The implementation of our ACM MM 2023 paper "AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning"
The implementation of our ACM MM 2023 paper "AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learning"
数据问题
No such file or directory: 'data/xmedianet/train.pkl'
Expected 3D (unbatched) or 4D (batched) input to conv2d, but got input of size: [32, 1024]
NameError: name 'Dataset' is not defined
Could you update the data from another source? I can not download the data from the cloud storage.
Conflict in dependencies