Viet Vo

Hello guys I have an issue with pre-trained model from this repo. I am trying to follow Cat and Dog notebook to load "pre-trained" model as below ``` import torch...

Hello guys I also follow another code in readme to load "pre-trained" model as below ``` import torch from vit_pytorch import ViT v = ViT( image_size = 256, patch_size =...

Hello, I have the same concern. 1. After downloading caltech256, it has totally 257 sub_folders and one .txt file to list down all folder name. So I guess if I...

@ginevracoal , thanks

I have the same question. Why the implementation of this approach does not clip the image within the range `[0,1]`. Without clarification, I think it is a pitfall. When using...

Hi BXuan I am not sure whether **dataset4u-trn.txt / dataset4u-val.txt** keep image data under a certain format or just keep the folder name (or label). When I read your code,...

Thanks @Hanjun-Dai Follow this instruction, I can clone both of them. I think you should change your instruction in order that other guys do not encounter the same issue.

Hi @Hanjun-Dai It seems that I cannot install an old version by following your instruction. I got an error as below when doing pip install. Any way to reuse your...

@xuyxu , this is my main script. ```python def load_ensemble_model(arch): if arch =='ensemble': model_path = './models/VotingClassifier_VGG_10_ckpt_no_dropout.pth' base_estimator = VGG('VGG16') ensemble = VotingClassifier( estimator=base_estimator, # estimator is your pytorch model n_estimators=10,...

@xuyxu Do you know what is going with `AdversarialTrainingClassifier`? Have you verify the implementation of this?