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
使用resrep对yolov5l, yolov5m剪枝,网络无法训练,一开始就就不收敛直接变nan。
The text was updated successfully, but these errors were encountered:
不确定,我自己没在这上边训练过。用了预训练模型吗?不用 resrep 的时候能训练不
Sorry, something went wrong.
没用预训练模型,不用resrep可以收敛。
刚开始训练的时候不适合剪枝;可以调参数,增大 warmup_epoch(前多少轮不剪),prune_interval(单位是 iter不是epoch)也可以改大点
还有个问题,就是我发现载剪枝训练过程中某些层通道被剪完了,然后就会报错。有什么方法可以设置每层最低保留的通道数吗?
目前没有吧。它确实有可能每次剪枝都找到同一个层,你可以自己加,在算 lasso 那块 torchslim/pruning/resrep.py: def prune_model(...): index = np.argsort(lasso_value) 这
def prune_model(...): index = np.argsort(lasso_value)
No branches or pull requests
使用resrep对yolov5l, yolov5m剪枝,网络无法训练,一开始就就不收敛直接变nan。
The text was updated successfully, but these errors were encountered: