search

YoadTew / zero-shot-image-to-text

Implementation of Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic
262 stars 42 forks source link

run.py #18

Open deyi89 opened 10 months ago

deyi89 commented 10 months ago

File "../run.py", line 61 best_clip_idx = (torch.cat(encoded_captions) @ image_features.t()).squeeze().argmax().item() ^ SyntaxError: invalid syntax