Upload README.md with huggingface_hub

README.md

@@ -1,3 +1,52 @@
+---
+language: "en"
+license: "cc-by-4.0"  
+tags:
+  - "vision"
+  - "image-classification"
+  - "cnn"
+  - "satellite-imagery"
+  - "land-use-classification"
+  - "france"
+  - "remote-sensing"
+model-index:
+  - name: "satellite-land-use-classifier-france"
+    results:
+      - task:
+          type: "image-classification"
+        dataset:
+          name: "hadrilec/satellite-pictures-classification-ign-france"
+          type: "image-dataset"
+        metrics:
+          - name: "accuracy"
+            type: "classification"
+            value: 0.9728
+        split: "validation"
+widget:
+  - task: image-classification
+    inputs:
+      - name: "example_input"
+        type: "image"
+        url: "https://huggingface.co/datasets/hadrilec/satellite-pictures-classification-ign-france/viewer/default/train?views%5B%5D=train&image-viewer=9473D066F7CE8EC28648894FD2FDAAF273ED2520"
+model:
+  architecture: "Custom CNN (2-layer Conv + 2-FC)"
+  framework: "PyTorch"
+  input_shape: [3, 256, 256]  
+  output_labels:
+    - "forest"
+    - "sea"
+    - "urban"
+    - "field"
+model_description: |
+  This model uses a custom convolutional neural network, trained on satellite images provided by IGN, to classify areas in France into four categories: forest, sea, urban, and field
+citation:
+  - authors:
+      - "Hadrien Leclerc"
+    title: "Satellite Image Classifier for Land-Use in France"
+    year: 2025
+---
+
+
 # Satellite Image Classifier (Custom CNN)
 
 This repository contains a **custom convolutional neural network (`Net`)** trained on satellite imagery for land classification in France.