Update README.md

README.md

@@ -1,14 +1,19 @@
 # Project Structure
 Out-of-distribution with language supervision
 
-`play_with_clip.py` is the main file. Currently we have three options: 
+- `play_with_clip.py`: ID zero-shot classification and ID fine-tuning (with img encoder). Currently we have three options: 
 
 1) evaluate zero shot performance of CLIP: call `zero_shot_evaluation_CLIP(image_dataset_name, test_labels, ckpt)`
 
 2) fine-tune CLIP image encoder and test (linear probe): call `linear_probe_evaluation_CLIP(image_dataset_name)`
 
 3) play with SkImages: call `play_with_skimage()`
 
+
+- `eval_ood_detection.py`: OOD detection for CIFAR-10, CIFAR-100, and ImageNet-1K as ID. Currently we support only one score (MIS, maximum inner product score). 
+
+- `play_with_clip.ipynb`: contains various visualization methods for trained CLIP model.
+
 # Week2 Record 
 New dataset from ImageNet: 
 - 10 Classes from ImageNet-1k