Zayn
/

AICVTG_What_if_a_machine_could_create_captions_automatically

vision-encoder-decoder

image-text-to-text

image-captioning

Inference Endpoints

Model card Files Files and versions Community

Zayn commited on Oct 23, 2022

Commit

a033e49

·

1 Parent(s): 27b15e3

Update README.md

Files changed (1) hide show

README.md +2 -2

README.md CHANGED Viewed

@@ -27,8 +27,8 @@ model.to(device)
-max_length = 16
-num_beams = 4
 gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
 def predict_step(image_paths):
   images = []

+max_length = 20
+num_beams = 8
 gen_kwargs = {"max_length": max_length, "num_beams": num_beams}
 def predict_step(image_paths):
   images = []