Ringkasan memberikan detail tentang arsitektur model, seperti tipe dan bentuk lapisan.
Proposal desain dapat ditemukan di sini . Implementasi ini adalah WIP, jadi harap ajukan Masalah dengan penyempurnaan yang ingin Anda lihat atau masalah yang Anda alami.
Melihat ringkasan model
Buat perangkat dan model X10.
import TensorFlow
public struct MyModel: Layer {
public var dense1 = Dense<Float>(inputSize: 1, outputSize: 1)
public var dense2 = Dense<Float>(inputSize: 4, outputSize: 4)
public var dense3 = Dense<Float>(inputSize: 4, outputSize: 4)
public var flatten = Flatten<Float>()
@differentiable
public func callAsFunction(_ input: Tensor<Float>) -> Tensor<Float> {
let layer1 = dense1(input)
let layer2 = layer1.reshaped(to: [1, 4])
let layer3 = dense2(layer2)
let layer4 = dense3(layer3)
return flatten(layer4)
}
}
let device = Device.defaultXLA
let model0 = MyModel()
let model = MyModel(copying: model0, to: device)
Buat tensor masukan.
let input = Tensor<Float>(repeating: 1, shape: [1, 4, 1, 1], on: device)
Hasilkan ringkasan model Anda.
let summary = model.summary(input: input)
print(summary)
Layer Output Shape Attributes
=============================== ==================== ======================
Dense<Float> [1, 4, 1, 1]
Dense<Float> [1, 4]
Dense<Float> [1, 4]
Flatten<Float> [1, 4]