apple
/

MobileCLIP-S2-OpenCLIP

Zero-Shot Image Classification

Model card Files Files and versions Community

Resources

View closed (3)

Why doesn't the S1/S2 text encoder use attn_mask or key_padding_mask to deal with padding tokens?

#5 opened 3 months ago by

the scores distribution is all around 0.2, why is that

#4 opened 6 months ago by

The inference speed of MobileCLIP-S2's image encoder is slower than OpenCLIP's ViT-B-32-256 model on both CPU and GPU

#3 opened 8 months ago by