neural_compressor.experimental.pytorch_pruner.pruning
¶
pruning module.
Module Contents¶
Classes¶
Pruning. |
- class neural_compressor.experimental.pytorch_pruner.pruning.Pruning(config)¶
Pruning.
The main class that users will used in codes to do pruning. Contain at least one Pruner object.
- Parameters:
config – a string. The path to a config file. For config file template, please refer to https://github.com/intel/neural-compressor/tree/master/examples/pytorch/nlp/huggingface_models/text-classification/pruning/pytorch_pruner/eager/
- model¶
The model object to prune.
- config_file_path¶
A string. The path to a config file.
- pruners¶
A list. A list of Pruner objects.
- pruner_info¶
A config dict object. Contains pruners’ information.
- update_items_for_all_pruners(**kwargs)¶
Functions which add User-defined arguments to the original configurations.
The original config of pruning is read from a file. However, users can still modify configurations by passing key-value arguments in this function. Please note that the key-value arguments’ keys are analysable in current configuration.
- prepare()¶
Align with old API’s calling pipeline.
- get_sparsity_ratio()¶
Functions that calculate a modules/layers sparsity.
- Returns:
Three floats. elementwise_over_matmul_gemm_conv refers to zero elements’ ratio in pruning layers. elementwise_over_all refers to zero elements’ ratio in all layers in the model. blockwise_over_matmul_gemm_conv refers to all-zero blocks’ ratio in pruning layers.
- on_train_begin()¶
Functions called in the beginning of training process.
Before training, ensure that pruners are generated.
- on_epoch_begin(epoch)¶
Functions called in the beginning of every epoch.
- on_step_begin(local_step)¶
Functions called in the beginning of every step.
- on_before_optimizer_step()¶
Functions called before optimizer.step().
- on_step_end()¶
Functions called in the end of every step.
- on_epoch_end()¶
Functions called in the end of every epoch.
- on_train_end()¶
Functions called in the end of training.
- on_before_eval()¶
Functions called in the beginning of evaluation.
- on_after_eval()¶
Functions called in the end of evaluation.
- on_after_optimizer_step()¶
Functions called after optimizer.step().