Add files using upload-large-folder tool

README.md

@@ -10,6 +10,8 @@ tags:
   - remote-sensing
 ---
 
+> [!WARNING] we do not have a full checkpoint conversion validation, if you encounter pipeline loading failure and unsidered output, please contact me via bili_sakura@zju.edu.cn
+
 # CUT-OpenEarthMap-SAR
 
 CUT (Contrastive Unpaired Translation) models for SAR ↔ optical image translation. Trained on OpenEarthMap data with anti-aliased ResNet generators.
@@ -27,17 +29,22 @@ CUT (Contrastive Unpaired Translation) models for SAR ↔ optical image translat
 
 ## Usage
 
-Use with [pytorch-image-translation-models](https://github.com/Bili-Sakura/pytorch-image-translation-models):
+Use with [pytorch-image-translation-models](https://github.com/Bili-Sakura/pytorch-image-translation-models) and the `openearthmap_sar` community pipeline:
 
 ```python
+from PIL import Image
+
 from examples.community.openearthmap_sar import load_openearthmap_sar_pipeline
 
 pipeline = load_openearthmap_sar_pipeline(
-    checkpoint_dir="BiliSakura/CUT-OpenEarthMap-SAR",  # or local path
-    model_name="sar2opt",
+    checkpoint_dir="/path/to/CUT-OpenEarthMap-SAR",
+    model_name="sar2opt",  # choose one: opt2sar, sar2opt, seman2opt, seman2opt_pesudo, seman2sar, seman2sar_pesudo
     device="cuda",
 )
-output = pipeline(source_image=pil_image, output_type="pil")
+
+source = Image.open("/path/to/sar.png").convert("RGB")
+output = pipeline(source_image=source, output_type="pil")
+output.images[0].save("cut_sar2opt.png")
 ```
 
 **CLI:**