{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "import numpy as np\n",
    "from matplotlib import pyplot as plt\n",
    "\n",
    "# Load the .h5 model\n",
    "model = tf.keras.models.load_model('modelo_entrenado.h5')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [],
   "source": [
    "imagen = tf.keras.preprocessing.image.load_img('imprueba.jpg')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {},
   "outputs": [],
   "source": [
    "def split_image(uploaded_file):  \n",
    "    \n",
    "    # Convert the image to a numpy array\n",
    "    img_array = tf.keras.preprocessing.image.img_to_array(uploaded_file)\n",
    "    print(img_array.shape)\n",
    "    # Split the image into four equal parts\n",
    "    height, width, _ = img_array.shape\n",
    "    split_width = width // 2\n",
    "    split_height = height // 2\n",
    "    top_left = img_array[0:split_height, 0:split_width, :]\n",
    "    top_right = img_array[0:split_height, split_width:width, :]\n",
    "    bottom_left = img_array[split_height:height, 0:split_width, :]\n",
    "    bottom_right = img_array[split_height:height, split_width:width, :]\n",
    "    \n",
    "    return top_left, top_right, bottom_left, bottom_right"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Create a function that accepts an image file and returns the classification predictions\n",
    "def classify_image(image_file):\n",
    "\n",
    "    img_resized = tf.image.resize(image_file, (255, 255))\n",
    "    \n",
    "    x = np.expand_dims(img_resized, axis=0)\n",
    "    \n",
    "\n",
    "    print(x.shape)\n",
    "\n",
    "    prediction = model.predict(x)\n",
    "    predicted_class = np.argmax(prediction)\n",
    "    return predicted_class"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 72,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1200, 1600, 3)\n"
     ]
    }
   ],
   "source": [
    "lista_images = split_image(imagen)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 81,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(1, 255, 255, 3)\n"
     ]
    }
   ],
   "source": [
    "label = classify_image(lista_images[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 82,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "2"
      ]
     },
     "execution_count": 82,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "label"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "ml",
   "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": "3.9.12"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}