Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.
MIT License
708
stars
73
forks
source link
Improved conversion stability when `H`, `W` and `D` of `MaxPool` and `AveragePool` contain undefined dimensions #620
Improved conversion stability when H, W and D of MaxPool and AveragePool contain undefined dimensions.
The accuracy of the converted model is not always accurate.
e.g. YOLOv8n dynamic inputs [N, 3, H, W]
YOLOvN has been modified only to avoid a situation where the conversion aborts, although this is undoubtedly not good for the design of the model, as fixed parameters such as the number of classes are embedded in the backward Split operation with fixed values.
Concatenating dimensions that have completely different meanings is also a major problem.
Unless you replace the PyTorch implementation with Slice, you won't be able to do proper inferencing.
ONNX
TFLite
2. Summary of corrections
3. Before/After (If there is an operating log that can be used as a reference)
4. Issue number (only if there is a related issue)
1. Content and background
MaxPool,AveragePoolH,WandDofMaxPoolandAveragePoolcontain undefined dimensions.[N, 3, H, W]Splitoperation with fixed values.Slice, you won't be able to do proper inferencing.2. Summary of corrections
3. Before/After (If there is an operating log that can be used as a reference)
4. Issue number (only if there is a related issue)