Skip to content
New issue

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

在训练过程中,验证集的准确率在50左右波动 #6

Open
xhlbkcc opened this issue Jul 30, 2024 · 0 comments
Open

在训练过程中,验证集的准确率在50左右波动 #6

xhlbkcc opened this issue Jul 30, 2024 · 0 comments

Comments

@xhlbkcc
Copy link

xhlbkcc commented Jul 30, 2024

您好,我在训练过程中遇到了验证集表现不佳的问题,希望能得到您的帮助。
在训练时,由于物理硬件限制,我每个视频截取了只60帧(4个连续的15帧),修改了dataset.py中的seq_len和network.py中的chunks以及卷积核的大小,其他参数设置未进行修改,batchsize=30,在24g显存的GPU上使用混合精度进行单gpu训练。
在迭代过程中的Epoch8,训练集的ACC就已经达到了100,但是验证集上的ACC和AUC却开始下降,以下是部分训练的结果。
Epoch8: Acc:52.500 Auc:87.726 Pre:51.289 Rec:99.500 F1:67.687
Epoch9: Acc:52.300 Auc:87.908 Pre:51.182 Rec:99.600 F1:67.617
Epoch10: Acc:52.750 Auc:88.515 Pre:51.421 Rec:99.500 F1:67.802
Epoch11: Acc:52.250 Auc:86.633 Pre:51.157 Rec:99.500 F1:67.572
请问模型是不是发生了过拟合现象,我应该怎么修改才能得到较好的结果?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant