-
Notifications
You must be signed in to change notification settings - Fork 5.6k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Update paths to Quant models #32870
Update paths to Quant models #32870
Conversation
Thanks for your contribution! |
- `ResNet50_qat_perf`, with input/output scales in `fake_quantize_moving_average_abs_max` operators, with weight scales in `fake_dequantize_max_abs` operators | ||
- `ResNet50_qat_range`, with input/output scales in `fake_quantize_range_abs_max` operators and the `out_threshold` attributes, with weight scales in `fake_dequantize_max_abs` operators | ||
- `ResNet50_qat_channelwise`, with input/output scales in `fake_quantize_range_abs_max` operators and the `out_threshold` attributes, with weight scales in `fake_channel_wise_dequantize_max_abs` operators | ||
- `MobileNet_qat_perf`. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This line means MobileNet_qat_perf has same rule as ResNet50_qat_perf to change names and then download MobileNet related models successfully?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I mean line 233 looks like single line you may delete it. Thanks
LGTM. |
@luotao1 Could you please start your review? |
PR types
Bug fixes
PR changes
Docs
Describe
This PR:
ResNet50_qat_range
orResNet50_qat_channelwise