Fix breakage in torch quanitization import

facebookresearch / ClassyVision

An end-to-end PyTorch framework for image and video classification

https://classyvision.ai

MIT License

1.59k stars 278 forks source link

Closed mannatsingh closed 2 years ago

mannatsingh commented 2 years ago

Summary: D31260088 (https://github.com/facebookresearch/ClassyVision/commit/4785d5ee19d3bcedd5b28c1eb51ea1f59188b54d) moved quantization imports to torch.ao.quantization, but in pytorch 1.10 torch.ao.quantization.quantize_fx does not exist. Changing the check to pytorch 1.11 so this starts getting used from the next release.

Differential Revision: D32809959

facebook-github-bot commented 2 years ago

This pull request was exported from Phabricator. Differential Revision: D32809959

facebook-github-bot commented 2 years ago

This pull request was exported from Phabricator. Differential Revision: D32809959