tf_nndct.IterativePruningRunner - 3.5 English

Runner for structured pruning of the model in an iterative way. This API has the following methods:

• __init__(model, input_specs)

  Creates a new IterativePruningRunner object.

  model

  A baseline model to prune. The model should be an instance of keras.Model.

  input_specs

  A single or a list of tf.TensorSpec is used to represent model input specifications.

• ana(eval_fn, excludes=None, forced=False)

  Performs model analysis. The analysis result is saved in the '.vai' directory, and this cached result is used directly in subsequent calls unless forced is set to True.

  eval_fn

  Callable object that takes a keras.Model object as its first argument and returns the evaluation score.

  excludes

  A list of layer names or layer instances to be excluded from pruning.

  forced

  When set to True, model analysis is run instead of the cached analysis result.

• prune(ratio=None, threshold=None, spec_path=None, excludes=None, mode='sparse')

  Prunes the baseline model and returns a sparse model. The degree of pruning can be specified in three ways: ratio, threshold, or pruning specification. The first method is preferred; the latter two are more suitable for experiments with manual tuning.

  ratio

  The expected percentage of FLOPs reduction of the baseline model. This is a guidance value, and the actual FLOPs reduction cannot strictly be equal to this value.

  threshold

  Relative proportion of model performance loss between the baseline and pruned models.

  spec_path

  Pruning specification path is used to prune the model.

  excludes

  A list of layer name or layer instance to be excluded from pruning.

  mode

  The mode in which the baseline model is pruned to return a sparse model.

• get_slim_model(spec_path=None)

  Gets a slim model from a sparse model. By default, you would use the latest pruning specification to do this transformation. A specification path can be provided explicitly if the sparse model was not generated from the latest specification.

  spec_path

  The pruning specification path transforms a sparse model into a slim one.