heuzef
/
jan24_cds_mushrooms

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Found 2199 images belonging to 2 classes.\n",
      "Found 549 images belonging to 2 classes.\n",
      "Training samples: 2199\n",
      "Validation samples: 549\n"
     ]
    }
   ],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n",
    "\n",
    "dataset_dir = 'C:/Users/vsavelev/GITHUB/DS_projet/jan24_cds_mushrooms/data'\n",
    "\n",
    "# Create ImageDataGenerator with validation split\n",
    "datagen = ImageDataGenerator(rescale=1.0/255, validation_split=0.2)\n",
    "\n",
    "train_generator = datagen.flow_from_directory(\n",
    "    dataset_dir,\n",
    "    target_size=(224, 224),\n",
    "    batch_size=32,\n",
    "    class_mode='categorical',\n",
    "    subset='training'  # Set as training data\n",
    ")\n",
    "\n",
    "validation_generator = datagen.flow_from_directory(\n",
    "    dataset_dir,\n",
    "    target_size=(224, 224),\n",
    "    batch_size=32,\n",
    "    class_mode='categorical',\n",
    "    subset='validation'  # Set as validation data\n",
    ")\n",
    "\n",
    "print(f'Training samples: {train_generator.samples}')\n",
    "print(f'Validation samples: {validation_generator.samples}')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from tensorflow.keras.applications import ResNet50\n",
    "from tensorflow.keras import layers, models\n",
    "import keras_tuner as kt\n",
    "\n",
    "def build_model(hp):\n",
    "    base_model = ResNet50(weights='imagenet', include_top=False, input_shape=(224, 224, 3))\n",
    "    base_model.trainable = False\n",
    "\n",
    "    model = models.Sequential()\n",
    "    model.add(base_model)\n",
    "    model.add(layers.GlobalAveragePooling2D())\n",
    "    model.add(layers.Dense(hp.Int('units', min_value=256, max_value=1024, step=256), activation='relu'))\n",
    "    model.add(layers.Dropout(hp.Float('dropout', min_value=0.2, max_value=0.5, step=0.1)))\n",
    "    model.add(layers.Dense(train_generator.num_classes, activation='softmax'))\n",
    "    \n",
    "    model.compile(optimizer=tf.keras.optimizers.Adam(hp.Choice('learning_rate', [1e-2, 1e-3, 1e-4])),\n",
    "                  loss='categorical_crossentropy',\n",
    "                  metrics=['accuracy'])\n",
    "    \n",
    "    return model\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Set Up the Tuner\n",
    "\n",
    "tuner = kt.RandomSearch(\n",
    "    build_model,\n",
    "    objective='val_accuracy',\n",
    "    max_trials=5,\n",
    "    executions_per_trial=3,\n",
    "    directory='my_dir',\n",
    "    project_name='mushroom_classification'\n",
    ")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Trial 5 Complete [05h 32m 33s]\n",
      "val_accuracy: 0.8870673775672913\n",
      "\n",
      "Best val_accuracy So Far: 0.8870673775672913\n",
      "Total elapsed time: 11h 14m 56s\n"
     ]
    }
   ],
   "source": [
    "tuner.search(train_generator, epochs=10, validation_data=validation_generator)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "The hyperparameter search is complete. The optimal number of units in the dense layer is 768.\n",
      "The optimal learning rate for the optimizer is 0.001.\n",
      "\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_1\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"sequential_1\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃<span style=\"font-weight: bold\"> Layer (type)                    </span>┃<span style=\"font-weight: bold\"> Output Shape           </span>┃<span style=\"font-weight: bold\">       Param # </span>┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ resnet50 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Functional</span>)           │ ?                      │    <span style=\"color: #00af00; text-decoration-color: #00af00\">23,587,712</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ global_average_pooling2d_1      │ ?                      │   <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
       "│ (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">GlobalAveragePooling2D</span>)        │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ ?                      │   <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)             │ ?                      │   <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                 │ ?                      │   <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (unbuilt) │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "text/plain": [
       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━┓\n",
       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                   \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape          \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m      Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━┩\n",
       "│ resnet50 (\u001b[38;5;33mFunctional\u001b[0m)           │ ?                      │    \u001b[38;5;34m23,587,712\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ global_average_pooling2d_1      │ ?                      │   \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
       "│ (\u001b[38;5;33mGlobalAveragePooling2D\u001b[0m)        │                        │               │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ ?                      │   \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_1 (\u001b[38;5;33mDropout\u001b[0m)             │ ?                      │   \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_3 (\u001b[38;5;33mDense\u001b[0m)                 │ ?                      │   \u001b[38;5;34m0\u001b[0m (unbuilt) │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">23,587,712</span> (89.98 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m23,587,712\u001b[0m (89.98 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">23,587,712</span> (89.98 MB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m23,587,712\u001b[0m (89.98 MB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "best_hps = tuner.get_best_hyperparameters(num_trials=1)[0]\n",
    "\n",
    "print(f\"\"\"\n",
    "The hyperparameter search is complete. The optimal number of units in the dense layer is {best_hps.get('units')}.\n",
    "The optimal learning rate for the optimizer is {best_hps.get('learning_rate')}.\n",
    "\"\"\")\n",
    "\n",
    "# Build the best model\n",
    "model = tuner.hypermodel.build(best_hps)\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m164s\u001b[0m 2s/step - accuracy: 0.8856 - loss: 0.4458 - val_accuracy: 0.8860 - val_loss: 0.3645\n",
      "Epoch 2/10\n",
      "\u001b[1m 1/68\u001b[0m \u001b[37m━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[1m1:57\u001b[0m 2s/step - accuracy: 0.9062 - loss: 0.3521"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "c:\\Users\\vsavelev\\AppData\\Local\\anaconda3\\Lib\\contextlib.py:158: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.\n",
      "  self.gen.throw(typ, value, traceback)\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 11ms/step - accuracy: 0.9062 - loss: 0.3521 - val_accuracy: 1.0000 - val_loss: 0.0784\n",
      "Epoch 3/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m153s\u001b[0m 2s/step - accuracy: 0.8923 - loss: 0.3465 - val_accuracy: 0.8879 - val_loss: 0.3535\n",
      "Epoch 4/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 6ms/step - accuracy: 0.8750 - loss: 0.4432 - val_accuracy: 0.8000 - val_loss: 0.5806\n",
      "Epoch 5/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m151s\u001b[0m 2s/step - accuracy: 0.8817 - loss: 0.3742 - val_accuracy: 0.8860 - val_loss: 0.3608\n",
      "Epoch 6/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 8ms/step - accuracy: 0.9375 - loss: 0.2319 - val_accuracy: 1.0000 - val_loss: 0.0935\n",
      "Epoch 7/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m156s\u001b[0m 2s/step - accuracy: 0.8882 - loss: 0.3576 - val_accuracy: 0.8860 - val_loss: 0.3543\n",
      "Epoch 8/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 7ms/step - accuracy: 0.8438 - loss: 0.4161 - val_accuracy: 1.0000 - val_loss: 0.1267\n",
      "Epoch 9/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m154s\u001b[0m 2s/step - accuracy: 0.8969 - loss: 0.3322 - val_accuracy: 0.8860 - val_loss: 0.3748\n",
      "Epoch 10/10\n",
      "\u001b[1m68/68\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 6ms/step - accuracy: 0.9375 - loss: 0.2687 - val_accuracy: 1.0000 - val_loss: 0.1681\n"
     ]
    }
   ],
   "source": [
    "history = model.fit(\n",
    "    train_generator,\n",
    "    steps_per_epoch=train_generator.samples // train_generator.batch_size,\n",
    "    validation_data=validation_generator,\n",
    "    validation_steps=validation_generator.samples // validation_generator.batch_size,\n",
    "    epochs=10\n",
    ")\n",
    "\n",
    "#This specifies the number of complete passes through the training dataset. Here, the model will train for 10 epochs."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 2s/step - accuracy: 0.8850 - loss: 0.3732\n",
      "Validation loss: 0.36864525079727173\n",
      "Validation accuracy: 0.8870673775672913\n"
     ]
    }
   ],
   "source": [
    "loss, accuracy = model.evaluate(validation_generator)\n",
    "print(f'Validation loss: {loss}')\n",
    "print(f'Validation accuracy: {accuracy}')\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "base",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.11.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}