search

leaderj1001 / BottleneckTransformers

Bottleneck Transformers for Visual Recognition
MIT License
274 stars 50 forks source link

RuntimeError: The size of tensor a (4) must match the size of tensor b (196) at non-singleton dimension 2 #13

Open YePG opened 3 years ago

YePG commented 3 years ago

RuntimeError: The size of tensor a (4) must match the size of tensor b (196) at non-singleton dimension 2

I'm using your code. And I didn't make any changes

YePG commented 3 years ago

I run the main.py

mfawzy commented 3 years ago

@YePG, you need to change the settings of ImageNet to CIFAR-10 in the model file

line 144: def ResNet50(num_classes=10, resolution=(32, 32), heads=4):

YePG commented 3 years ago

Thank you. I have solved this problem. Have you pre-trained on Image Net before?Can you provide me with the best model file?

------------------ 原始邮件 ------------------ 发件人: @.>; 发送时间: 2021年4月27日(星期二) 上午6:09 收件人: @.>; 抄送: @.>; @.>; 主题: Re: [leaderj1001/BottleneckTransformers] RuntimeError: The size of tensor a (4) must match the size of tensor b (196) at non-singleton dimension 2 (#13)

@YePG, you need to change the settings of ImageNet to CIFAR-10 in the model file

line 144: def ResNet50(num_classes=10, resolution=(32, 32), heads=4):

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub, or unsubscribe.