search

Chris-hughes10 / Yolov7-training

A clean, modular implementation of the Yolov7 model family, which uses the official pretrained weights, with utilities for training the model on custom (non-COCO) tasks.
GNU General Public License v3.0
116 stars 35 forks source link

Fixed mixed precision #23

Closed lars-nieradzik closed 7 months ago

lars-nieradzik commented 7 months ago

binary_cross_entropy_with_logits is required for AMP. Refer to https://github.com/WongKinYiu/yolov7/blob/a207844b1ce82d204ab36d87d496728d3d2348e7/utils/loss.py#L731 in the original YOLOv7 code.

Chris-hughes10 commented 7 months ago

Looks great, one minor nit, would you add a comment above to highlight that we are doing this due to mixed precision support?

lars-nieradzik commented 7 months ago

Okay, done.