensor of 32-bit signless integer values
end tensor of 32-bit signless integer values
strides tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 32-bit unsigned integer or QI8 type or QUI8 type or 1-bit signless integer or 16-bit signless integer or QI16 type or TFLite quint8 type or TFLite string type values

tfl.sub (TFL::SubOp)

Subtraction operator

Element-wise subtraction operation.

Traits: ::mlir::OpTrait::TFLRuntimeOpTrait, AlwaysSpeculatableImplTrait, QuantizableResult, ResultsBroadcastableShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand 설명
lhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type values
rhs tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or QI16 type values

tfl.sum (TFL::SumOp)

Sum operator

Computes the sum reduction along the specified axes

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
keep_dims ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values
axes tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer or 64-bit signless integer or QI8 type or QUI8 type or TFLite quint8 type or QI16 type values

tfl.svdf (TFL::SVDFOp)

Single value decomposition filter operator

The SVDF op is a decomposition of a densely connected op into low rank filters. For details: https://research.google.com/pubs/pub43813.html https://arxiv.org/abs/1812.02802

Traits: QuantizableResult, quant::AccumulatorUniformScale<3, 2, 4>

Interfaces: DynamicRangeQuantizedOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
rank ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float or QI8 type values
feature_weights tensor of 32-bit float or QI8 type or QUI8 type values
time_weights tensor of 32-bit float or QI16 type values
input_gate_bias tensor of any type values or none type
activation_state stateful tensor

Results:

Result 설명
output tensor of 32-bit float or QI8 type values

tfl.tanh (TFL::TanhOp)

Hyperbolic tangent operator

Computes element-wise Hyperbolic tangent of input

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, FixedOutputRangeInterface, NoMemoryEffect (MemoryEffectOpInterface), TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

Results:

Result 설명
output tensor of 32-bit float or QI8 type or QUI8 type or QI16 type or TFLite quint8 type values

tfl.tile (TFL::TileOp)

Tile operator.

Constructs a tensor by tiling a given tensor.

This operation creates a new tensor by replicating input multiples times. The output tensor's i'th dimension has input.dims(i) * multiples[i] elements, and the values of input are replicated multiples[i] times along the 'i'th dimension. For example, tiling [abcd] by [2] produces [abcdabcd].

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 1-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite string type values
multiples tensor of 32/64-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 1-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite string type values

tfl.topk_v2 (TFL::TopKV2Op)

TopK operator

Returns the top k largest element along each last dimensional slice of input and the indices of values within the last dimension of the input tensor.

Results are always sorted in the descending order.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type values
k tensor of 16-bit signless integer or 32-bit signless integer values

Results:

Result 설명
values tensor of 32-bit float or 8-bit signless integer or 16-bit signless integer or 32-bit signless integer or 64-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type values
indices tensor of 16-bit signless integer or 32-bit signless integer values

tfl.transpose (TFL::TransposeOp)

Transpose operator

Returns the Transpose of x

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit signless integer or 32-bit float or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type or 1-bit signless integer or 64-bit signless integer or QI16 type values
perm tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit signless integer or 32-bit float or 8-bit signless integer or 8-bit unsigned integer or QI8 type or QUI8 type or TFLite quint8 type or 1-bit signless integer or 64-bit signless integer or QI16 type values

tfl.transpose_conv (TFL::TransposeConvOp)

Transpose convolution operator

Performs transpose convolution operation on input.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, quant::AccumulatorUniformScale<3, 1, 2>, quant::AffineOpCoefficient<0, 1>

Interfaces: AffineQuantizedOpInterface, ConditionallySpeculatable, DynamicRangeQuantizedOpInterface, NoMemoryEffect (MemoryEffectOpInterface), TFL_SparseOp, TflArithmeticCountOpInterface, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
padding ::mlir::StringAttr string attribute whose value is SAME, or VALID
stride_h ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive
stride_w ::mlir::IntegerAttr 32-bit signless integer attribute whose value is positive
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT

Operands:

Operand 설명
output_shape tensor of 32-bit signless integer values
weights tensor of 32-bit float or QI8 type or QUI8 type or QI16 type values
input tensor of 32-bit float or QI8 type or QUI8 type or QI16 type values
bias tensor of any type values or none type

Results:

Result 설명
output tensor of 32-bit float or QI8 type or QUI8 type or QI16 type values

tfl.unidirectional_sequence_lstm (TFL::UnidirectionalSequenceLSTMOp)

Unidirectional sequence lstm operator

A recurrent neural network specified by an LSTM cell. This Op supports unrolling the input along the time or batch dimensions, and implements the following operation for each element in the sequence s = 1...sequence_length: outputs[s] = state = activation(LSTMOp(inputs[s]))

where LSTMOp is LSTM TF Lite Op and the “activation” is the function passed as the “fused_activation_function” argument (if not “NONE”).

