[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

@@ -15,7 +15,7 @@ Results of accuracy evaluation with [tools/eval](../../tools/eval) at different
 
 \*: 'FP16' or 'INT8' stands for 'model quantized into FP16' or 'model quantized into int8'
 
-Note:
+**Note**:
 
 - Model source:
   - `text_recognition_CRNN_EN_2021sep.onnx`: https://docs.opencv.org/4.5.2/d9/d1e/tutorial_dnn_OCR.html (CRNN_VGG_BiLSTM_CTC.onnx)
@@ -25,6 +25,7 @@ Note:
 - `text_recognition_CRNN_CH_2021sep.onnx` can detect digits (0\~9), upper/lower-case letters (a\~z and A\~Z), and some special characters (see `CHARSET_CH_94` for details in `crnn.py`).
 - `text_recognition_CRNN_CN_2021nov.onnx` can detect digits (0\~9), upper/lower-case letters (a\~z and A\~Z), some Chinese characters and some special characters (see `CHARSET_CN_3944` for details in `crnn.py`).
 - For details on training this model series, please visit https://github.com/zihaomu/deep-text-recognition-benchmark.
+- `text_recognition_CRNN_XX_2021xxx_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`.
 
 ## Demo