[GSoC] Add block quantized models (#270)

* Gemm and MatMul block quantization support

* refactoring

* fix indentation

* node name independent

* Block quantization tool:
- constant weight category supported
- add data type saturation
- handled the case in which all the elements within a block are the same

benchmark script modified to support block quantized models

block quantized some models

* add missing block quantized models

* formatting

* add blocked models to eval script. Evaluation yunet

* Add sface and pphumanseg evaluation, block quantization tool fix, handpose blocked model fix, removed blocked CRNN EN,

* changed evaluation metric in block_quantize script and add verbose mode

* Add evaluation for PP-ResNet and Mobilenet

* changed file suffix and update readmes

* renamed int8bq

README.md

@@ -4,14 +4,19 @@ Deep Residual Learning for Image Recognition
 
 This model is ported from [PaddleHub](https://github.com/PaddlePaddle/PaddleHub) using [this script from OpenCV](https://github.com/opencv/opencv/blob/master/samples/dnn/dnn_model_runner/dnn_conversion/paddlepaddle/paddle_resnet50.py).
 
+**Note**:
+- `image_classification_ppresnet50_2022jan_int8bq.onnx` represents the block-quantized version in int8 precision and is generated using [block_quantize.py](../../tools/quantize/block_quantize.py) with `block_size=64`.
+
 Results of accuracy evaluation with [tools/eval](../../tools/eval).
 
 | Models          | Top-1 Accuracy | Top-5 Accuracy |
 | --------------- | -------------- | -------------- |
 | PP-ResNet       | 82.28          | 96.15          |
+| PP-ResNet block | 82.27          | 96.15          |
 | PP-ResNet quant | 0.22           | 0.96           |
 
 \*: 'quant' stands for 'quantized'.
+\*\*: 'block' stands for 'blockwise quantized'.
 
 ## Demo