update INC link (#494)

Signed-off-by: mengniwa <[email protected]>

Co-authored-by: Wenbing Li <[email protected]>

Author: mengniwang95

text/machine_comprehension/bert-squad/README.md

@@ -118,7 +118,7 @@ Metric is Exact Matching (EM) of 80.7, computed over SQuAD v1.1 dev data, for th
 Fine-tuned the model using SQuAD-1.1 dataset. Look at [BertTutorial.ipynb](https://github.com/onnx/tensorflow-onnx/blob/master/tutorials/BertTutorial.ipynb) for more information for converting the model from tensorflow to onnx and for fine-tuning
 
 ## Quantization
-BERT-Squad-int8 is obtained by quantizing BERT-Squad model (opset=12). We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel-innersource/frameworks.ai.lpot.intel-lpot/blob/master/examples/onnxrt/onnx_model_zoo/bert-squad/readme.md) to understand how to use Intel® Neural Compressor for quantization.
+BERT-Squad-int8 is obtained by quantizing BERT-Squad model (opset=12). We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/language_translation/onnx_model_zoo/bert-squad/quantization/ptq/readme.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.9.0 

vision/classification/alexnet/README.md

@@ -15,7 +15,7 @@
 >
 > **Note** 
 >
-> Different preprocess methods will lead to different accuracies, the accuracy in table depends on this specific [preprocess method](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/onnx_model_zoo/alexnet/main.py).
+> Different preprocess methods will lead to different accuracies, the accuracy in table depends on this specific [preprocess method](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/alexnet/quantization/ptq/main.py).
 > 
 > The performance depends on the test hardware. Performance data here is collected with Intel® Xeon® Platinum 8280 Processor, 1s 4c per instance, CentOS Linux 8.3, data batch size is 1.
 
@@ -63,7 +63,7 @@ This model obtains a top-1 accuracy 57.1% and a top-5 accuracy
 should obtain a bit higher accuracy.)
 
 ## Quantization
-AlexNet-int8 is obtained by quantizing fp32 AlexNet model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/onnx_model_zoo/alexnet/README.md) to understand how to use Intel® Neural Compressor for quantization.
+AlexNet-int8 is obtained by quantizing fp32 AlexNet model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/alexnet/quantization/ptq/README.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.9.0 

vision/classification/caffenet/README.md

@@ -15,7 +15,7 @@
 >
 > **Note** 
 >
-> Different preprocess methods will lead to different accuracies, the accuracy in table depends on this specific [preprocess method](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/onnx_model_zoo/caffenet/main.py).
+> Different preprocess methods will lead to different accuracies, the accuracy in table depends on this specific [preprocess method](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/caffenet/quantization/ptq/main.py).
 > 
 > The performance depends on the test hardware. Performance data here is collected with Intel® Xeon® Platinum 8280 Processor, 1s 4c per instance, CentOS Linux 8.3, data batch size is 1.
 
@@ -64,7 +64,7 @@ This model obtains a top-1 accuracy 57.4% and a top-5 accuracy
 should obtain a bit higher accuracy still.)
 
 ## Quantization
-CaffeNet-int8 is obtained by quantizing fp32 CaffeNet model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/onnx_model_zoo/caffenet/README.md) to understand how to use Intel® Neural Compressor for quantization.
+CaffeNet-int8 is obtained by quantizing fp32 CaffeNet model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/caffenet/quantization/ptq/README.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.9.0 

vision/classification/inception_and_googlenet/googlenet/README.md

@@ -103,7 +103,7 @@ just the center crop. (Using the average of 10 crops,
 (4 + 1 center) * 2 mirror, should obtain a bit higher accuracy.)
 
 ## Quantization
-GoogleNet-int8 is obtained by quantizing fp32 GoogleNet model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel-innersource/frameworks.ai.lpot.intel-lpot/blob/master/examples/onnxrt/onnx_model_zoo/googlenet/README.md) to understand how to use Intel® Neural Compressor for quantization.
+GoogleNet-int8 is obtained by quantizing fp32 GoogleNet model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/googlenet/quantization/ptq/README.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.9.0 

vision/classification/resnet/README.md

@@ -109,7 +109,7 @@ We used MXNet as framework with gluon APIs to perform training. View the [traini
 We used MXNet as framework with gluon APIs to perform validation. Use the notebook [imagenet_validation](../imagenet_validation.ipynb) to verify the accuracy of the model on the validation set. Make sure to specify the appropriate model name in the notebook.
 
 ## Quantization
-ResNet50_int8 is obtained by quantizing ResNet50_fp32 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/onnx_model_zoo/resnet50/README.md) to understand how to use Intel® Neural Compressor for quantization.
+ResNet50_int8 is obtained by quantizing ResNet50_fp32 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/resnet50/quantization/ptq/README.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.7.0 
@@ -154,4 +154,4 @@ In European Conference on Computer Vision, pp. 630-645. Springer, Cham, 2016.
 * [hshen14](https://github.com/hshen14) (Intel)
 
 ## License
-Apache 2.0
+Apache 2.0

vision/classification/shufflenet/README.md

@@ -79,7 +79,7 @@ Details of performance on COCO object detection are provided in [this paper](htt
 <hr>
 
 ## Quantization
-ShuffleNet-v2-int8 is obtained by quantizing ShuffleNet-v2-fp32 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/onnx_model_zoo/shufflenet/README.md) to understand how to use Intel® Neural Compressor for quantization.
+ShuffleNet-v2-int8 is obtained by quantizing ShuffleNet-v2-fp32 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/shufflenet/quantization/ptq/README.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.9.0 

vision/classification/squeezenet/README.md

@@ -64,7 +64,7 @@ We used MXNet as framework with gluon APIs to perform training. View the [traini
 We used MXNet as framework with gluon APIs to perform validation. Use the notebook [imagenet_validation](../imagenet_validation.ipynb) to verify the accuracy of the model on the validation set. Make sure to specify the appropriate model name in the notebook.
 
 ## Quantization
-SqueezeNet 1.0-int8 is obtained by quantizing fp32 SqueezeNet 1.0 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel-innersource/frameworks.ai.lpot.intel-lpot/blob/master/examples/onnxrt/onnx_model_zoo/squeezenet/README.md) to understand how to use Intel® Neural Compressor for quantization.
+SqueezeNet 1.0-int8 is obtained by quantizing fp32 SqueezeNet 1.0 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/squeezenet/quantization/ptq/README.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.9.0 

vision/classification/vgg/README.md

@@ -81,7 +81,7 @@ We used MXNet as framework with gluon APIs to perform training. View the [traini
 We used MXNet as framework with gluon APIs to perform validation. Use the notebook [imagenet_validation](../imagenet_validation.ipynb) to verify the accuracy of the model on the validation set. Make sure to specify the appropriate model name in the notebook.
 
 ## Quantization
-VGG 16-int8 is obtained by quantizing VGG 16-fp32 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/onnx_model_zoo/vgg16/README.md) to understand how to use Intel® Neural Compressor for quantization.
+VGG 16-int8 is obtained by quantizing VGG 16-fp32 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/vgg16/quantization/ptq/README.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.9.0 

vision/classification/zfnet-512/README.md

@@ -52,7 +52,7 @@ random generated sampe test data:
 ## Results/accuracy on test set
 
 ## Quantization
-ZFNet-512-int8 is obtained by quantizing fp32 ZFNet-512 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel-innersource/frameworks.ai.lpot.intel-lpot/blob/master/examples/onnxrt/onnx_model_zoo/zfnet/README.md) to understand how to use Intel® Neural Compressor for quantization.
+ZFNet-512-int8 is obtained by quantizing fp32 ZFNet-512 model. We use [Intel® Neural Compressor](https://github.com/intel/neural-compressor) with onnxruntime backend to perform quantization. View the [instructions](https://github.com/intel/neural-compressor/blob/master/examples/onnxrt/image_recognition/onnx_model_zoo/zfnet/quantization/ptq/README.md) to understand how to use Intel® Neural Compressor for quantization.
 
 ### Environment
 onnx: 1.9.0