YoadTew / zero-shot-image-to-text

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

time-step in code #5

Closed heliossun closed 1 year ago

heliossun commented 2 years ago

In paper section 5: Experiments, you mentioned a variable called time-step t_e, but in code, I can't find it. Please help me. Thank you so much!

YoadTew commented 2 years ago

Its the self.ef_idx variable in the CLIPTextGenerator class