{ "cells": [ { "cell_type": "code", "execution_count": 1, "id": "cad950d4", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "D:/cats-v-dogs created\n", "D:/cats-v-dogs/training created\n", "D:/cats-v-dogs/testing created\n", "D:/cats-v-dogs/training/cats created\n", "D:/cats-v-dogs/training/dogs created\n", "D:/cats-v-dogs/testing/cats created\n", "D:/cats-v-dogs/testing/dogs created\n", "666.jpg is zero length, so ignoring\n" ] } ], "source": [ "import tensorflow as tf\n", "from tensorflow import keras\n", "import os\n", "import random\n", "from shutil import copyfile\n", "\n", "\n", "\n", "def split_data(SOURCE, TRAINING, TESTING, SPLIT_SIZE):\n", " all_files = []\n", " \n", " for file_name in os.listdir(SOURCE):\n", " file_path = SOURCE + file_name\n", "\n", " if os.path.getsize(file_path):\n", " all_files.append(file_name)\n", " else:\n", " print('{} is zero length, so ignoring'.format(file_name))\n", " \n", " n_files = len(all_files)\n", " split_point = int(n_files * SPLIT_SIZE)\n", " \n", " shuffled = random.sample(all_files, n_files)\n", " \n", " train_set = shuffled[:split_point]\n", " test_set = shuffled[split_point:]\n", " \n", " for file_name in train_set:\n", " copyfile(SOURCE + file_name, TRAINING + file_name)\n", " \n", " for file_name in test_set:\n", " copyfile(SOURCE + file_name, TESTING + file_name)\n", "\n", "to_create = [\n", " 'D:/cats-v-dogs',\n", " 'D:/cats-v-dogs/training',\n", " 'D:/cats-v-dogs/testing',\n", " 'D:/cats-v-dogs/training/cats',\n", " 'D:/cats-v-dogs/training/dogs',\n", " 'D:/cats-v-dogs/testing/cats',\n", " 'D:/cats-v-dogs/testing/dogs'\n", "]\n", "\n", "for directory in to_create:\n", " try:\n", " os.mkdir(directory)\n", " print(directory, 'created')\n", " except:\n", " print(directory, 'failed')\n", "\n", "CAT_SOURCE_DIR = r\"D:/PettImages/Cat/\"\n", "TRAINING_CATS_DIR = r\"D:/cats-v-dogs/training/cats/\"\n", "TESTING_CATS_DIR = r\"D:/cats-v-dogs/testing/cats/\"\n", "DOG_SOURCE_DIR = r\"D:/PettImages/Dog/\"\n", "TRAINING_DOGS_DIR = r\"D:/cats-v-dogs/training/dogs/\"\n", "TESTING_DOGS_DIR = r\"D:/cats-v-dogs/testing/dogs/\"\n", "\n", "split_size = .7\n", "split_data(CAT_SOURCE_DIR, TRAINING_CATS_DIR, TESTING_CATS_DIR, split_size)\n", "split_data(DOG_SOURCE_DIR, TRAINING_DOGS_DIR, TESTING_DOGS_DIR, split_size)\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "id": "aa6a7fa8", "metadata": {}, "outputs": [ { "name": "stdout", "output_type": "stream", "text": [ "Found 2801 images belonging to 2 classes.\n", "Found 1202 images belonging to 2 classes.\n", "Model: \"sequential\"\n", "_________________________________________________________________\n", "Layer (type) Output Shape Param # \n", "=================================================================\n", "conv2d (Conv2D) (None, 148, 148, 32) 896 \n", "_________________________________________________________________\n", "max_pooling2d (MaxPooling2D) (None, 74, 74, 32) 0 \n", "_________________________________________________________________\n", "conv2d_1 (Conv2D) (None, 72, 72, 64) 18496 \n", "_________________________________________________________________\n", "max_pooling2d_1 (MaxPooling2 (None, 36, 36, 64) 0 \n", "_________________________________________________________________\n", "conv2d_2 (Conv2D) (None, 34, 34, 64) 36928 \n", "_________________________________________________________________\n", "max_pooling2d_2 (MaxPooling2 (None, 17, 17, 64) 0 \n", "_________________________________________________________________\n", "conv2d_3 (Conv2D) (None, 15, 15, 128) 73856 \n", "_________________________________________________________________\n", "max_pooling2d_3 (MaxPooling2 (None, 7, 7, 128) 0 \n", "_________________________________________________________________\n", "flatten (Flatten) (None, 6272) 0 \n", "_________________________________________________________________\n", "dense (Dense) (None, 512) 3211776 \n", "_________________________________________________________________\n", "dense_1 (Dense) (None, 64) 32832 \n", "_________________________________________________________________\n", "dense_2 (Dense) (None, 1) 65 \n", "=================================================================\n", "Total params: 3,374,849\n", "Trainable params: 3,374,849\n", "Non-trainable params: 0\n", "_________________________________________________________________\n", "Epoch 1/50\n", "29/29 [==============================] - 167s 6s/step - loss: 0.6929 - accuracy: 0.5112 - val_loss: 0.6913 - val_accuracy: 0.5300\n", "Epoch 2/50\n", "29/29 [==============================] - 135s 5s/step - loss: 0.6916 - accuracy: 0.5095 - val_loss: 0.6901 - val_accuracy: 0.5549\n", "Epoch 3/50\n", "29/29 [==============================] - 136s 5s/step - loss: 0.6901 - accuracy: 0.5562 - val_loss: 0.6896 - val_accuracy: 0.5699\n", "Epoch 4/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6894 - accuracy: 0.5619 - val_loss: 0.6882 - val_accuracy: 0.5524\n", "Epoch 5/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6876 - accuracy: 0.5612 - val_loss: 0.6881 - val_accuracy: 0.5100\n", "Epoch 6/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6869 - accuracy: 0.5477 - val_loss: 0.6867 - val_accuracy: 0.5932\n", "Epoch 7/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6873 - accuracy: 0.5441 - val_loss: 0.6854 - val_accuracy: 0.5158\n", "Epoch 8/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6862 - accuracy: 0.5602 - val_loss: 0.6843 - val_accuracy: 0.5349\n", "Epoch 9/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6862 - accuracy: 0.5659 - val_loss: 0.6831 - val_accuracy: 0.5632\n", "Epoch 10/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6855 - accuracy: 0.5787 - val_loss: 0.6820 - val_accuracy: 0.5699\n", "Epoch 11/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6830 - accuracy: 0.5652 - val_loss: 0.6813 - val_accuracy: 0.5998\n", "Epoch 12/50\n", "29/29 [==============================] - 132s 5s/step - loss: 0.6818 - accuracy: 0.5869 - val_loss: 0.6849 - val_accuracy: 0.5574\n", "Epoch 13/50\n", "29/29 [==============================] - 133s 5s/step - loss: 0.6821 - accuracy: 0.5698 - val_loss: 0.6790 - val_accuracy: 0.5857\n", "Epoch 14/50\n", "29/29 [==============================] - 3630s 125s/step - loss: 0.6798 - accuracy: 0.5801 - val_loss: 0.6772 - val_accuracy: 0.5899\n", "Epoch 15/50\n", "29/29 [==============================] - 168s 6s/step - loss: 0.6802 - accuracy: 0.5930 - val_loss: 0.6764 - val_accuracy: 0.5699\n", "Epoch 16/50\n", "29/29 [==============================] - 179s 6s/step - loss: 0.6768 - accuracy: 0.6026 - val_loss: 0.6751 - val_accuracy: 0.5849\n", "Epoch 17/50\n", "29/29 [==============================] - 154s 5s/step - loss: 0.6770 - accuracy: 0.5837 - val_loss: 0.6761 - val_accuracy: 0.5599\n", "Epoch 18/50\n", "29/29 [==============================] - 171s 6s/step - loss: 0.6750 - accuracy: 0.5866 - val_loss: 0.6723 - val_accuracy: 0.5899\n", "Epoch 19/50\n", "29/29 [==============================] - 185s 6s/step - loss: 0.6746 - accuracy: 0.5869 - val_loss: 0.6716 - val_accuracy: 0.5882\n", "Epoch 20/50\n", "29/29 [==============================] - 168s 6s/step - loss: 0.6743 - accuracy: 0.5884 - val_loss: 0.6702 - val_accuracy: 0.5965\n", "Epoch 21/50\n", "29/29 [==============================] - 163s 6s/step - loss: 0.6728 - accuracy: 0.5994 - val_loss: 0.6727 - val_accuracy: 0.5566\n", "Epoch 22/50\n", "29/29 [==============================] - 158s 5s/step - loss: 0.6694 - accuracy: 0.5987 - val_loss: 0.6696 - val_accuracy: 0.5807\n", "Epoch 23/50\n", "29/29 [==============================] - 153s 5s/step - loss: 0.6717 - accuracy: 0.5987 - val_loss: 0.6708 - val_accuracy: 0.5649\n", "Epoch 24/50\n", " 4/29 [===>..........................] - ETA: 1:28 - loss: 0.6726 - accuracy: 0.6075" ] } ], "source": [ "\n", "\n", "from tensorflow.keras.preprocessing.image import