Traits: QuantizableResult

Interfaces: DynamicRangeQuantizedOpInterface, InferTypeOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
cell_clip ::mlir::FloatAttr 32-bit float attribute whose value is non-negative
proj_clip ::mlir::FloatAttr 32-bit float attribute whose value is non-negative
time_major ::mlir::BoolAttr bool attribute
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute
diagonal_recurrent_tensors ::mlir::BoolAttr bool attribute
input_to_input_intermediate ::mlir::TypeAttr any type attribute
input_to_forget_intermediate ::mlir::TypeAttr any type attribute
input_to_cell_intermediate ::mlir::TypeAttr any type attribute
input_to_output_intermediate ::mlir::TypeAttr any type attribute
effective_hidden_scale_intermediate ::mlir::TypeAttr any type attribute

Operands:

Operand 설명
input tensor of 32-bit float values
input_to_input_weights tensor of any type values or none type
input_to_forget_weights tensor of 32-bit float or QI8 type values
input_to_cell_weights tensor of 32-bit float or QI8 type values
input_to_output_weights tensor of 32-bit float or QI8 type values
recurrent_to_input_weights tensor of any type values or none type
recurrent_to_forget_weights tensor of 32-bit float or QI8 type values
recurrent_to_cell_weights tensor of 32-bit float or QI8 type values
recurrent_to_output_weights tensor of 32-bit float or QI8 type values
cell_to_input_weights tensor of any type values or none type
cell_to_forget_weights tensor of any type values or none type
cell_to_output_weights tensor of any type values or none type
input_gate_bias tensor of any type values or none type
forget_gate_bias tensor of 32-bit float values
cell_bias tensor of 32-bit float values
output_gate_bias tensor of 32-bit float values
projection_weights tensor of any type values or none type
projection_bias tensor of any type values or none type
input_activation_state stateful tensor
input_cell_state stateful tensor
input_layer_norm_coefficients tensor of any type values or none type
forget_layer_norm_coefficients tensor of any type values or none type
cell_layer_norm_coefficients tensor of any type values or none type
output_layer_norm_coefficients tensor of any type values or none type

Results:

Result 설명
output tensor of 32-bit float or QI8 type values

tfl.unidirectional_sequence_rnn (TFL::UnidirectionalSequenceRNNOp)

Unidirectional sequence rnn operator

A recurrent neural network specified by an RNN cell. This Op takes in input in a format {batch_size, seq_len, input_size} or {seq_len, batch_size, input_size} if it's time-majored.

It implements the following operation for each element in the sequence s = 1...sequence_length: outputs[s] = state = activation(RNNOp(inputs[s]))

where RNNOp is RNNOp TF Lite Op and the “activation” is the function passed as the “fused_activation_function” argument (if not “NONE”).

Traits: QuantizableResult

Interfaces: DynamicRangeQuantizedOpInterface, TFL_StatefulOp, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
time_major ::mlir::BoolAttr bool attribute
fused_activation_function ::mlir::StringAttr string attribute whose value is NONE, or RELU, or RELU_N1_TO_1, or RELU6, or TANH, or SIGN_BIT
asymmetric_quantize_inputs ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of 32-bit float values
input_to_input_weights tensor of 32-bit float or QI8 type values
recurrent_to_input_weights tensor of 32-bit float or QI8 type values
input_gate_bias tensor of 32-bit float values
hidden_state stateful tensor

Results:

Result 설명
output tensor of 32-bit float values

tfl.unique (TFL::UniqueOp)

Unique Op.

This operation returns a tensor output containing all of the unique elements of input sorted in the same order that they occur in input . This operation also returns a tensor idx the same size as x that contains the index of each value of input in the unique output output . In other words:

Traits: AlwaysSpeculatableImplTrait, QuantizableResult

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
idx_out_type ::mlir::Attribute derived attribute

Operands:

Operand 설명
input tensor of 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or 16-bit signless integer or QI16 type or 32-bit signless integer or 64-bit signless integer or 32-bit float values

Results:

Result 설명
output tensor of 8-bit signless integer or QI8 type or 8-bit unsigned integer or QUI8 type or 16-bit signless integer or QI16 type or 32-bit signless integer or 64-bit signless integer or 32-bit float values
idx tensor of 32/64-bit signless integer values

tfl.unpack (TFL::UnpackOp)

Unpacks a tensor along a dimension into multiple tensors

Unpacks a given dimension of a rank- R tensor into num rank- (R-1) tensors.

Unpacks num tensors from value by chipping it along the axis dimension. For example, given a tensor of shape (A, B, C, D) ;

If axis == 0 then the i'th tensor in output is the slice value[i, :, :, :] and each tensor in output will have shape (B, C, D) . (Note that the dimension unpacked along is gone, unlike split ).

If axis == 1 then the i'th tensor in output is the slice value[:, i, :, :] and each tensor in output will have shape (A, C, D) . Etc.

This is the opposite of pack .

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, SameOperandsAndResultElementType

Interfaces: ConditionallySpeculatable, InferTypeOpInterface, NoMemoryEffect (MemoryEffectOpInterface), SameOperandsAndResultsScale, TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Attributes:

Attribute MLIR Type 설명
num ::mlir::IntegerAttr 32-bit signless integer attribute whose value is non-negative
axis ::mlir::IntegerAttr 32-bit signless integer attribute

Operands:

Operand 설명
input tensor of 32-bit float or 1-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 32-bit signless integer or QI8 type or QUI8 type or 16-bit signless integer or QI16 type values

Results:

Result 설명
outputs tensor of any type values

tfl.unsorted_segment_max (TFL::UnsortedSegmentMaxOp)

UnsortedSegmentMax operator

Computes the maximum value along segments of a tensor such that output[i] = max(data[j....]) where segment_ids[j...] = i if the maximum is empty for a given segment ID i, it outputs the smallest possible value for the specific numeric type, output[i] = numeric_limits::lowest(). Note the values of segment_ids are always validated to be less than num_segments and an error is thrown for out-of-bound indices.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values
num_segments tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer values

tfl.unsorted_segment_min (TFL::UnsortedSegmentMinOp)

UnsortedSegmentMin operator

Computes the minimum value along segments of a tensor such that output[i] = min(data[j....]) where segment_ids[j...] = i if the minimum is empty for a given segment ID i, it outputs the largest possible value for the specific numeric type, output[i] = numeric_limits::max(). Note the values of segment_ids are always validated to be less than num_segments and an error is thrown for out-of-bound indices.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values
num_segments tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer values

tfl.unsorted_segment_prod (TFL::UnsortedSegmentProdOp)

UnsortedSegmentProd operator

Computes the product along segments of a tensor.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values
num_segments tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer values

tfl.unsorted_segment_sum (TFL::UnsortedSegmentSumOp)

UnsortedSegmentSum operator

From a tensor segmentation, computes the output resulting from summing together elements mapped to the same segment_id. Ie output[i] is equal to the tensor sum of all elements from the input tensor mapped to segment_id i . If no tensors are mapped to a particular included segment_id, the output at that indice will be a zero tensor with the appropriate shape. Note the values of segment_ids are always validated to be less than num_segments and an error is thrown for out-of-bound indices

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 32-bit float or 32-bit signless integer values
segment_ids tensor of 32-bit signless integer values
num_segments tensor of 32-bit signless integer values

Results:

Result 설명
output tensor of 32-bit float or 32-bit signless integer values

tfl.var_handle (TFL::VarHandleOp)

Returns a handle to a variable resource from its name.

Returns a handle for a variable resource from its name. container: the container this variable is placed in. shared_name: the name by which this variable is referred to.

Interfaces: TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
container ::mlir::StringAttr string attribute
shared_name ::mlir::StringAttr string attribute

Results:

Result 설명
resource_handle tensor of resource values

tfl.where (TFL::WhereOp)

Returns locations of nonzero / true values in a tensor.

This operation returns the coordinates of true elements in condition . The coordinates are returned in a 2-D tensor where the first dimension (rows) represents the number of true elements, and the second dimension (columns) represents the coordinates of the true elements. Keep in mind, the shape of the output tensor can vary depending on how many true values there are in condition . Indices are output in row-major order.

