Update README.md

README.md

@@ -22,7 +22,7 @@ After, refer the path to OFA-huge to `ckpt_dir`, and prepare an image for the te
 >>> from generate import sequence_generator
 
 >>> mean, std = [0.5, 0.5, 0.5], [0.5, 0.5, 0.5]
->>> resolution = 256
+>>> resolution = 480
 >>> patch_resize_transform = transforms.Compose([
         lambda image: image.convert("RGB"),
         transforms.Resize((resolution, resolution), interpolation=Image.BICUBIC),
@@ -30,7 +30,7 @@ After, refer the path to OFA-huge to `ckpt_dir`, and prepare an image for the te
         transforms.Normalize(mean=mean, std=std)
     ])
 
->>> model = OFAModel.from_pretrained(ckpt_dir)
+
 >>> tokenizer = OFATokenizer.from_pretrained(ckpt_dir)
 
 >>> txt = " what does the image describe?"
@@ -40,16 +40,16 @@ After, refer the path to OFA-huge to `ckpt_dir`, and prepare an image for the te
 
 
 >>> # using the generator of fairseq version
->>> generator = sequence_generator.SequenceGenerator(tokenizer=tokenizer,beam_size=5,
-                                                                      max_len_b=16,
-                                                                      min_len=0,
-                                                                      no_repeat_ngram_size=3) # using the generator of fairseq version
+>>> model = OFAModel.from_pretrained(ckpt_dir, use_cache=True)
+>>> generator = sequence_generator.SequenceGenerator(tokenizer=tokenizer,beam_size=5, max_len_b=16, 
+                    min_len=0, no_repeat_ngram_size=3) # using the generator of fairseq version
 >>> data = {}
 >>> data["net_input"] = {"input_ids": inputs, 'patch_images': patch_img, 'patch_masks':torch.tensor([True])}
 >>> gen_output = generator.generate([model], data)
 >>> gen = [gen_output[i][0]["tokens"] for i in range(len(gen_output))]
 
 >>> # using the generator of huggingface version
+>>> model = OFAModel.from_pretrained(ckpt_dir, use_cache=False)
 >>> gen = model.generate(inputs, patch_images=patch_img, num_beams=5, no_repeat_ngram_size=3) 
 
 >>> print(tokenizer.batch_decode(gen, skip_special_tokens=True))