pytorch
071f8750 - [quant] Fix per channel weight observer (#85883)

Commit
2 years ago
[quant] Fix per channel weight observer (#85883) Summary: `per_channel_weight_observer_range_neg_127_to_127` now correctly uses `PerChannelMinMaxObserver` instead of `MinMaxObserver` Test Plan: Adds a new test `quantization.core.test_top_level_apis ` to instansiate and run `forward()` on all `default` observers Differential Revision: D39916482 Pull Request resolved: https://github.com/pytorch/pytorch/pull/85883 Approved by: https://github.com/salilsdesai
Author
Committer
Parents
Loading