Merge branch 'master' into mengni/weight_only

.azure-pipelines/scripts/codeScan/pyspelling/inc_dict.txt

@@ -495,6 +495,7 @@ dnf
 dnn
 dnnl
 DNNL
+DnnlExecutionProvider
 Dockerfile
 doclist
 docstrings
@@ -563,6 +564,7 @@ enum
 env
 environ
 ep
+eps
 eq
 erf
 Erf

README.md

@@ -45,9 +45,8 @@ pip install tensorflow
 wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v1_6/mobilenet_v1_1.0_224_frozen.pb
 ```
 ```python
+from neural_compressor.data import DataLoader, Datasets
 from neural_compressor.config import PostTrainingQuantConfig
-from neural_compressor.data import DataLoader
-from neural_compressor.data import Datasets
 
 dataset = Datasets('tensorflow')['dummy'](shape=(1, 224, 224, 3))
 dataloader = DataLoader(framework='tensorflow', dataset=dataset)
@@ -56,8 +55,7 @@ from neural_compressor.quantization import fit
 q_model = fit(
     model="./mobilenet_v1_1.0_224_frozen.pb",
     conf=PostTrainingQuantConfig(),
-    calib_dataloader=dataloader,
-    eval_dataloader=dataloader)
+    calib_dataloader=dataloader)
 ```
 
 ## Documentation

docs/source/get_started.md

@@ -15,20 +15,17 @@ pip install tensorflow
 wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v1_6/mobilenet_v1_1.0_224_frozen.pb
 ```
 ```python
+from neural_compressor.data import DataLoader, Datasets
 from neural_compressor.config import PostTrainingQuantConfig
-from neural_compressor.data import DataLoader
-from neural_compressor.data import Datasets
 
 dataset = Datasets('tensorflow')['dummy'](shape=(1, 224, 224, 3))
 dataloader = DataLoader(framework='tensorflow', dataset=dataset)
 
 from neural_compressor.quantization import fit
-config = PostTrainingQuantConfig()
 q_model = fit(
     model="./mobilenet_v1_1.0_224_frozen.pb",
-    conf=config,
-    calib_dataloader=dataloader,
-    eval_dataloader=dataloader)
+    conf=PostTrainingQuantConfig(),
+    calib_dataloader=dataloader)
 ```
 
 ## Validated Models

docs/source/mixed_precision.md

@@ -17,6 +17,7 @@ The recently launched 3rd Gen Intel® Xeon® Scalable processor (codenamed Coope
 </p>
 
 ## Mixed Precision Support Matrix
+
 <table class="center">
     <thead>
         <tr>
@@ -48,7 +49,7 @@ The recently launched 3rd Gen Intel® Xeon® Scalable processor (codenamed Coope
             <td align="left">:x:</td>
         </tr>
         <tr>
-            <td rowspan="3" align="left">ONNX Runtime</td>
+            <td rowspan="4" align="left">ONNX Runtime</td>
             <td align="left">CPUExecutionProvider</td>
             <td align="left">MLAS</td>
             <td align="left">"default"</td>
@@ -72,6 +73,14 @@ The recently launched 3rd Gen Intel® Xeon® Scalable processor (codenamed Coope
             <td align="left">&#10004;</td>
             <td align="left">&#10004;</td>
         </tr>
+        <tr>
+            <td align="left">DnnlExecutionProvider</td>
+            <td align="left">OneDNN</td>
+            <td align="left">"onnxrt_dnnl_ep"</td>
+            <td align="left">cpu</td>
+            <td align="left">&#10004;</td>
+            <td align="left">:x:</td>
+        </tr>
         <tr>
             <td rowspan="2" align="left">Tensorflow</td>
             <td align="left">Tensorflow</td>
@@ -162,4 +171,5 @@ converted_model.save('./path/to/save/')
 - Quick started with [helloworld example](/examples/helloworld/tf_example3)
 - PyTorch [ResNet18](/examples/pytorch/image_recognition/torchvision_models/mixed_precision/resnet18)
 - IPEX [DistilBERT base](/examples/pytorch/nlp/huggingface_models/question-answering/mixed_precision/ipex)
-- Tensorflow [ResNet50](/examples/tensorflow/image_recognition/tensorflow_models/resnet50_v1/mixed_precision) 
+- Tensorflow [ResNet50](/examples/tensorflow/image_recognition/tensorflow_models/resnet50_v1/mixed_precision)
+- ONNX Runtime [Bert base](/examples/onnxrt/nlp/huggingface_model/text_classification/mix_precision)

docs/source/objective.md

@@ -19,7 +19,7 @@ Objective
 
 ## Introduction
 
-In terms of evaluating the status of a specific model during tuning, we should have general objectives. Intel® Neural Compressor Objective supports code-free configuration through a yaml file. With built-in objectives, users can compress models with different objectives easily. In special cases, users can also register their own objective classes.
+In terms of evaluating the status of a specific model during tuning, we should have general objectives. Intel® Neural Compressor Objective supports code-free configuration through `neural_compressor.config.TuningCriterion`. With built-in objectives, users can compress models with different objectives easily. In special cases, users can also register their own objective classes.
 
 ### Single Objective
 

docs/source/quantization.md

@@ -452,7 +452,7 @@ Intel(R) Neural Compressor support multi-framework: PyTorch, Tensorflow, ONNX Ru
             <td align="left">cpu</td>
         </tr>
         <tr>
-            <td rowspan="3" align="left">ONNX Runtime</td>
+            <td rowspan="4" align="left">ONNX Runtime</td>
             <td align="left">CPUExecutionProvider</td>
             <td align="left">MLAS</td>
             <td align="left">"default"</td>
@@ -470,6 +470,12 @@ Intel(R) Neural Compressor support multi-framework: PyTorch, Tensorflow, ONNX Ru
             <td align="left">"onnxrt_cuda_ep"</td>
             <td align="left">gpu</td>
         </tr>
+        <tr>
+            <td align="left">DnnlExecutionProvider</td>
+            <td align="left">OneDNN</td>
+            <td align="left">"onnxrt_dnnl_ep"</td>
+            <td align="left">cpu</td>
+        </tr>
         <tr>
             <td rowspan="2" align="left">Tensorflow</td>
             <td align="left">Tensorflow</td>