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

predict缺少eval_top #1

Open
shengdada opened this issue Jul 20, 2022 · 4 comments
Open

predict缺少eval_top #1

shengdada opened this issue Jul 20, 2022 · 4 comments

Comments

@shengdada
Copy link

兄弟,predict.py中没有from eval import eval_top呀

@jiantenggei
Copy link
Owner

是因为 我在使用人脸表情数据集训练的时候 发现验证集准确率与训练时验证的不一样,所以给删除掉了

@shengdada
Copy link
Author

哇中国速度!兄弟。另外有个疑问,nets.MLPmixer是不能直接替换
model = ConvMixer_768_32(n_classes=num_classes)么?发现MLPMixer(in_channels=3, dim=512, num_classes=1000, patch_size=16, image_size=224, depth=1, token_dim=256,channel_dim=2048)模型中image_size参数是图像尺寸,而数据集中图像尺寸都是不同的,想用MLPmixer不知道如何设置该参数。感谢!

@jiantenggei
Copy link
Owner

jiantenggei commented Jul 26, 2022 via email

@shengdada
Copy link
Author

牛的,原来如此,这个参数image_size就是config中设置的input_shape=[48,48] 参数。

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

2 participants