Update README.md

README.md

@@ -32,11 +32,12 @@ You can use this model for conditional and un-conditional image captioning
 <summary> Click to expand </summary>
 
 ```python
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
 
-from transformers import BlipProcessor, BlipForImageCaptioning
-
-processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-model = BlipForConditionalGeneration.from_pretrained("Salesfoce/blip-image-captioning-base")
+processor = BlipProcessor.from_pretrained("ybelkada/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("ybelkada/blip-image-captioning-base")
 
 img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
 raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
@@ -46,13 +47,15 @@ text = "a photography of"
 inputs = processor(raw_image, text, return_tensors="pt")
 
 out = model.generate(**inputs)
-print(processor.decode(out[0], skip_special_tokens=True)
+print(processor.decode(out[0], skip_special_tokens=True))
+# >>> a photography of a woman and her dog
 
 # unconditional image captioning
 inputs = processor(raw_image, return_tensors="pt")
 
 out = model.generate(**inputs)
-print(processor.decode(out[0], skip_special_tokens=True)
+print(processor.decode(out[0], skip_special_tokens=True))
+>>> a woman sitting on the beach with her dog
 ```
 </details>
 
@@ -64,11 +67,12 @@ print(processor.decode(out[0], skip_special_tokens=True)
 <summary> Click to expand </summary>
 
 ```python
-
-from transformers import BlipProcessor, BlipForImageCaptioning
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
 
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
-model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to("cuda")
+model = BlipForConditionalGeneration.from_pretrained("Salesfoce/blip-image-captioning-base").to("cuda")
 
 img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 
 raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')
@@ -78,13 +82,15 @@ text = "a photography of"
 inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
 
 out = model.generate(**inputs)
-print(processor.decode(out[0], skip_special_tokens=True)
+print(processor.decode(out[0], skip_special_tokens=True))
+# >>> a photography of a woman and her dog
 
 # unconditional image captioning
 inputs = processor(raw_image, return_tensors="pt").to("cuda")
 
 out = model.generate(**inputs)
-print(processor.decode(out[0], skip_special_tokens=True)
+print(processor.decode(out[0], skip_special_tokens=True))
+>>> a woman sitting on the beach with her dog
 ```
 </details>
 
@@ -95,7 +101,9 @@ print(processor.decode(out[0], skip_special_tokens=True)
 
 ```python
 import torch
-from transformers import BlipProcessor, BlipForImageCaptioning
+import requests
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
 
 processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
 model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to("cuda")
@@ -108,13 +116,15 @@ text = "a photography of"
 inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
 
 out = model.generate(**inputs)
-print(processor.decode(out[0], skip_special_tokens=True)
+print(processor.decode(out[0], skip_special_tokens=True))
+# >>> a photography of a woman and her dog
 
 # unconditional image captioning
 inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
 
 out = model.generate(**inputs)
-print(processor.decode(out[0], skip_special_tokens=True)
+print(processor.decode(out[0], skip_special_tokens=True))
+>>> a woman sitting on the beach with her dog
 ```
 </details>