Update README.md

README.md

@@ -5,23 +5,81 @@ base_model: google/vit-large-patch16-224
 
 ## LoRA Image Binary Classification LoRA adapter
 
-Model: google/vit-large-patch16-224
+Trained on APTOS 2019 Kaggle competition for identifying diabetic retinopathy. In this case I've modified the problem
+to binary classifier (diagnosis=0 vs. all others; 50-50% distribution in training data)
 
-Dataset: https://www.kaggle.com/c/aptos2019-blindness-detection - fundus images of the back of the eye, and diabetic retinopathy score
+Base Model: [google/vit-large-patch16-224](https://huggingface.co/google/vit-large-patch16-224)
 
-Source docs: https://huggingface.co/docs/peft/task_guides/image_classification_lora
+Dataset: https://www.kaggle.com/c/aptos2019-blindness-detection - fundus images of the back of the eye, and diabetic retinopathy score
 
 Training notebook: https://colab.research.google.com/drive/1TVsUyyou87E26Sz40CdBH3CzWoVckgtq?usp=sharing
 
-Adapted to binary classifier (diagnosis=0 vs. all others; 50-50% distribution in training data)
-
 On 10% held-out of training data: accuracy 98%
 
 - PEFT 0.5.0
 
+PEFT Image classifier inference / [Gradio app](https://huggingface.co/spaces/monsoon-nlp/eyegazer-demo/blob/main/app.py)
+
+```python
+from peft import PeftModel
+from PIL import Image
+from transformers import AutoImageProcessor, AutoModelForImageClassification
+
+from torchvision.transforms import (
+    CenterCrop,
+    Compose,
+    Normalize,
+    RandomHorizontalFlip,
+    RandomResizedCrop,
+    Resize,
+    ToTensor,
+)
+
+model_name = 'google/vit-large-patch16-224'
+adapter = 'monsoon-nlp/eyegazer-vit-binary'
+
+image_processor = AutoImageProcessor.from_pretrained(model_name)
+
+normalize = Normalize(mean=image_processor.image_mean, std=image_processor.image_std)
+train_transforms = Compose(
+    [
+        RandomResizedCrop(image_processor.size["height"]),
+        RandomHorizontalFlip(),
+        ToTensor(),
+        normalize,
+    ]
+)
+
+val_transforms = Compose(
+    [
+        Resize(image_processor.size["height"]),
+        CenterCrop(image_processor.size["height"]),
+        ToTensor(),
+        normalize,
+    ]
+)
+
+model = AutoModelForImageClassification.from_pretrained(
+    model_name,
+    ignore_mismatched_sizes=True,
+    num_labels=2,
+)
+
+lora_model = PeftModel.from_pretrained(model, adapter)
+
+img = Image.open("sample.png")
+pimg = val_transforms(img.convert("RGB"))
+batch = pimg.unsqueeze(0)
+op = lora_model(batch)
+vals = op.logits.tolist()[0]
+
+if vals[0] > vals[1]:
+    return "Predicted unaffected"
+else:
+    return "Predicted affected to some degree"
+```
 
 ## Future goals
 
 - More documentation
-- Modify loss for regression on 0-4 score
-- Script and Gradio to use raw images
+- Modify loss for regression on 0-4 score