YoadTew / zero-shot-image-to-text

Implementation of Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic

YoadTew/zero-shot-image-to-text Issues

How the entire dataset is converted into captions
Updated 10 months ago4
run.py
Updated a year ago
Questions about modifying context cache?
Updated a year ago5
the generated caption effect is not good（The main reason is that the resolution of the picture is too low）
Updated a year ago
Precict.py Question
Updated a year ago
I encountered a problem while running the code. Please help me solve it. Thank you
Closed a year ago
UnboundLocalError - 'context' reference before assignment
Updated a year ago7
in model/ZeroCLIP.py tmp_weights in 290 row is not used
Updated a year ago1
Should I additionally set end_factor to 1.04 in the command and set the variable self.ef_idx to 3 in class CLIPTextGenerator to reproduce image caption results?
Updated a year ago1
Any evaluate script provided to quickly calculate the metrics in this paper?
Updated a year ago1
Question about the cache update
Closed 2 years ago
About Eq.(5) in paper
Updated 2 years ago
time-step in code
Closed 2 years ago1
Metrics Computations : B@1 = BLEU-1, M = METEOR, C = CIDEr, S = SPICE.
Updated 2 years ago
Colab notebook availability
Updated 3 years ago