Traits: AlwaysSpeculatableImplTrait

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
condition tensor of 1-bit signless integer or 32-bit float or 32/64-bit signless integer or 8-bit signless integer or 8-bit unsigned integer or 32-bit unsigned integer values

Results:

Result 설명
index tensor of 64-bit signless integer values

tfl.while (TFL::WhileOp)

While loop

output = input; while (cond(output)) { output = body(output) }

While loop where all values are passes through arguments with implicit capture.

input: A list of input tensors whose types are T. output: A list of output tensors whose types are T. cond: A region that takes 'input' and returns a boolean scalar tensor. body: A region that takes a list of tensors and returns another list of tensors. Both lists have the same types.

Traits: SingleBlockImplicitTerminator

Interfaces: LoopLikeOpInterface, TflRuntimeVerifyOpInterface

Attributes:

Attribute MLIR Type 설명
is_stateless ::mlir::BoolAttr bool attribute

Operands:

Operand 설명
input tensor of any type values

Results:

Result 설명
output tensor of any type values

tfl.yield (TFL::YieldOp)

Yield operation

The "yield" operation represents a return operation within the conditional and body of structured control flow (eg, while), and a terminator for ControlNodeOp. The operation takes a variable number of operands and produces no results. The operand number and types must match the signature of the region that contains the operation.

Traits: AlwaysSpeculatableImplTrait, QuantizableResult, Terminator

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
«unnamed» any type

tfl.zeros_like (TFL::ZerosLikeOp)

ZerosLike operator

Returns a tensor of zeros with the same shape and type as the input tensor.

Traits: AlwaysSpeculatableImplTrait, SameOperandsAndResultShape

Interfaces: ConditionallySpeculatable, NoMemoryEffect (MemoryEffectOpInterface), TflRuntimeVerifyOpInterface

Effects: MemoryEffects::Effect{}

Operands:

Operand 설명
input tensor of 64-bit signless integer or 32-bit signless integer or 32-bit float values

Results:

Result 설명
output tensor of 64-bit signless integer or 32-bit signless integer or 32-bit float values

Attribute definition

DimensionMetadataAttr

Dimension metadata.

Syntax:

#tfl.dimension_metadata<
  ::mlir::TFL::DimensionTypeAttr,   # format
  int32_t,   # dense_size
  ::llvm::ArrayRef<int32_t>,   # segments
  ::llvm::ArrayRef<int32_t>   # indices
>

매개변수:

Parameter C++ type 설명
format ::mlir::TFL::DimensionTypeAttr dimension_type
dense_size int32_t
segments ::llvm::ArrayRef<int32_t>
indices ::llvm::ArrayRef<int32_t>

SparsityParameterAttr

Sparsity parameter.

Syntax:

#tfl.sparsity_parameter<
  ::llvm::ArrayRef<int32_t>,   # traversal_order
  ::llvm::ArrayRef<int32_t>,   # block_map
  ::llvm::ArrayRef<DimensionMetadataAttr>   # dim_metadata
>

매개변수:

Parameter C++ type 설명
traversal_order ::llvm::ArrayRef<int32_t>
block_map ::llvm::ArrayRef<int32_t>
dim_metadata ::llvm::ArrayRef<DimensionMetadataAttr>

ConstBytesAttr

A string attribute representation of compiled bytes

Syntax Examples:

#tfl<const_bytes : "0xDEADBEEF">

매개변수:

Parameter C++ type 설명
value ::llvm::StringRef

DimensionTypeAttr

dimension_type

Syntax:

#tfl.dimension_type_attr<
  ::mlir::TFL::DimensionType   # value
>

매개변수:

Parameter C++ type 설명
value ::mlir::TFL::DimensionType an enum of type DimensionType

LSTMKernelTypeAttr

lstm_kernel_type

Syntax:

#tfl.lstm_kernel_type_attr<
  ::mlir::TFL::LSTMKernelType   # value
>

매개변수:

Parameter C++ type 설명
value ::mlir::TFL::LSTMKernelType an enum of type LSTMKernelType

MirrorPaddingTypeAttr

mirror_pad_enum

Syntax:

#tfl.mirror_pad_attr<
  ::mlir::TFL::MirrorPaddingType   # value
>

매개변수:

Parameter C++ type 설명
value ::mlir::TFL::MirrorPaddingType an enum of type MirrorPaddingType