Buckets:
| Setting up [LPIPS] perceptual loss: trunk [alex], v[0.1], spatial [off] | |
| /usr/local/lib/python3.11/dist-packages/torchvision/models/_utils.py:208: UserWarning: The parameter 'pretrained' is deprecated since 0.13 and may be removed in the future, please use 'weights' instead. | |
| warnings.warn( | |
| /usr/local/lib/python3.11/dist-packages/torchvision/models/_utils.py:223: UserWarning: Arguments other than a weight enum or `None` for 'weights' are deprecated since 0.13 and may be removed in the future. The current behavior is equivalent to passing `weights=AlexNet_Weights.IMAGENET1K_V1`. You can also use `weights=AlexNet_Weights.DEFAULT` to get the most up-to-date weights. | |
| warnings.warn(msg) | |
| Loading model from: /usr/local/lib/python3.11/dist-packages/lpips/weights/v0.1/alex.pth | |
| /usr/local/lib/python3.11/dist-packages/open_clip/factory.py:450: UserWarning: QuickGELU mismatch between final model config (quick_gelu=False) and pretrained tag 'openai' (quick_gelu=True). | |
| warnings.warn( | |
| W0613 19:28:57.813000 28952 torch/utils/_pytree.py:630] <enum 'KernelPreference'> is an Enum subclass and is now natively supported by torch.compile as an opaque value type. Calling register_constant() on Enum subclasses is deprecated and will be an error in a future release. | |
| W0613 19:28:57.836000 28952 torch/utils/_pytree.py:630] <enum 'ScaleCalculationMode'> is an Enum subclass and is now natively supported by torch.compile as an opaque value type. Calling register_constant() on Enum subclasses is deprecated and will be an error in a future release. | |
| Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. | |
| WARNING:huggingface_hub.utils._http:Warning: You are sending unauthenticated requests to the HF Hub. Please set a HF_TOKEN to enable higher rate limits and faster downloads. | |
| Loading weights: 0%| | 0/910 [00:00<?, ?it/s] Loading weights: 82%|████████▏ | 747/910 [00:00<00:00, 7468.23it/s] Loading weights: 100%|██████████| 910/910 [00:00<00:00, 7541.25it/s] | |
| --- teacher (64 imgs) --- | |
| {'PickScore': 21.7849, 'CLIP': 31.1447, 'LPIPS': None, 'PSNR': None, 'FID_vs_real': np.float64(219.406), 'FID_vs_teacher': None} | |
| --- pilot_ours128_real (64 imgs) --- | |
| {'PickScore': 21.8082, 'CLIP': 31.1317, 'LPIPS': 0.1688, 'PSNR': 18.9134, 'FID_vs_real': np.float64(217.655), 'FID_vs_teacher': np.float64(52.606)} | |
| --- pilot_fq128 (64 imgs) --- | |
| {'PickScore': 21.7575, 'CLIP': 31.3089, 'LPIPS': 0.1702, 'PSNR': 18.9429, 'FID_vs_real': np.float64(217.17), 'FID_vs_teacher': np.float64(54.883)} | |
| --- pilot_fq0 (64 imgs) --- | |
| {'PickScore': 21.7593, 'CLIP': 31.1597, 'LPIPS': 0.2095, 'PSNR': 17.835, 'FID_vs_real': np.float64(216.649), 'FID_vs_teacher': np.float64(65.268)} | |
| === SUMMARY (outputs/eval/metrics.json) === | |
| model PickScore↑ CLIP↑ LPIPS↓ PSNR↑ FIDreal↓ FIDteach↓ | |
| teacher 21.7849 31.1447 None None 219.406 None | |
| pilot_ours128_real 21.8082 31.1317 0.1688 18.9134 217.655 52.606 | |
| pilot_fq128 21.7575 31.3089 0.1702 18.9429 217.17 54.883 | |
| pilot_fq0 21.7593 31.1597 0.2095 17.835 216.649 65.268 | |
Xet Storage Details
- Size:
- 3.28 kB
- Xet hash:
- 5125d8d0381664c7ea2b959a910d13578127ea1ffd6d463e8f6d05be9ad28003
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.