Spaces:
Runtime error
Runtime error
| import os | |
| os.system('pip install git+https://github.com/huggingface/transformers --upgrade') | |
| import gradio as gr | |
| from transformers import ImageGPTFeatureExtractor, ImageGPTForCausalLM | |
| import torch | |
| import requests | |
| from PIL import Image | |
| import os | |
| import matplotlib.pyplot as plt | |
| feature_extractor = ImageGPTFeatureExtractor.from_pretrained("openai/imagegpt-small") | |
| model = ImageGPTForCausalLM.from_pretrained("openai/imagegpt-small") | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| model.to(device) | |
| # load image examples | |
| urls = ['https://assetsnffrgf-a.akamaihd.net/assets/m/502013285/univ/art/502013285_univ_sqr_xl.jpg'] | |
| for idx, url in enumerate(urls): | |
| image = Image.open(requests.get(url, stream=True).raw) | |
| image.save(f"image_{idx}.png") | |
| def process_image(image): | |
| # prepare 8 images, shape (8, 1024) | |
| encoding = feature_extractor([image for _ in range(8)], return_tensors="pt") | |
| # create primers | |
| samples = encoding.pixel_values.numpy() | |
| n_px = feature_extractor.size | |
| clusters = feature_extractor.clusters | |
| n_px_crop = 16 | |
| primers = samples.reshape(-1,n_px*n_px)[:,:n_px_crop*n_px] # crop top n_px_crop rows. These will be the conditioning tokens | |
| # generate (no beam search) | |
| context = np.concatenate((np.full((batch_size, 1), model.config.vocab_size - 1), primers), axis=1) | |
| context = torch.tensor(context).to(device) | |
| output = model.generate(input_ids=context, max_length=n_px*n_px + 1, temperature=1.0, do_sample=True, top_k=40) | |
| # decode back to images | |
| samples = output[:,1:].cpu().detach().numpy() | |
| samples_img = [np.reshape(np.rint(127.5 * (clusters[s] + 1.0)), [n_px, n_px, 3]).astype(np.uint8) for s in samples] # convert color cluster tokens back to pixels | |
| # save as list of files | |
| completions = [] | |
| output_dir = '.' | |
| for i in range(len(samples_img)): | |
| fname = os.path.join(output_dir, "completion" + str(i) + ".png") | |
| plt.imsave(fname=fname, arr=samples_img[i], format='png') | |
| completions.append(fname) | |
| return completions | |
| title = "Interactive demo: ImageGPT" | |
| description = "Demo for OpenAI's ImageGPT: Generative Pretraining from Pixels. To use it, simply upload an image or use the example image below and click 'submit'. Results will show up in a few seconds." | |
| article = "<p style='text-align: center'><a href='https://arxiv.org/abs/2109.10282'>ImageGPT: Generative Pretraining from Pixels</a> | <a href='https://openai.com/blog/image-gpt/'>Official blog</a></p>" | |
| examples =[["image_0.png"]] | |
| iface = gr.Interface(fn=process_image, | |
| inputs=gr.inputs.Image(type="pil"), | |
| outputs=[gr.outputs.Image(type='file', label=f'completion_{i}') for i in range(8)], | |
| title=title, | |
| description=description, | |
| article=article, | |
| examples=examples, | |
| enable_queue=True) | |
| iface.launch(debug=True) |