SohanAnisetty/ofa-vqa-base

OFA-Base

Introduction

This is the base version of OFA pretrained model finetuned on CLEVR and a custom block stack dataset.

The directory includes 4 files, namely config.json which consists of model configuration, vocab.json and merge.txt for our OFA tokenizer, and lastly pytorch_model.bin which consists of model weights.

How to use

Download the models as shown below.

git clone https://github.com/sohananisetty/OFA_VQA.git
git clone https://huggingface.co/SohanAnisetty/ofa-vqa-base

After, refer the path to ofa-vqa-base to ckpt_dir, and prepare an image for the testing example below.

from PIL import Image
from torchvision import transforms
from transformers import OFATokenizer, OFAModelForVQA

mean, std = [0.5, 0.5, 0.5], [0.5, 0.5, 0.5]
resolution = 480
patch_resize_transform = transforms.Compose([
        lambda image: image.convert("RGB"),
        transforms.Resize((resolution, resolution), interpolation=Image.BICUBIC),
        transforms.ToTensor(), 
        transforms.Normalize(mean=mean, std=std)
    ])


tokenizer = OFATokenizer.from_pretrained(ckpt_dir)

txt = " what does the image describe?"
inputs = tokenizer([txt], return_tensors="pt").input_ids
inputs = inputs.cuda()
img = Image.open(path_to_image)
patch_img = patch_resize_transform(img).unsqueeze(0).cuda()


model = OFAModel.from_pretrained(ckpt_dir, use_cache=False).cuda()
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))