| import marimo |
|
|
| __generated_with = "0.17.0" |
| app = marimo.App() |
|
|
|
|
| @app.cell |
| def _(): |
| from open_clip import create_model_from_pretrained |
| import torch |
| from transformers import CLIPImageProcessor, AutoImageProcessor |
| from urllib.request import urlopen |
| from PIL import Image |
| return ( |
| AutoImageProcessor, |
| CLIPImageProcessor, |
| Image, |
| create_model_from_pretrained, |
| torch, |
| urlopen, |
| ) |
|
|
|
|
| @app.cell |
| def _(Image, urlopen): |
| image = Image.open(urlopen( |
| |
| 'https://media.gettyimages.com/id/1309385864/photo/las-vegas-strip-skyline-landscaped-ultra-wide-shot-at-night.jpg?s=1024x1024&w=gi&k=20&c=bBxkjq8FoK2bPKYLtqbJMCgpsvjUm-vI7-yw04cq7AU=' |
| )) |
| image.size |
| return (image,) |
|
|
|
|
| @app.cell |
| def _(): |
| model = "apple/DFN5B-CLIP-ViT-H-14" |
| return (model,) |
|
|
|
|
| @app.cell |
| def _( |
| AutoImageProcessor, |
| CLIPImageProcessor, |
| create_model_from_pretrained, |
| model, |
| ): |
| try: |
| hf_pre = AutoImageProcessor.from_pretrained(model) |
| except: |
| print("Auto image processor not found") |
| hf_pre = CLIPImageProcessor() |
| hf_pre_fix = CLIPImageProcessor( |
| do_center_crop=False, |
| do_normalize=True, |
| do_resize=True, |
| feature_extractor_type="CLIPFeatureExtractor", |
| image_mean=[ |
| 0.48145466, |
| 0.4578275, |
| 0.40821073 |
| ], |
| image_std=[ |
| 0.26862954, |
| 0.26130258, |
| 0.27577711 |
| ], |
| size={"width": 224, "height": 224}, |
| do_convert_rgb=True |
| ) |
| _, preprocess = create_model_from_pretrained(f'hf-hub:{model}') |
| preprocess |
| return hf_pre, hf_pre_fix, preprocess |
|
|
|
|
| @app.cell |
| def _(hf_pre, hf_pre_fix, image, preprocess, torch): |
| hf_res_fix = torch.tensor(hf_pre_fix(images=image)["pixel_values"]).squeeze() |
| hf_res = torch.tensor(hf_pre(images=image)["pixel_values"]).squeeze() |
| op_res = preprocess(image) |
| op_res.shape, hf_res.shape |
| return hf_res, hf_res_fix, op_res |
|
|
|
|
| @app.cell |
| def _(hf_res, op_res): |
| (hf_res == op_res).all() |
| return |
|
|
|
|
| @app.cell |
| def _(hf_res_fix, op_res): |
| (hf_res_fix == op_res).all() |
| return |
|
|
|
|
| @app.cell |
| def _(hf_res, hf_res_fix, image, op_res): |
| |
| import matplotlib.pyplot as plt |
| fig, axs = plt.subplots(1, 4, figsize=(15, 5)) |
| axs[0].imshow(image) |
| axs[0].set_title("Original Image") |
| axs[1].imshow(op_res.permute(1, 2, 0).numpy()) |
| axs[1].set_title("OpenCLIP Preprocessed Image") |
| axs[2].imshow(hf_res.permute(1, 2, 0).numpy()) |
| axs[2].set_title("HuggingFace Preprocessed Image") |
| axs[3].imshow(hf_res_fix.permute(1, 2, 0).numpy()) |
| axs[3].set_title("HuggingFace FIXED Preprocessed Image") |
| plt.show() |
| return |
|
|
|
|
| @app.cell |
| def _(hf_pre_fix): |
| hf_pre_fix.to_json_file("test.json") |
| return |
|
|
|
|
| @app.cell |
| def _(): |
| return |
|
|
|
|
| if __name__ == "__main__": |
| app.run() |
|
|
