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
您好,请问用给出的预训练权重微调分类模型, 多个Epoch 后得到的准确率只有 7%,请问是什么原因呢 [11/21 11:46:59 train]: Epoch: [68][99/104] ETA: 0:13:42 total_loss: 3.048 iter_time: 0.0598 data_time: 0.0002 lr: 0.0022951 max_mem: 4538M [11/21 11:47:01 train]: Epoch: 68 acc@1: 3.1250 acc@5: 16.8269 [11/21 11:47:01 train]: Max accuracy: 7.45%
我的 UCM 数据集是按照 8:2 去分割的
数据集: freeway23.tif 8 tenniscourt49.tif 20 mediumresidential89.tif 12 river83.tif 16
The text was updated successfully, but these errors were encountered:
我也一样,在UCM分类上,我用给的预训练权重训练200个epoch,准确率也是个位数,用作者放出来的微调好的权重,准确率也只有17%
Sorry, something went wrong.
No branches or pull requests
您好,请问用给出的预训练权重微调分类模型, 多个Epoch 后得到的准确率只有 7%,请问是什么原因呢
[11/21 11:46:59 train]: Epoch: [68][99/104] ETA: 0:13:42 total_loss: 3.048 iter_time: 0.0598 data_time: 0.0002 lr: 0.0022951 max_mem: 4538M
[11/21 11:47:01 train]: Epoch: 68 acc@1: 3.1250 acc@5: 16.8269
[11/21 11:47:01 train]: Max accuracy: 7.45%
我的 UCM 数据集是按照 8:2 去分割的
数据集:
freeway23.tif 8
tenniscourt49.tif 20
mediumresidential89.tif 12
river83.tif 16
The text was updated successfully, but these errors were encountered: