[Doc] update compression tutorials (#4646)

nni/algorithms/compression/pytorch/quantization/dorefa_quantizer.py

@@ -15,7 +15,7 @@ logger = logging.getLogger(__name__)
 class DoReFaQuantizer(Quantizer):
     r"""
     Quantizer using the DoReFa scheme, as defined in:
-    `DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients <https://arxiv.org/abs/1606.06160>`__\ ,
+    `DoReFa-Net: Training Low Bitwidth Convolutional Neural Networks with Low Bitwidth Gradients <https://arxiv.org/abs/1606.06160>`__,
     authors Shuchang Zhou and Yuxin Wu provide an algorithm named DoReFa to quantize the weight, activation and gradients with training.
 
     Parameters

nni/algorithms/compression/pytorch/quantization/qat_quantizer.py

@@ -109,8 +109,8 @@ def update_ema(biased_ema, value, decay):
 class QAT_Quantizer(Quantizer):
     r"""
     Quantizer defined in:
-    Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
-    http://openaccess.thecvf.com/content_cvpr_2018/papers/Jacob_Quantization_and_Training_CVPR_2018_paper.pdf
+    `Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
+    <http://openaccess.thecvf.com/content_cvpr_2018/papers/Jacob_Quantization_and_Training_CVPR_2018_paper.pdf>`__
 
     Authors Benoit Jacob and Skirmantas Kligys provide an algorithm to quantize the model with training.
 
@@ -124,6 +124,7 @@ class QAT_Quantizer(Quantizer):
 
         * Weights are quantized before they are convolved with the input. If batch normalization (see [17]) is used for the layer,
           the batch normalization parameters are “folded into” the weights before quantization.
+
         * Activations are quantized at points where they would be during inference,
           e.g. after the activation function is applied to a convolutional or fully connected layer’s output,
           or after a bypass connection adds or concatenates the outputs of several layers together such as in ResNets.
@@ -184,7 +185,7 @@ class QAT_Quantizer(Quantizer):
         dummy_input = torch.randn(1, 1, 28, 28)
 
         # pass the dummy_input to the quantizer
-        quantizer = QAT_Quantizer(model, config_list, dummy_input=dummy_input)
+        quantizer = QAT_Quantizer(model, config_list, optimizer, dummy_input=dummy_input)
 
 
     The quantizer will automatically detect Conv-BN patterns and simulate batch normalization folding process in the training

nni/algorithms/compression/v2/pytorch/pruning/basic_pruner.py

@@ -148,8 +148,8 @@ class LevelPruner(BasicPruner):
         operation an example, weight tensor will be split into sub block whose shape is aligned to
         balance_gran. Then finegrained pruning will be applied internal of sub block. This sparsity
         pattern have more chance to achieve better trade-off between model performance and hardware
-        acceleration. Please refer to releated paper for further information 'Balanced Sparsity for 
-        Efficient DNN Inference on GPU'(https://arxiv.org/pdf/1811.00206.pdf).
+        acceleration. Please refer to releated paper for further information `Balanced Sparsity for
+        Efficient DNN Inference on GPU <https://arxiv.org/pdf/1811.00206.pdf>`__.
     balance_gran : list
         Balance_gran is for special sparse pattern balanced sparsity, Default value is None which means pruning
         without awaring balance, namely normal finegrained pruning.
@@ -290,7 +290,7 @@ class L1NormPruner(NormPruner):
     i.e., compute the l1 norm of the filters in convolution layer as metric values,
     compute the l1 norm of the weight by rows in linear layer as metric values.
 
-    For more details, please refer to `PRUNING FILTERS FOR EFFICIENT CONVNETS <https://arxiv.org/abs/1608.08710>`__\.
+    For more details, please refer to `PRUNING FILTERS FOR EFFICIENT CONVNETS <https://arxiv.org/abs/1608.08710>`__.
 
     In addition, L1 norm pruner also supports dependency-aware mode.