fix models readme

examples/README.md

@@ -55,13 +55,13 @@ Intel® Neural Compressor validated examples with multiple compression technique
     <td>MobileNet V1</td>
     <td>Image Recognition</td>
     <td>Post-Training Static Quantization</td>
-    <td><a href="./tensorflow/image_recognition/tensorflow_models/quantization/ptq">pb</a> / <a href="./tensorflow/image_recognition/SavedModel/quantization/ptq">SavedModel</a></td>
+    <td><a href="./tensorflow/image_recognition/tensorflow_models/quantization/ptq">pb</a></td>
   </tr>
   <tr>
     <td>MobileNet V2</td>
     <td>Image Recognition</td>
     <td>Post-Training Static Quantization</td>
-    <td><a href="./tensorflow/image_recognition/tensorflow_models/quantization/ptq">pb</a>  / <a href="./tensorflow/image_recognition/SavedModel/quantization/ptq">SavedModel</a> / <a href="./tensorflow/image_recognition/keras_models/mobilenet_v2/quantization/ptq">keras</a></td>
+    <td><a href="./tensorflow/image_recognition/tensorflow_models/quantization/ptq">pb</a> / <a href="./tensorflow/image_recognition/keras_models/mobilenet_v2/quantization/ptq">keras</a></td>
   </tr>
   <tr>
     <td>MobileNet V3</td>
@@ -237,6 +237,12 @@ Intel® Neural Compressor validated examples with multiple compression technique
     <td>Post-Training Static Quantization</td>
     <td><a href="./tensorflow/nlp/transformer_lt/quantization/ptq">pb</a></td>
   </tr>
+  <tr>
+    <td>Transformer LT MLPerf</td>
+    <td>Natural Language Processing</td>
+    <td>Post-Training Static Quantization</td>
+    <td><a href="./tensorflow/nlp/transformer_lt_mlperf/quantization/ptq">pb</a></td>
+  </tr>
   <tr>
     <td>SSD ResNet50 V1</td>
     <td>Object Detection</td>

examples/pytorch/image_recognition/torchvision_models/quantization/ptq/cpu/fx/README.md

@@ -177,7 +177,7 @@ Here we choose topk built-in metric and set accuracy target as tolerating 0.01 r
 
 ### Prepare
 
-The related code please refer to examples/pytorch/fx/image_recognition/imagenet/cpu/ptq/main.py.
+The related code please refer to examples/pytorch/image_recognition/torchvision_models/quantization/ptq/cpu/fx/main.py.
 
 ### Code Update
 

examples/pytorch/image_recognition/torchvision_models/quantization/ptq/cpu/ipex/README.md

@@ -203,7 +203,7 @@ As ResNet18/50/101 series are typical classification models, use Top-K as metric
 
 ### Prepare
 
-The related code please refer to examples/pytorch/ipex/image_recognition/imagenet/cpu/ptq/main.py.
+The related code please refer to examples/pytorch/image_recognition/torchvision_models/quantization/ptq/cpu/ipex/main.py.
 
 ### Tuning With Intel PyTorch Extension
 

examples/tensorflow/image_recognition/SavedModel/quantization/ptq/README.md

@@ -38,8 +38,8 @@ pip install --upgrade intel-extension-for-tensorflow[cpu]
 Download the model from tensorflow-hub.
 
 image recognition
-- [mobilenetv1](https://hub.tensorflow.google.cn/google/imagenet/mobilenet_v1_075_224/classification/5)
-- [mobilenetv2](https://hub.tensorflow.google.cn/google/imagenet/mobilenet_v2_035_224/classification/5)
+- [mobilenetv1(experiment)](https://hub.tensorflow.google.cn/google/imagenet/mobilenet_v1_075_224/classification/5)
+- [mobilenetv2(experiment)](https://hub.tensorflow.google.cn/google/imagenet/mobilenet_v2_035_224/classification/5)
 - [efficientnet_v2_b0](https://hub.tensorflow.google.cn/google/imagenet/efficientnet_v2_imagenet1k_b0/classification/2)
 
 ## Write Yaml config file
@@ -51,4 +51,4 @@ In examples directory, there are mobilenet_v1.yaml, mobilenet_v2.yaml and effici
   ```
   ```shell
   bash run_benchmark.sh --config=./config.yaml --input_model=./SavedModel --mode=performance
-  ```
+  ```

examples/tensorflow/image_recognition/keras_models/resnet50_fashion/quantization/ptq/README.md

@@ -36,7 +36,7 @@ pip install --upgrade intel-extension-for-tensorflow[cpu]
 
 ### 4. Prepare Pretrained model
 
-Run the `resnet50_fashion_mnist_train.py` script located in `LowPrecisionInferenceTool/examples/tensorflow/keras`, and it will generate a saved model called `resnet50_fashion` at current path.
+Run the `resnet50_fashion_mnist_train.py` script located in `examples/tensorflow/image_recognition/keras_models/resnet50_fashion/quantization/ptq`, and it will generate a saved model called `resnet50_fashion` at current path.
 
 ### 5. Prepare dataset
 

examples/tensorflow/image_recognition/tensorflow_models/quantization/ptq/README.md

@@ -308,7 +308,7 @@ pip install --upgrade intel-extension-for-tensorflow[cpu]
           --input_model=/PATH/TO/frozen_nasnet_mobile.pb --output_model=./nc_nasnet_mobile
   ```
 
-### 20. EfficientNet-b0
+### 20. EfficientNet-b0(experiment)
 
   Download pre-trained checkpoint
   ```shell

examples/tensorflow/object_detection/yolo_v3/quantization/ptq/README.md

@@ -15,7 +15,7 @@ pip install neural-compressor
 ```shell
 pip install intel-tensorflow
 ```
-> Note: Supported Tensorflow versions please refer to Neural Compressor readme file.
+> Note: Only supported Tensorflow 1.x versions.
 
 ### 3. Installation Dependency packages
 ```shell