[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

@@ -4,16 +4,22 @@ MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicatio
 
 MobileNetV2: Inverted Residuals and Linear Bottlenecks
 
+**Note**:
+- `image_classification_mobilenetvX_2022apr_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 |
 | ------------------ | -------------- | -------------- |
 | MobileNet V1       | 67.64          | 87.97          |
+| MobileNet V1 block | 67.21          | 87.62          |
 | MobileNet V1 quant | 55.53          | 78.74          |
 | MobileNet V2       | 69.44          | 89.23          |
+| MobileNet V2 block | 68.66          | 88.90          |
 | MobileNet V2 quant | 68.37          | 88.56          |
 
 \*: 'quant' stands for 'quantized'.
+\*\*: 'block' stands for 'blockwise quantized'.
 
 ## Demo