You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi, I found that if I don't use the preetrained model, the code don't work. So I can't train from scratch? If I need to train with other dataset like Imagenet, or use other backbone like resnet50, how can I find pretrained model? Thank you.
The text was updated successfully, but these errors were encountered:
yeah like for example we want to check for dogs and cats classification.so if we gave them as input,it will show type mismatch error
while loading pretrained models weights and bias(cifar10) because they were trained on 10 classes.so what should we do now?
Our method is add-on module on top of the off-the-shelf clustering model.
So I also borrowed pretrained model from SCAN github. https://github.com/wvangansbeke/Unsupervised-Classification
If you want to train from scratch, please refer above SCAN github :)
Hi, I found that if I don't use the preetrained model, the code don't work. So I can't train from scratch? If I need to train with other dataset like Imagenet, or use other backbone like resnet50, how can I find pretrained model? Thank you.
The text was updated successfully, but these errors were encountered: