* 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
* bump opencv version to 4.10.0
* doc: version change
* fix version control
* fix version control for efficient sam
C++ Demo - Image Classification (PPResNet) (#241)
Ryan Lee
30e431e
* Functional version of C++ demo.
* Improve printout.
* Remove printouts and add README examples
* Add goldfish example
* Add empty space at EOF
* Add empty line at EOF for Python
* Use the shared labels.txt file instead of having the entire list as a variable in the demo.py
* Address PR comments. Revert example and labels
* Use namespaces for brevity
* Follow OpenCV formatting
* Remove LoadLabel() and use a vector of strings instead of having redundant work.
* bump version to 4.8.0
* update benchmark results on i7 & rpi
* correct python command on i7
* update results on jetson nano
* update results on atlas 200 cpu
* update results on vim3 cpu, sunrise x3 cpu
* update results on vim3 npu
* update results on edge2
* update results on rv1126 and vision2
* update results on axp
* update table
Limit combinations of backends and targets in demos and benchmark (#145)
add model path searcher and remove hardwritten file paths from benchmark configs; pack ppresnet, mobilenet & crnn with labels; fix palm det data; add flags to enable models of different precision separately (#123)
Merge pull request #95 from Satgoy152:adding-doc
Satyam Goyal
e7d94f5
Improved help messages for demo programs (#95)
- Added Demo Documentation
- Updated help messages
- Changed exception link
add evaluation framework and imagenet evaluation (#69)
update ONNX opset version of PP-ResNet50 to 11 (#37)
Yuantao Feng
2074f99
Bug fixes and corrections (#33)
Yuantao Feng
f134c2e
* add (ms) to each hardware header
* add a argument for label path
* correct filenames for face detection
* add a download link for face recognition data
* fix path to face recognition data
* correct shasum for face_detection.zip
* fix filename for person_reid benchmark data package
correct default values of model filenames in demo scripts (#11)
Yuantao Feng
9e1d36f
Add PPResNet from PaddleHub conversion (#4)
Yuantao Feng
e0b3895
* add PPResNet impl and demo
* add benchmark impl and results for PPResNet
