Updating model zoo examples (#2271)

Author: wangkl2

examples/README.md

@@ -9,8 +9,8 @@ A wide variety of examples are provided to demonstrate the usage of Intel® Exte
 |[BERT Training for Classifying Text](./train_bert)|BERT training with Intel® Extension for TensorFlow* on Intel CPU or GPU.<br>Use the TensorFlow official example without code change.|CPU & GPU|
 |[Speed up Inference of Inception v4 by Advanced Automatic Mixed Precision via Docker Container or Bare Metal](./infer_inception_v4_amp)|Test and compare the performance of inference with FP32 and Advanced Automatic Mixed Precision (AMP) (mix BF16/FP16 and FP32).<br>Shows the acceleration of inference by Advanced AMP on Intel CPU and GPU via Docker Container or Bare Metal.|CPU & GPU|
 |[Accelerate AlexNet by Quantization with Intel® Extension for TensorFlow*](./accelerate_alexnet_by_quantization)| An end-to-end example to show a pipeline to build up a CNN model to <br>recognize handwriting number and speed up AI model with quantization <br>by Intel® Neural Compressor and Intel® Extension for TensorFlow* on Intel GPU.|GPU|
-|[Accelerate Deep Learning Inference for Model Zoo Workloads on Intel CPU and GPU](./model_zoo_example)|Examples on running Model Zoo workloads on Intel CPU and GPU with the optimizations from Intel® Extension for TensorFlow*, without any code changes.|CPU & GPU|
-|[Quantize Inception V3 by Intel® Extension for TensorFlow* on Intel® Xeon®](./quantize_inception_v3)|An end-to-end example to show how Intel® Extension for TensorFlow* provides quantization feature by cooperating with Intel® Neural Compressor and oneDNN Graph. It will provide better quantization: better performance and accuracy loss is in controlled.|CPU & GPU|
+|[Accelerate Deep Learning Training and Inference for Model Zoo Workloads on Intel GPU](./model_zoo_example)|Examples on running Model Zoo workloads on Intel GPU with the optimizations from Intel® Extension for TensorFlow*.|GPU|
+|[Quantize Inception V3 by Intel® Extension for TensorFlow* on Intel® Xeon®](./quantize_inception_v3)|An end-to-end example to show how Intel® Extension for TensorFlow* provides quantization feature by cooperating with Intel® Neural Compressor and oneDNN Graph. It will provide better quantization: better performance and accuracy loss is in controlled.|CPU|
 |[ResNet50 and Mnist training with Horovod](./train_horovod)|ResNet50 and Mnist distributed training examples on Intel GPU.|GPU|
 |[Stable Diffusion Inference for Text2Image on Intel GPU](./stable_diffussion_inference)|Example for running Stable Diffusion Text2Image inference on Intel GPU with the optimizations from Intel® Extension for TensorFlow*.|GPU|
 |[Accelerate ResNet50 Training by XPUAutoShard on Intel GPU](./train_resnet50_with_autoshard)|Example on running ResNet50 training on Intel GPU with the XPUAutoShard feature.|GPU|

examples/examples.md

@@ -9,8 +9,8 @@ A wide variety of examples are provided to demonstrate the usage of Intel® Exte
 |[BERT Training for Classifying Text](./train_bert/README.html)|BERT training with Intel® Extension for TensorFlow* on Intel CPU or GPU.<br>Use the TensorFlow official example without code change.|CPU & GPU|
 |[Speed up Inference of Inception v4 by Advanced Automatic Mixed Precision via Docker Container or Bare Metal](./infer_inception_v4_amp/README.html)|Test and compare the performance of inference with FP32 and Advanced Automatic Mixed Precision (AMP) (mix BF16/FP16 and FP32).<br>Shows the acceleration of inference by Advanced AMP on Intel® CPU and GPU via Docker Container or Bare Metal.|CPU & GPU|
 |[Accelerate AlexNet by Quantization with Intel® Extension for TensorFlow*](./accelerate_alexnet_by_quantization/README.html)| An end-to-end example to show a pipeline to build up a CNN model to <br>recognize handwriting number and speed up AI model with quantization <br>by Intel® Neural Compressor and Intel® Extension for TensorFlow* on Intel GPU.|GPU|
-|[Accelerate Deep Learning Inference for Model Zoo Workloads on Intel CPU and GPU](./model_zoo_example/README.html)|Examples on running Model Zoo workloads on Intel CPU and GPU with the optimizations from Intel® Extension for TensorFlow*, without any code changes.|CPU & GPU|
-|[Quantize Inception V3 by Intel® Extension for TensorFlow*](./quantize_inception_v3/README.html)|An end-to-end example to show how Intel® Extension for TensorFlow* provides quantization feature by cooperating with Intel® Neural Compressor and oneDNN Graph. It will provide better quantization: better performance and accuracy loss is in controlled.|CPU & GPU|
+|[Accelerate Deep Learning Training and Inference for Model Zoo Workloads on Intel GPU](./model_zoo_example)|Examples on running Model Zoo workloads on Intel GPU with the optimizations from Intel® Extension for TensorFlow*.|GPU|
+|[Quantize Inception V3 by Intel® Extension for TensorFlow* on Intel® Xeon®](./quantize_inception_v3/README.html)|An end-to-end example to show how Intel® Extension for TensorFlow* provides quantization feature by cooperating with Intel® Neural Compressor and oneDNN Graph. It will provide better quantization: better performance and accuracy loss is in controlled.|CPU|
 |[Mnist training with Intel® Optimization for Horovod*](./train_horovod/mnist/README.html)|Mnist distributed training example on Intel GPU. |GPU|
 |[ResNet50 training with Intel® Optimization for Horovod*](./train_horovod/resnet50/README.html)|ResNet50 distributed training example on Intel GPU. |GPU|
 |[Stable Diffusion Inference for Text2Image on Intel GPU](./stable_diffussion_inference/README.html)|Example for running Stable Diffusion Text2Image inference on Intel GPU with the optimizations from Intel® Extension for TensorFlow*. |GPU|

examples/model_zoo_example/README.md

@@ -1,59 +1,20 @@
-# Accelerating Deep Learning Inference for Model Zoo Workloads on Intel CPU and GPU
+# Accelerate Deep Learning Training and Inference for Model Zoo Workloads on Intel GPU
 
 ## Introduction
-This example shows the guideline to run Model Zoo workloads on Intel CPU and GPU with the optimizations from Intel® Extension for TensorFlow*, without any model code changes.
+This example shows the guideline to run Model Zoo workloads using TensorFlow* framework on Intel GPU with the optimizations from Intel® Extension for TensorFlow*.
 
-## Prerequisites
-For Intel CPU, refer to [Intel CPU software installation](../../docs/install/install_for_cpu.md#intel-cpu-software-installation).
-For Intel GPU, refer to [Intel XPU software installation](../../docs/install/install_for_xpu.md#intel-gpu-software-installation).
+## Quick Start Guide
 
-## Execute
+### Run Models in the Docker Container
 
-### Prepare the Codes
-```bash
-git clone https://github.com/IntelAI/models
-cd models
-git checkout v2.8.0
-```
+- For Intel® Data Center GPU Flex Series
 
-### Sample Use cases
+    Refer to [AI Model Zoo Containers on Flex Series](https://www.intel.com/content/www/us/en/developer/articles/containers/model-zoo-flex-series-containers.html) to run optimized Deep Learning inference workloads.
 
+- For Intel® Data Center GPU Max Series
 
-|Model|Mode|Model Documentation|
-|-|-|-|
-|Inception V3|Inference|[FP32](https://github.com/IntelAI/models/blob/v2.8.0/benchmarks/image_recognition/tensorflow/inceptionv3/inference/fp32/README.md)  [INT8](https://github.com/IntelAI/models/blob/v2.8.0/benchmarks/image_recognition/tensorflow/inceptionv3/inference/int8/README.md)|
-|Inception V4|Inference|[FP32](https://github.com/IntelAI/models/blob/v2.8.0/benchmarks/image_recognition/tensorflow/inceptionv4/inference/fp32/README.md)  [INT8](https://github.com/IntelAI/models/blob/v2.8.0/benchmarks/image_recognition/tensorflow/inceptionv4/inference/int8/README.md)|
-|ResNet50 V1.5|Inference|[FP32](https://github.com/IntelAI/models/blob/v2.8.0/benchmarks/image_recognition/tensorflow/resnet50v1_5/inference/fp32/README.md)  [INT8](https://github.com/IntelAI/models/blob/v2.8.0/benchmarks/image_recognition/tensorflow/resnet50v1_5/inference/int8/README.md)|
+    Refer to [AI Model Zoo Containers on Max Series](https://www.intel.com/content/www/us/en/developer/articles/containers/model-zoo-max-series-containers/model-zoo-max-series-containers.html) to run optimized Deep Learning training and inference workloads.
 
-### Performance Optimization
-- FP16/BF16 INT8 Inference Optimization  
+### Run Models on Bare Metal
 
-  Refer to the above FP32 model documentation, and only set one extra environment variable to enable advanced auto mixed precision Graph optimization before running inference.
-  ```bash
-  export ITEX_AUTO_MIXED_PRECISION=1
-  ```
-- INT8 Inference Optimization
-  
-  To avoid memory copy on GPU, we provide a tool to convert the const to host const for INT8 pretrained-models.
-
-  Take the ResNet50 v1.5 INT8 pb for example,
-  ```
-
-  wget https://storage.googleapis.com/intel-optimized-tensorflow/models/v1_8/resnet50v1_5_int8_pretrained_model.pb
-
-  python host_const.py -i <path to the frozen graph downloaded above>/resnet50v1_5_int8_pretrained_model.pb -b -o <path to save the converted frozen graph>/resnet50v1_5_int8_pretrained_model-hostconst.pb
-  ```
-  Use the new INT8 pb for INT8 inference, After converting to the new INT8 pb.
-
-## FAQ
-1.  During the Inception V3 INT8 batch inference, if running with real data, you might encounter a message "Running out of images from dataset". It is a known issue of Model Zoo script.
-
-Solution: 
-
-- Option 1: Please use dummy data instead. 
-
-- Option 2: If you want to run inference with real data, use the command below. And comment the last line of below int8_batch_inference.sh script to unspecify the warmup_steps and steps.  
-```bash
-cd models
-vi ./quickstart/image_recognition/tensorflow/inceptionv3/inference/cpu/int8/int8_batch_inference.sh
-```
+Refer to [AI Model Zoo Examples on Intel® Data Center GPU](https://github.com/IntelAI/models/tree/master#intel-data-center-gpu-workloads) to run optimized Deep Learning training and inference workloads on bare metal.