ImageDataGenerator\n", "train_img= ImageDataGenerator(rescale=1 / 255,\n", " rotation_range=180,\n", " width_shift_range=.2,\n", " height_shift_range=.2,\n", " shear_range=.2,\n", " zoom_range=.2,\n", " horizontal_flip=True,\n", " fill_mode='nearest' )\n", "\n", "val_img=ImageDataGenerator(rescale=1/255)\n", "\n", "train_img_gen= train_img.flow_from_directory('D:/cats-v-dogs/training', target_size=(150,150), batch_size=100, class_mode='binary')\n", "validation_img_gen = val_img.flow_from_directory('D:/cats-v-dogs/testing', target_size=(150,150), batch_size=100, class_mode='binary')\n", "\n", "\n", "\n", "model= keras.models.Sequential([\n", " keras.layers.Conv2D(32,(3,3),input_shape=(150,150,3), activation= 'relu' ),\n", " keras.layers.MaxPool2D(2,2),\n", " \n", " keras.layers.Conv2D(64,(3,3), activation= 'relu'),\n", " keras.layers.MaxPool2D(2,2),\n", " \n", " keras.layers.Conv2D(64,(3,3), activation= 'relu'),\n", " keras.layers.MaxPool2D(2,2),\n", " \n", " keras.layers.Conv2D(128,(3,3), activation= 'relu'),\n", " keras.layers.MaxPool2D(2,2),\n", " \n", " keras.layers.Flatten(),\n", " keras.layers.Dense(units=512, activation='relu'),\n", " keras.layers.Dense(units=64, activation='relu'),\n", " keras.layers.Dense(units=1, activation= 'sigmoid')\n", "])\n", "\n", "model.summary()\n", "\n", "from tensorflow.keras.optimizers import RMSprop\n", "\n", "model.compile(RMSprop(lr=0.00001), loss='binary_crossentropy', metrics=['accuracy'])\n", "\n", "history= model.fit(train_img_gen, epochs=50, verbose=1,validation_data=validation_img_gen)\n", "\n", "\n", "\n" ] }, { "cell_type": "code", "execution_count": null, "id": "50d5b341", "metadata": {}, "outputs": [], "source": [ "# PLOT LOSS AND ACCURACY\n", "%matplotlib inline\n", "\n", "import matplotlib.image as mpimg\n", "import matplotlib.pyplot as plt\n", "\n", "#-----------------------------------------------------------\n", "# Retrieve a list of list results on training and test data\n", "# sets for each training epoch\n", "#-----------------------------------------------------------\n", "acc=history.history['accuracy']\n", "val_acc=history.history['val_accuracy']\n", "loss=history.history['loss']\n", "val_loss=history.history['val_loss']\n", "\n", "epochs=range(len(acc)) # Get number of epochs\n", "\n", "#------------------------------------------------\n", "# Plot training and validation accuracy per epoch\n", "#------------------------------------------------\n", "plt.plot(epochs, acc, 'r', label=\"Training Accuracy\")\n", "plt.plot(epochs, val_acc, 'b', label=\"Validation Accuracy\")\n", "plt.legend()\n", "plt.title('Training and validation accuracy')\n", "plt.figure()\n", "\n", "#------------------------------------------------\n", "# Plot training and validation loss per epoch\n", "#------------------------------------------------\n", "plt.plot(epochs, loss, 'r', \"Training Loss\")\n", "plt.plot(epochs, val_loss, 'b', \"Validation Loss\")\n", "\n", "\n", "plt.title('Training and validation loss')\n", "\n", "# Desired output. Charts with training and validation metrics. No crash :)\n" ] }, { "cell_type": "code", "execution_count": null, "id": "10dc297c", "metadata": {}, "outputs": [], "source": [ "import numpy as np\n", "from google.colab import files\n", "from keras.preprocessing import image\n", "\n", "uploaded = files.upload()\n", "\n", "for fn in uploaded.keys():\n", " \n", " # predicting images\n", " path = '/content/' + fn\n", " img = image.load_img(path, target_size=(150,150))\n", " x = image.img_to_array(img)\n", " x = np.expand_dims(x, axis=0)\n", "\n", " images = np.vstack([x])\n", " classes = model.predict(images, batch_size=10)\n", " print(classes[0])\n", " if classes[0]>0.5:\n", " print(fn + \" is a dog\")\n", " else:\n", " print(fn + \" is a cat\")" ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "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": "3.8.8" } }, "nbformat": 4, "nbformat_minor": 5 }