The MCT should be taking in a floating-point PyTorch model in this case, not a quantised ONNX model as suggested by the above step 7. The MCT step 8 does the compression/quantisation.The process I'm going through to produce the model is:
1. Collect Images
2. Annotate Images (using labelimg)
3. Split Data - into train and val for training and testing the model
4. Train - run 50 or so epochs of training
5. Evaluate - looking at the graphs that are produced
6. Deploy - converting the model to onnx format using PyTorch
7. Quantize - using either PyTorch or the ONNX library
8. Compress using the MCT
Statistics: Posted by naushir — Thu Oct 24, 2024 7:52 am