InceptionE should use different instances of FloatFunctional #1948

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.

Sign up for GitHub

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

Jump to bottom

Closed

jerryzh168 opened this issue Mar 6, 2020 · 3 comments

Assignees

Labels

module: models.quantization

Contributor

jerryzh168 commented Mar 6, 2020

https://github.com/pytorch/vision/blob/master/torchvision/models/quantization/inception.py#L138-L166
We need to use different instances of FloatFunctional at each invocation of cat

jerryzh168 added the module: models.quantization label

Contributor Author

jerryzh168 commented Mar 6, 2020 •

edited

Loading

need to modify this code and requantize and update the model here: https://download.pytorch.org/models/quantized/inception_v3_google_fbgemm-4f6e4894.pth
cc @raghuramank100 @hx89 @z-a-f

raghuramank100 assigned hx89

hx89 mentioned this issue

Fix the issue: InceptionE should use different instances of FloatFunctional #1948 #1954

Merged

Member

fmassa commented Mar 10, 2020

Fixed via #1954

fmassa closed this as completed

Contributor

hx89 commented Mar 14, 2020

Updated inception quantized model path in #1969 and updated quantized inception accuracy number in README.md via #1975.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment