Quantization and Pruning
seekingdeep opened this issue · comments
seekingdeep commented
@songqi-github
Have you considered to Quantize
the ResNet18 model > Training
the model > Pruning
the trained model > Finetuning
?
i believe that the final ResNet18 model could achieve much more efficiency and fps, while maintaining almost same accuracy.
Qi Song commented
Hi, I haven't tried this before. Maybe you can try it out and make the model more efficient.