Spaces:
Running on Zero
Running on Zero
Download scripts/compare_official_inference.py from Thiru1122/Multimodel_setup: direct link, hf CLI and curl.
- Browser
- Download file 4.84 kB
-
https://huggingface.co/spaces/Thiru1122/Multimodel_setup/resolve/main/scripts/compare_official_inference.py
- Command line
-
hf download hf://spaces/Thiru1122/Multimodel_setup/scripts/compare_official_inference.py
-
curl -L -o compare_official_inference.py https://huggingface.co/spaces/Thiru1122/Multimodel_setup/resolve/main/scripts/compare_official_inference.py
4.84 kB
| import os | |
| import sys | |
| import torch | |
| import torchvision.transforms as transforms | |
| import torchvision.transforms.functional as TF | |
| from PIL import Image | |
| # Add UniversalFakeDetect to path | |
| BASE_DIR = os.path.dirname(os.path.dirname(os.path.abspath(__file__))) | |
| UFD_DIR = os.path.join(BASE_DIR, "UniversalFakeDetect") | |
| if UFD_DIR not in sys.path: | |
| sys.path.insert(0, UFD_DIR) | |
| from models import get_model | |
| # Constants from validate.py | |
| MEAN_CLIP = [0.48145466, 0.4578275, 0.40821073] | |
| STD_CLIP = [0.26862954, 0.26130258, 0.27577711] | |
| # 1. Pipeline A: validate.py (RealFakeDataset in validate.py) | |
| transform_validate_py = transforms.Compose([ | |
| transforms.CenterCrop(224), | |
| transforms.ToTensor(), | |
| transforms.Normalize(mean=MEAN_CLIP, std=STD_CLIP) | |
| ]) | |
| # 2. Pipeline B: datasets.py (data_loader in train.py / val_opt with loadSize=256, cropSize=224) | |
| transform_train_val = transforms.Compose([ | |
| transforms.Resize(256, interpolation=transforms.InterpolationMode.BICUBIC), | |
| transforms.CenterCrop(224), | |
| transforms.ToTensor(), | |
| transforms.Normalize(mean=MEAN_CLIP, std=STD_CLIP) | |
| ]) | |
| def main(): | |
| print("=================================================================") | |
| print("TASK 5: Comparing Official Inference Implementations vs Current App") | |
| print("=================================================================\n") | |
| device = torch.device("cuda" if torch.cuda.is_available() else "cpu") | |
| print(f"Using device: {device}") | |
| # Load Model exactly as official validate.py | |
| print("Loading CLIP:ViT-L/14 model...") | |
| model = get_model("CLIP:ViT-L/14") | |
| ckpt_path = os.path.join(UFD_DIR, "pretrained_weights", "fc_weights.pth") | |
| state_dict = torch.load(ckpt_path, map_location="cpu") | |
| model.fc.load_state_dict(state_dict) | |
| model.eval() | |
| model.to(device) | |
| print(f"Model and weights loaded from {ckpt_path}\n") | |
| # Pipeline C: clip.load's preprocess (used in current app.py) | |
| transform_app_py = model.preprocess | |
| test_images = [ | |
| ("Known real photograph", r"C:\Users\user\.gemini\antigravity-ide\brain\3b54ff09-c09f-4fe6-9276-f4cca9fbc6d7\scratch\real_phone_photo.png", "REAL"), | |
| ("Known AI-generated image", r"C:\Users\user\.gemini\antigravity-ide\brain\3b54ff09-c09f-4fe6-9276-f4cca9fbc6d7\ai_cyberpunk_city_1789660863192.jpg", "FAKE"), | |
| ("Known manipulated image", r"C:\Users\user\.gemini\antigravity-ide\brain\3b54ff09-c09f-4fe6-9276-f4cca9fbc6d7\scratch\manipulated_image.png", "EVALUATE") | |
| ] | |
| pipelines = [ | |
| ("Current app.py (model.preprocess: Resize(224, bicubic) -> CenterCrop(224))", transform_app_py), | |
| ("validate.py (Direct CenterCrop(224) without resizing)", transform_validate_py), | |
| ("train.py/datasets.py (Resize(256, bicubic) -> CenterCrop(224))", transform_train_val) | |
| ] | |
| results = [] | |
| for img_name, img_path, expected_label in test_images: | |
| print(f"-----------------------------------------------------------------") | |
| print(f"Test Image: {img_name}") | |
| print(f"Path: {img_path}") | |
| print(f"Expected / Label: {expected_label}") | |
| with Image.open(img_path) as raw_img: | |
| img_rgb = raw_img.convert("RGB") | |
| print(f"Original size: {img_rgb.size} ({img_rgb.width}x{img_rgb.height})") | |
| for pipe_name, pipe_transform in pipelines: | |
| # Apply transform | |
| tensor = pipe_transform(img_rgb).unsqueeze(0).to(device) | |
| with torch.inference_mode(): | |
| feat = model.model.encode_image(tensor) | |
| logit = model.fc(feat.float()).item() | |
| prob_fake = torch.sigmoid(torch.tensor(logit)).item() | |
| pred_label = "FAKE" if prob_fake >= 0.50 else "REAL" | |
| conf = prob_fake if pred_label == "FAKE" else (1.0 - prob_fake) | |
| print(f" [{pipe_name}]") | |
| print(f" Raw Logit: {logit:+.5f}") | |
| print(f" Fake Prob: {prob_fake:.6f} ({prob_fake*100:.2f}%)") | |
| print(f" Prediction: {pred_label} (Confidence: {conf*100:.2f}%)") | |
| results.append({ | |
| "image": img_name, | |
| "pipeline": pipe_name, | |
| "logit": logit, | |
| "prob_fake": prob_fake, | |
| "prediction": pred_label, | |
| "confidence": conf | |
| }) | |
| print() | |
| print("=================================================================") | |
| print("Summary Analysis:") | |
| print("=================================================================") | |
| for r in results: | |
| print(f"{r['image'][:25]:<25} | {r['pipeline'][:35]:<35} | logit: {r['logit']:+8.4f} | prob: {r['prob_fake']*100:6.2f}% | pred: {r['prediction']}") | |
| if __name__ == "__main__": | |
| main() | |