Salesforce
/
blip-image-captioning-base
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update README.md

This commit is contained in:
Younes Belkada 2022-12-13 11:11:31 +00:00 committed by huggingface-web
parent af1d88b9ac
commit 25d2acb8e5
1 changed files with 24 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
README.md
View File

@ -32,11 +32,12 @@ You can use this model for conditional and un-conditional image captioning
<summary> Click to expand </summary> <summary> Click to expand </summary>
```python ```python
import requests
from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
from transformers import BlipProcessor, BlipForImageCaptioning processor = BlipProcessor.from_pretrained("ybelkada/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("ybelkada/blip-image-captioning-base")
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesfoce/blip-image-captioning-base")
img_url = 'https://storage.googleapis.com/sfr-vision-language-research/BLIP/demo.jpg' 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') 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") inputs = processor(raw_image, text, return_tensors="pt")
out = model.generate(**inputs) 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 # unconditional image captioning
inputs = processor(raw_image, return_tensors="pt") inputs = processor(raw_image, return_tensors="pt")
out = model.generate(**inputs) 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> </details>
@ -64,11 +67,12 @@ print(processor.decode(out[0], skip_special_tokens=True)
<summary> Click to expand </summary> <summary> Click to expand </summary>
```python ```python
import requests
from transformers import BlipProcessor, BlipForImageCaptioning from PIL import Image
from transformers import BlipProcessor, BlipForConditionalGeneration
processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base") 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' 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') 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") inputs = processor(raw_image, text, return_tensors="pt").to("cuda")
out = model.generate(**inputs) 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 # unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda") inputs = processor(raw_image, return_tensors="pt").to("cuda")
out = model.generate(**inputs) 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> </details>
@ -95,7 +101,9 @@ print(processor.decode(out[0], skip_special_tokens=True)
```python ```python
import torch 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") processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base", torch_dtype=torch.float16).to("cuda") 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) inputs = processor(raw_image, text, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs) 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 # unconditional image captioning
inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16) inputs = processor(raw_image, return_tensors="pt").to("cuda", torch.float16)
out = model.generate(**inputs) 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> </details>