Instructions to use hf-internal-testing/tiny-random-Swin2SRForImageSuperResolution with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hf-internal-testing/tiny-random-Swin2SRForImageSuperResolution with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("image-to-image", model="hf-internal-testing/tiny-random-Swin2SRForImageSuperResolution")# Load model directly from transformers import AutoImageProcessor, AutoModelForImageToImage processor = AutoImageProcessor.from_pretrained("hf-internal-testing/tiny-random-Swin2SRForImageSuperResolution") model = AutoModelForImageToImage.from_pretrained("hf-internal-testing/tiny-random-Swin2SRForImageSuperResolution") - Notebooks
- Google Colab
- Kaggle
| { | |
| "architectures": [ | |
| "Swin2SRForImageSuperResolution" | |
| ], | |
| "attention_probs_dropout_prob": 0.0, | |
| "depths": [ | |
| 1, | |
| 2, | |
| 1 | |
| ], | |
| "drop_path_rate": 0.1, | |
| "embed_dim": 16, | |
| "hidden_act": "gelu", | |
| "hidden_dropout_prob": 0.0, | |
| "image_size": 32, | |
| "img_range": 1.0, | |
| "initializer_range": 0.02, | |
| "layer_norm_eps": 1e-05, | |
| "mlp_ratio": 2.0, | |
| "model_type": "swin2sr", | |
| "num_channels": 3, | |
| "num_heads": [ | |
| 2, | |
| 2, | |
| 4 | |
| ], | |
| "num_layers": 3, | |
| "patch_size": 1, | |
| "path_norm": true, | |
| "qkv_bias": true, | |
| "resi_connection": "1conv", | |
| "torch_dtype": "float32", | |
| "transformers_version": "4.34.0.dev0", | |
| "upsampler": "pixelshuffle", | |
| "upscale": 2, | |
| "use_absolute_embeddings": false, | |
| "window_size": 2 | |
| } | |