[Model Compression] Update api of iterative pruners

docs/en_US/Compression/CompressionReference.rst

@@ -34,7 +34,7 @@ Weight Masker
 ..  autoclass:: nni.algorithms.compression.pytorch.pruning.weight_masker.WeightMasker
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.structured_pruning.StructuredWeightMasker
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.structured_pruning_masker.StructuredWeightMasker
     :members:
 
 
@@ -43,40 +43,40 @@ Pruners
 ..  autoclass:: nni.algorithms.compression.pytorch.pruning.sensitivity_pruner.SensitivityPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.OneshotPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot_pruner.OneshotPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.LevelPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot_pruner.LevelPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.SlimPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot_pruner.L1FilterPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.L1FilterPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot_pruner.L2FilterPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.L2FilterPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot_pruner.FPGMPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.FPGMPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.iterative_pruner.IterativePruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.TaylorFOWeightFilterPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.iterative_pruner.SlimPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.ActivationAPoZRankFilterPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.iterative_pruner.TaylorFOWeightFilterPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.one_shot.ActivationMeanRankFilterPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.iterative_pruner.ActivationAPoZRankFilterPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.lottery_ticket.LotteryTicketPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.iterative_pruner.ActivationMeanRankFilterPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.agp.AGPPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.iterative_pruner.AGPPruner
     :members:
 
-..  autoclass:: nni.algorithms.compression.pytorch.pruning.admm_pruner.ADMMPruner
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.iterative_pruner.ADMMPruner
     :members:
 
 ..  autoclass:: nni.algorithms.compression.pytorch.pruning.auto_compress_pruner.AutoCompressPruner
@@ -88,6 +88,9 @@ Pruners
 ..  autoclass:: nni.algorithms.compression.pytorch.pruning.simulated_annealing_pruner.SimulatedAnnealingPruner
     :members:
 
+..  autoclass:: nni.algorithms.compression.pytorch.pruning.lottery_ticket.LotteryTicketPruner
+    :members:
+
 
 Quantizers
 ^^^^^^^^^^

docs/en_US/Compression/CustomizeCompressor.rst

@@ -28,7 +28,7 @@ An implementation of ``weight masker`` may look like this:
            # mask = ...
            return {'weight_mask': mask}
 
-You can reference nni provided :githublink:`weight masker <nni/algorithms/compression/pytorch/pruning/structured_pruning.py>` implementations to implement your own weight masker.
+You can reference nni provided :githublink:`weight masker <nni/algorithms/compression/pytorch/pruning/structured_pruning_masker.py>` implementations to implement your own weight masker.
 
 A basic ``pruner`` looks likes this:
 
@@ -52,7 +52,7 @@ A basic ``pruner`` looks likes this:
                wrapper.if_calculated = True
                return masks
 
-Reference nni provided :githublink:`pruner <nni/algorithms/compression/pytorch/pruning/one_shot.py>` implementations to implement your own pruner class.
+Reference nni provided :githublink:`pruner <nni/algorithms/compression/pytorch/pruning/one_shot_pruner.py>` implementations to implement your own pruner class.
 
 ----
 

docs/en_US/Compression/Overview.rst

@@ -14,10 +14,19 @@ NNI provides a model compression toolkit to help user compress and speed up thei
 * Provide friendly and easy-to-use compression utilities for users to dive into the compression process and results.
 * Concise interface for users to customize their own compression algorithms.
 
+
+Compression Pipeline
+--------------------
+
+.. image:: ../../img/compression_flow.jpg
+   :target: ../../img/compression_flow.jpg
+   :alt: 
+
+The overall compression pipeline in NNI. For compressing a pretrained model, pruning and quantization can be used alone or in combination. 
+
 .. note::
   Since NNI compression algorithms are not meant to compress model while NNI speedup tool can truly compress model and reduce latency. To obtain a truly compact model, users should conduct `model speedup <./ModelSpeedup.rst>`__. The interface and APIs are unified for both PyTorch and TensorFlow, currently only PyTorch version has been supported, TensorFlow version will be supported in future.
 
-
 Supported Algorithms
 --------------------
 
@@ -26,7 +35,7 @@ The algorithms include pruning algorithms and quantization algorithms.
 Pruning Algorithms
 ^^^^^^^^^^^^^^^^^^
 
-Pruning algorithms compress the original network by removing redundant weights or channels of layers, which can reduce model complexity and address the over-fitting issue. 
+Pruning algorithms compress the original network by removing redundant weights or channels of layers, which can reduce model complexity and mitigate the over-fitting issue.
 
