finetuned model + more instructions

app.py

@@ -3,6 +3,7 @@ from datasets import load_dataset
 import torch
 from torchvision import transforms, models
 from PIL import Image
+from transformers import pipeline
 import numpy as np
 import random
 
@@ -14,12 +15,11 @@ dataset = load_dataset("gymprathap/Breast-Cancer-Ultrasound-Images-Dataset", spl
 # Map numeric labels to readable classes
 label_names = dataset.features["label"].names  # ['benign', 'malignant', 'normal']
 
-# ---- 2. Define model (mock pretrained or real CNN) ----
-# For MVP, load a pretrained ResNet18 and adapt its head
-model = models.resnet18(pretrained=True)
-model.fc = torch.nn.Linear(model.fc.in_features, len(label_names))
-# For demo purposes, we’ll use random weights (no fine-tuning)
-model.eval()
+# ---- 2. Define model (pretrained or real CNN) ----
+clf = pipeline(
+    "image-classification",
+    model="hugging-science/sample-breast-cancer-classification"
+)
 
 # Transform for inference
 transform = transforms.Compose([
@@ -32,38 +32,37 @@ transform = transforms.Compose([
 
 # ---- 3. Utility: get image + run prediction ----
 def predict_from_sample(sample_idx):
-    """Return image, prediction info, and true label."""
     row = dataset[int(sample_idx)]
     image = row["image"]
     true_label_idx = row["label"]
     true_label = label_names[true_label_idx]
 
-    image_t = transform(image).unsqueeze(0)
-
-    with torch.no_grad():
-        logits = model(image_t)
-        probs = torch.nn.functional.softmax(logits, dim=1).numpy().flatten()
-        pred_idx = int(np.argmax(probs))
-        pred_label = label_names[pred_idx]
-        conf = probs[pred_idx]
-
-    # Build output caption
-    if pred_label == true_label:
-        status = "✅ **Correct**"
-    else:
-        status = "❌ **Incorrect**"
-
+    # Run Hugging Face pipeline
+    preds = clf(image.convert("RGB"))
+    pred_label = preds[0]["label"]
+    conf = preds[0]["score"]
+
+    label_map = {
+        "LABEL_0": "benign",
+        "LABEL_1": "malignant",
+        "LABEL_2": "normal"
+    }
+    pred_label_raw = preds[0]["label"]
+    pred_label = label_map.get(pred_label_raw, pred_label_raw)  # fallback to raw if missing
+    conf = preds[0]["score"]
+
+    # Format output
+    correct = (pred_label.lower() == true_label.lower())
     caption = (
-        f"**Predicted:** {pred_label}  (confidence: {conf:.2f})  \n"
+        f"**Predicted:** {pred_label} (confidence: {conf:.2f})  \n"
         f"**True Label:** {true_label}  \n"
-        f"{status}"
+        f"{'✅ Correct' if correct else '❌ Incorrect'}"
     )
 
-    return image, caption
-
+    return image.convert("RGB"), caption
 
 # ---- 4. Build Gradio UI ----
-N_SAMPLES = 10  # number of random samples to show
+N_SAMPLES = 30  # number of random samples to show
 total = len(dataset)
 random_indices = random.sample(range(total), N_SAMPLES)
 
@@ -76,7 +75,16 @@ with gr.Blocks(title="Women's Longevity Hack") as demo:
     with gr.Tabs():
         with gr.Tab("Getting Started"):
             gr.Markdown(
-                "## Getting Started\n"
+                """## Getting Started
+                
+                Welcome to the Women's Longevity Hack demo! This app showcases a simple image classification model trained to identify breast cancer from ultrasound images. It also provides resources for exploring related datasets.
+
+                To build something like this yourself, check out the files in this repo:
+                - `train.py`: Code to fine-tune a Hugging Face vision model (e.g., ViT) on breast ultrasound images.
+                - `app.py`: Code for this Gradio app, which loads the model and dataset, and provides an interactive demo.
+
+                Don't be afraid to modify and experiment with the code! Or, ask ChatGPT to help you customize it for your own use case. If a generative model gives you something that doesn't work (especially if a flag is not recognized), I recommend telling the model you think it's hallucinating and checking its suggestions against the most recent documentation.
+                """
             )
 
         with gr.Tab("More Datasets"):
@@ -84,6 +92,9 @@ with gr.Blocks(title="Women's Longevity Hack") as demo:
                 """
                 ## 📚 Dataset Inspiration
 
+
+                If you want to explore other potentially interesting datasets, please check these out:
+
                 | Dataset | Modalities / Type | Description & Use Cases |
                 |---|---|---|
                 | [gymprathap/Breast-Cancer-Ultrasound-Images-Dataset](https://huggingface.co/datasets/gymprathap/Breast-Cancer-Ultrasound-Images-Dataset) | Images (ultrasound) + labels | Ultrasound images labeled as benign / malignant / normal. Useful for image classification, explainability (e.g., Grad-CAM), or multimodal fusion if metadata available. |
@@ -93,6 +104,8 @@ with gr.Blocks(title="Women's Longevity Hack") as demo:
                 | [BoneMet/BoneMet](https://huggingface.co/datasets/BoneMet/BoneMet) | Biomedical / genomic / imaging | Dataset focused on bone-metastasis research; can support multimodal modeling combining clinical, imaging, and molecular data. |
                 | [AIBIC/MLOmics](https://huggingface.co/datasets/AIBIC/MLOmics) | Multi-omics / biomedical | Multi-omics resource (genomic, transcriptomic, proteomic) for biomedical discovery and precision-health modeling. |
 
+                
+                If none of these is quite what you're looking for, you can also explore the [Datasets Semantic Search](https://huggingface.co/spaces/librarian-bots/huggingface-semantic-search) to find something more your speed.
                 """
             )
 
@@ -118,7 +131,6 @@ with gr.Blocks(title="Women's Longevity Hack") as demo:
             gr.Markdown(
                 "Dataset: [gymprathap/Breast-Cancer-Ultrasound-Images-Dataset]"
                 "(https://huggingface.co/datasets/gymprathap/Breast-Cancer-Ultrasound-Images-Dataset)\n"
-                "Note: Model weights here are for demonstration only."
             )
 
 # ---- 5. Launch app ----