Image-to-Image
Transformers
PyTorch
TensorBoard
Spanish
English
conv_swin2sr
climate
super-resolution
Instructions to use predictia/convswin2sr_mediterranean with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use predictia/convswin2sr_mediterranean with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "image-to-image" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("image-to-image", model="predictia/convswin2sr_mediterranean")# pip install -U transformers accelerate # Load model directly from transformers import ConvSwin2SR model = ConvSwin2SR.from_pretrained("predictia/convswin2sr_mediterranean", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -126,7 +126,7 @@ On the other hand, the target high-resolution grid (CERRA) correspond to a 2D ma
|
|
| 126 |
latitude: [44.95, 37]
|
| 127 |
```
|
| 128 |
|
| 129 |
-

|
| 130 |
|
| 131 |
The data samples used for training corresponds to the period from 1985 and 2013 (both included) and from 2014 to 2017 for per-epoch validation.
|
| 132 |
|
|
|
|
| 126 |
latitude: [44.95, 37]
|
| 127 |
```
|
| 128 |
|
| 129 |
+

|
| 130 |
|
| 131 |
The data samples used for training corresponds to the period from 1985 and 2013 (both included) and from 2014 to 2017 for per-epoch validation.
|
| 132 |
|