Update README.md

README.md

@@ -1,28 +1,88 @@
----
-title: Satellite Classification Dashboard
-emoji: 🛰️
-colorFrom: blue
-colorTo: purple
-sdk: gradio
-sdk_version: 5.38.0
-app_file: app.py
-pinned: false
----
 
+title: Satellite Classification Dashboardemoji: 🛰️colorFrom: bluecolorTo: purplesdk: gradiosdk_version: 5.0.2app_file: app.pypinned: false
 🛰️ Satellite Classification Dashboard
-
 A Gradio-based application for classifying satellite images using pre-trained deep learning models. Upload a PNG, JPG, or JPEG image, select one or more models (Custom CNN, MobileNetV2, EfficientNetB0, DenseNet121), and view predictions with confidence scores and visualizations.
-
-## Quick Start
+Quick Start
 
 Try the Live Demo: Visit https://huggingface.co/spaces/your-username/Satellite-Classification-Gradio.
-
-### Local Setup
-
-```bash
-git clone https://huggingface.co/spaces/your-username/Satellite-Classification-Gradio
+Local Setup:git clone https://huggingface.co/spaces/your-username/Satellite-Classification-Gradio
 cd Satellite-Classification-Gradio
 python -m venv venv
 source venv/bin/activate  # On Windows: venv\Scripts\activate
 pip install -r requirements.txt
-python app.py
+python app.py
+
+Open http://localhost:7860 in your browser.
+
+Dependencies
+Listed in requirements.txt:
+
+gradio==5.0.2
+tensorflow-cpu==2.15.0
+h5py==3.10.0
+numpy==1.26.4
+pandas==2.2.2
+plotly==5.22.0
+Pillow==10.4.0
+requests==2.32.3
+protobuf==3.20.3
+
+Troubleshooting
+Error loading <model>: Unable to load model. Filepath is not an hdf5 file (or h5py is not available) or SavedModel
+
+Cause: The model file is not a valid HDF5 or SavedModel, or h5py is missing.
+Fix:
+Ensure requirements.txt includes h5py==3.10.0.
+Verify the model URL (e.g., https://huggingface.co/Bhavi23/Custom_CNN/resolve/main/best_multimodal_model.keras) is correct and accessible.
+Download the model file locally and test:wget https://huggingface.co/Bhavi23/Custom_CNN/resolve/main/best_multimodal_model.keras
+python -c "import tensorflow as tf; model = tf.keras.models.load_model('best_multimodal_model.keras')"
+
+
+If the file is invalid, check the Hugging Face repository for the correct file or contact the model owner.
+Alternatively, include model files in the repository:git add models/best_multimodal_model.keras
+git commit -m "Add Custom CNN model file"
+git push
+
+
+Use a Dockerfile for a consistent environment:FROM python:3.9-slim
+WORKDIR /app
+COPY requirements.txt .
+RUN pip install --no-cache-dir -r requirements.txt
+COPY . .
+EXPOSE 7860
+CMD ["python", "app.py"]
+
+
+Restart the Space after changes.
+
+
+
+ModuleNotFoundError: No module named 'tensorflow'
+
+Cause: TensorFlow failed to install.
+Fix:
+Verify requirements.txt includes tensorflow-cpu==2.15.0 and protobuf==3.20.3.
+Check build logs in the Space’s Settings tab.
+Test locally:python -m venv venv
+source venv/bin/activate
+pip install -r requirements.txt
+python app.py
+
+
+Use the above Dockerfile if needed.
+
+
+
+Missing configuration in README
+
+Cause: The README.md lacked the YAML front matter.
+Fix: This file includes the correct YAML header. Ensure it is saved as README.md:git add README.md
+git commit -m "Update README.md"
+git push
+
+
+
+Support
+
+Issues: Hugging Face Discussions
+Email: bhavithrass@gmail.com