{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Running on local URL:  http://127.0.0.1:7881\n",
      "\n",
      "To create a public link, set `share=True` in `launch()`.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div><iframe src=\"http://127.0.0.1:7881/\" width=\"100%\" height=\"500\" allow=\"autoplay; camera; microphone; clipboard-read; clipboard-write;\" frameborder=\"0\" allowfullscreen></iframe></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": []
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import gradio as gr\n",
    "import tensorflow as tf\n",
    "from PIL import Image\n",
    "import numpy as np\n",
    "\n",
    "# Load the model\n",
    "model_path = \"best_model.keras\"\n",
    "model = tf.keras.models.load_model(model_path)\n",
    "\n",
    "# Define labels\n",
    "labels = ['AnnualCrop', 'Forest', 'HerbaceousVegetation', 'Highway', 'Industrial', 'Pasture', 'PermanentCrop', 'Residential', 'River', 'SeaLake']\n",
    "\n",
    "def predict_image(image):\n",
    "    image = Image.fromarray(image.astype('uint8'), 'RGB')\n",
    "    image = image.resize((64, 64)) \n",
    "    image = np.array(image)\n",
    "\n",
    "    prediction = model.predict(np.expand_dims(image, axis=0))\n",
    "    confidences = {labels[i]: float(prediction[0][i]) for i in range(len(labels))}\n",
    "    return confidences\n",
    "\n",
    "# Gradio interface\n",
    "iface = gr.Interface(\n",
    "    fn=predict_image,\n",
    "    inputs=gr.Image(),\n",
    "    outputs=gr.Label(num_top_classes=10),\n",
    "    title=\"Sentinel Image Classifier\",\n",
    "    description=\"Upload a satellite image and the classifier will predict the type of land cover or feature.\",\n",
    "    examples = [\"images/annualcrop.jpg\", \"images/forest.jpg\", \"images/herbaceousvegetation.jpg\", \"images/highway.jpg\", \"images/industrial.jpg\", \"images/pasture.jpg\", \"images/permanentcrop.jpg\", \"images/residential.jpg\", \"images/river.jpg\", \"images/sealake.jpg\"]\n",
    ")\n",
    "# Launch the interface\n",
    "iface.launch(share=False)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 647ms/step\n",
      "[[2.98899226e-06 3.38417292e-02 1.58750382e-08 1.03646407e-08\n",
      "  3.04554437e-10 3.97204403e-08 7.68960629e-09 1.02308356e-10\n",
      "  1.51210475e-06 9.66153681e-01]]\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Min and max values: 0.16862745098039217 1.0\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step\n",
      "Min and max values: 0.1411764705882353 1.0\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step\n",
      "Min and max values: 0.16862745098039217 1.0\n",
      "\u001b[1m1/1\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step\n"
     ]
    }
   ],
   "source": [
    "from PIL import Image\n",
    "import numpy as np\n",
    "import tensorflow as tf\n",
    "\n",
    "# Load the trained model\n",
    "model_path = 'sentinel_classificatiion_model.keras'  # Adjust the path as necessary\n",
    "model = tf.keras.models.load_model(model_path)\n",
    "\n",
    "# Load and process an example image\n",
    "image_path = 'images/forest.jpg'  # Replace with an example image from your dataset\n",
    "image = Image.open(image_path)\n",
    "\n",
    "\n",
    "# Predict using the model\n",
    "prediction = model.predict(np.expand_dims(image, axis=0))  # Add batch dimension\n",
    "print(prediction)\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.14"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}