michelecafagna26/clipcap-base-captioning-ft-hl-rationales

pip install git+https://github.com/michelecafagna26/CLIPCap.git

git lfs install # if not installed
git clone https://huggingface.co/michelecafagna26/clipcap-base-captioning-ft-hl-rationales

from clipcap import ClipCaptionModel
from transformers import (
    GPT2Tokenizer,
    GPT2LMHeadModel,
)
import torch
import clip
import requests
from PIL import Image

model_path = "clipcap-base-captioning-ft-hl-rationales/pytorch_model.pt" # change accordingly

# load clip
device = "cuda" if torch.cuda.is_available() else "cpu"
clip_model, preprocess = clip.load("ViT-B/32", device=device, jit=False)
tokenizer = GPT2Tokenizer.from_pretrained("gpt2")
prefix_length = 10

# load ClipCap
model = ClipCaptionModel(prefix_length, tokenizer=tokenizer)
model.from_pretrained(model_path)
model = model.eval()
model = model.to(device)

# load the image
img_url = 'https://datasets-server.huggingface.co/assets/michelecafagna26/hl/--/default/train/0/image/image.jpg'
raw_image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')


# extract the prefix
image = preprocess(raw_image).unsqueeze(0).to(device)
with torch.no_grad():
    prefix = clip_model.encode_image(image).to(
        device, dtype=torch.float32
    )
    prefix_embed = model.clip_project(prefix).reshape(1, prefix_length, -1)

# generate the caption   
model.generate_beam(embed=prefix_embed)[0]


# >> "she is posing for a photo."

@inproceedings{cafagna2023hl,
  title={{HL} {D}ataset: {V}isually-grounded {D}escription of {S}cenes, {A}ctions and
{R}ationales},
  author={Cafagna, Michele and van Deemter, Kees and Gatt, Albert},
  booktitle={Proceedings of the 16th International Natural Language Generation Conference (INLG'23)},
address = {Prague, Czech Republic},
  year={2023}
}