 .. list-table::
    :header-rows: 1
@@ -96,6 +105,7 @@ Model Speedup
 
 The final goal of model compression is to reduce inference latency and model size. However, existing model compression algorithms mainly use simulation to check the performance (e.g., accuracy) of compressed model, for example, using masks for pruning algorithms, and storing quantized values still in float32 for quantization algorithms. Given the output masks and quantization bits produced by those algorithms, NNI can really speed up the model. The detailed tutorial of Masked Model Speedup can be found `here <./ModelSpeedup.rst>`__, The detailed tutorial of Mixed Precision Quantization Model Speedup can be found `here <./QuantizationSpeedup.rst>`__.
 
+
 Compression Utilities
 ---------------------
 
@@ -110,7 +120,6 @@ NNI model compression leaves simple interface for users to customize a new compr
 Reference and Feedback
 ----------------------
 
-
 * To `report a bug <https://github.com/microsoft/nni/issues/new?template=bug-report.rst>`__ for this feature in GitHub;
 * To `file a feature or improvement request <https://github.com/microsoft/nni/issues/new?template=enhancement.rst>`__ for this feature in GitHub;
 * To know more about `Feature Engineering with NNI <../FeatureEngineering/Overview.rst>`__\ ;

docs/en_US/Compression/Pruner.rst

@@ -1,15 +1,11 @@
 Supported Pruning Algorithms on NNI
 ===================================
 
-We provide several pruning algorithms that support fine-grained weight pruning and structural filter pruning. **Fine-grained Pruning** generally results in  unstructured models, which need specialized hardware or software to speed up the sparse network. **Filter Pruning** achieves acceleration by removing the entire filter. Some pruning algorithms use one-shot method that prune weights at once based on an importance metric. Other pruning algorithms control the **pruning schedule** that prune weights during optimization, including some automatic pruning algorithms.
+We provide several pruning algorithms that support fine-grained weight pruning and structural filter pruning. **Fine-grained Pruning** generally results in  unstructured models, which need specialized hardware or software to speed up the sparse network. **Filter Pruning** achieves acceleration by removing the entire filter. Some pruning algorithms use one-shot method that prune weights at once based on an importance metric (It is necessary to finetune the model to compensate for the loss of accuracy). Other pruning algorithms **iteratively** prune weights during optimization, which control the pruning schedule, including some automatic pruning algorithms.
 
 
-**Fine-grained Pruning**
-
-* `Level Pruner <#level-pruner>`__
-
-**Filter Pruning**
-
+**One-shot Pruning**
+* `Level Pruner <#level-pruner>`__ ((fine-grained pruning))
 * `Slim Pruner <#slim-pruner>`__
 * `FPGM Pruner <#fpgm-pruner>`__
 * `L1Filter Pruner <#l1filter-pruner>`__
@@ -18,18 +14,17 @@ We provide several pruning algorithms that support fine-grained weight pruning a
 * `Activation Mean Rank Filter Pruner <#activationmeanrankfilter-pruner>`__
 * `Taylor FO On Weight Pruner <#taylorfoweightfilter-pruner>`__
 
-**Pruning Schedule**
+**Iteratively Pruning**
 
 * `AGP Pruner <#agp-pruner>`__
 * `NetAdapt Pruner <#netadapt-pruner>`__
 * `SimulatedAnnealing Pruner <#simulatedannealing-pruner>`__
 * `AutoCompress Pruner <#autocompress-pruner>`__
 * `AMC Pruner <#amc-pruner>`__
 * `Sensitivity Pruner <#sensitivity-pruner>`__
+* `ADMM Pruner <#admm-pruner>`__
 
 **Others**
-
-* `ADMM Pruner <#admm-pruner>`__
 * `Lottery Ticket Hypothesis <#lottery-ticket-hypothesis>`__
 
 Level Pruner
@@ -382,11 +377,7 @@ PyTorch code
 
    from nni.algorithms.compression.pytorch.pruning import AGPPruner
    config_list = [{
-       'initial_sparsity': 0,
-       'final_sparsity': 0.8,
-       'start_epoch': 0,
-       'end_epoch': 10,
-       'frequency': 1,
+       'sparsity': 0.8,
        'op_types': ['default']
    }]
 

examples/model_compress/.gitignore

@@ -0,0 +1,6 @@
+.pth
+.tar.gz
+data/
+MNIST/
+cifar-10-batches-py/
+experiment_data/