Harshita Mangal
Harshita Mangal
HI @YouYueHuang, let me know if you have any questions.
@YouYueHuang, you will also need to use the https://quic.github.io/aimet-pages/AimetDocs/api_docs/torch_quantsim.html#api-torch-quantsim API for quantizing the model. As @quic-akhobare mentioned they should be well explained with an example in the documentation, but if...
@roycyh we use the following hyper-parameters- Batch size = 256 LR = 0.01 and it is reduced by a factor of 10 for epochs [20, 35]. Let us know if...
@quic-bharathr, could you help reply to this. Thanks
Can you check if your PYTHONPATH is set correctly?
@Piotr94, AIMET does not support adjusted_weights_quantizer, could you disable it SNPE as well. Also, are you using Per channel quantization in AIMET, since it is being used with SNPE in...
Yes, looks like it is not documented. For per channel you can an example here- https://github.com/quic/aimet/blob/develop/NightlyTests/torch/test_quantize_resnet18.py You need to change the config file that is passed to Quantsim as show...
@cosperypf, can you sign the commit as pointed out by Abhi.
Closing this issue due to inactivity. Please re-open it/ create a new issue if you need further help.
Closing this issue due to inactivity. Please re-open it/ create a new issue if you need further help.