We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
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
已经更新代码,解决了损失值为nan的问题,在kld损失中,分母部分加上了eps值避免loss值为0
从第一步开始loss就为nan,如果换成adam优化器,lr设置1e-3,训练3步出现nan。
The text was updated successfully, but these errors were encountered:
继续降低学习率,或者检查下数据集标注
Sorry, something went wrong.
No branches or pull requests
Originally posted by @Egrt in #18 (comment)
我使用的3090显卡,训练参数如下:
Configurations:
| keys | values|
| classes_path | model_data/test.txt|
| anchors_path | model_data/yolo_anchors.txt|
| anchors_mask | [[6, 7, 8], [3, 4, 5], [0, 1, 2]]|
| model_path | |
| input_shape | [960, 960]|
| Init_Epoch | 0|
| Freeze_Epoch | 3|
| UnFreeze_Epoch | 500|
| Freeze_batch_size | 2|
| Unfreeze_batch_size | 8|
| Freeze_Train | False|
| Init_lr | 0.01|
| Min_lr | 0.0001|
| optimizer_type | sgd|
| momentum | 0.937|
| lr_decay_type | step|
| save_period | 5|
| save_dir | logs_gf1pms|
| num_workers | 8|
| num_train | 2740|
| num_val | 305|
从第一步开始loss就为nan,如果换成adam优化器,lr设置1e-3,训练3步出现nan。
The text was updated successfully, but these errors were encountered: