Upgrade to Keras 3.0 with JAX backend and direct HF model loading

- Set KERAS_BACKEND to 'jax' for improved performance
- Use keras.saving.load_model('hf://Siraja704/DermaAI') for direct model loading
- Remove dependency on huggingface_hub package
- Add jax[cpu] to requirements for JAX backend support
- Update README with modern technical stack information
- Simplify model loading process with new Keras 3.0 features

README.md

@@ -15,10 +15,25 @@ short_description: Derma AI skin Disease model
 
 AI-powered skin condition analysis using deep learning with EfficientNetV2 architecture.
 
+## Features
+
+- **Modern Keras 3.0 with JAX Backend**: Uses the latest Keras with JAX for improved performance
+- **Direct HuggingFace Model Loading**: Loads models directly from HuggingFace Hub
+- **5 Skin Conditions**: Classifies Atopic Dermatitis, Eczema, Psoriasis, Seborrheic Keratoses, and Tinea Ringworm Candidiasis
+- **Medical Disclaimers**: Includes proper medical disclaimers and advice
+
+## Technical Stack
+
+- **Backend**: JAX (via Keras 3.0)
+- **Frontend**: Gradio 5.0+
+- **Model Architecture**: EfficientNetV2
+- **Model Source**: Direct loading from `hf://Siraja704/DermaAI`
+
 ## Setup
 
-This Space requires authentication to access the private model. To run this Space:
+This application uses Keras 3.0 with JAX backend for optimal performance. The model is loaded directly from HuggingFace Hub using the new `keras.saving.load_model("hf://...")` syntax.
 
+If the model repository is private, you may need to:
 1. Go to the Space settings
 2. Add a new secret with key `HF_TOKEN` and your Hugging Face access token as the value
 3. Make sure your token has access to the `Siraja704/DermaAI` model repository

app.py

@@ -1,10 +1,13 @@
+# Available backend options are: "jax", "torch", "tensorflow".
+import os
+os.environ["KERAS_BACKEND"] = "jax"
+
 import gradio as gr
-import tensorflow as tf
+import keras
 import numpy as np
 from PIL import Image
-from huggingface_hub import hf_hub_download
+import tensorflow as tf  # Keep for preprocessing function
 from tensorflow.keras.applications.efficientnet_v2 import preprocess_input
-import os
 
 # Class names for the 5 skin conditions
 CLASS_NAMES = [
@@ -30,17 +33,11 @@ class DermaAIModel:
         self.load_model()
     
     def load_model(self):
-        """Load the DermaAI model from Hugging Face Hub"""
+        """Load the DermaAI model from Hugging Face Hub using Keras 3.0"""
         try:
             print("🔄 Loading DermaAI model from Hugging Face...")
-            # Get HF token from environment variable for authentication
-            hf_token = os.getenv("HF_TOKEN")
-            model_path = hf_hub_download(
-                repo_id="Siraja704/DermaAI", 
-                filename="DermaAI.keras",
-                token=hf_token
-            )
-            self.model = tf.keras.models.load_model(model_path)
+            # Load model directly from Hugging Face using Keras 3.0
+            self.model = keras.saving.load_model("hf://Siraja704/DermaAI")
             print("✅ Model loaded successfully!")
         except Exception as e:
             error_msg = str(e)

requirements.txt

@@ -1,5 +1,6 @@
 gradio>=5.0.0
+keras>=3.0.0
+jax[cpu]>=0.4.0
 tensorflow>=2.13.0
-huggingface_hub>=0.20.0
 pillow>=9.0.0
 numpy>=1.21.0