tfm.vision.MaskRCNNTask

A single-replica view of training procedure.

Inherits From: Task

Mask R-CNN task provides artifacts for training/evalution procedures, including loading/iterating over Datasets, initializing the model, calculating the loss, post-processing, and customized metrics with reduction.

params the task configuration instance, which can be any of dataclass, ConfigDict, namedtuple, etc.
logging_dir a string pointing to where the model, summaries etc. will be saved. You can also write additional stuff in this directory.
name the task name.

logging_dir

task_config

Methods

aggregate_logs

View source

Optional aggregation over logs returned from a validation step.

build_inputs

View source

Builds input dataset.

build_losses

View source

Builds Mask R-CNN losses.

build_metrics

View source

Builds detection metrics.

build_model

View source

Builds Mask R-CNN model.

create_optimizer

View source

Creates an TF optimizer from configurations.

Args
optimizer_config the parameters of the Optimization settings.
runtime_config the parameters of the runtime.
dp_config the parameter of differential privacy.

Returns
A tf.optimizers.Optimizer object.

inference_step

View source

Performs the forward step.

With distribution strategies, this method runs on devices.

Args
inputs a dictionary of input tensors.
model the keras.Model.

Returns
Model outputs.

initialize

View source

Loads pretrained checkpoint.

process_compiled_metrics

View source

Process and update compiled_metrics.

call when using compile/fit API.

Args
compiled_metrics the compiled metrics (model.compiled_metrics).
labels a tensor or a nested structure of tensors.
model_outputs a tensor or a nested structure of tensors. For example, output of the keras model built by self.build_model.

process_metrics

View source

Process and update metrics.

Called when using custom training loop API.

Args
metrics a nested structure of metrics objects. The return of function self.build_metrics.
labels a tensor or a nested structure of tensors.
model_outputs a tensor or a nested structure of tensors. For example, output of the keras model built by self.build_model.
**kwargs other args.

reduce_aggregated_logs

View source

Optional reduce of aggregated logs over validation steps.

train_step

View source

Does forward and backward.

Args
inputs a dictionary of input tensors.
model the model, forward pass definition.
optimizer the optimizer for this training step.
metrics a nested structure of metrics objects.

Returns
A dictionary of logs.

validation_step

View source

Validatation step.

Args
inputs a dictionary of input tensors.
model the keras.Model.
metrics a nested structure of metrics objects.

Returns
A dictionary of logs.

loss 'loss'