Fixed titles

Exercises/Exercise 6 - Cats v Dogs with Augmentation/Exercise 6 - Answer.ipynb

@@ -3,7 +3,7 @@
   "nbformat_minor": 0,
   "metadata": {
     "colab": {
-      "name": "Exercise 4 - Answer.ipynb",
+      "name": "Exercise 6 - Answer.ipynb",
       "version": "0.3.2",
       "provenance": []
     },

Exercises/Exercise 6 - Cats v Dogs with Augmentation/Exercise 6 - Question.ipynb

@@ -1 +1 @@
-{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Exercise 4 - Question.ipynb","version":"0.3.2","provenance":[{"file_id":"1dGHF5_gCd_iW3blaWG-kNce153CHvM-I","timestamp":1550529081161}],"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"accelerator":"GPU"},"cells":[{"metadata":{"id":"dn-6c02VmqiN","colab_type":"code","colab":{}},"cell_type":"code","source":["# In this exercise you will train a CNN on the FULL Cats-v-dogs dataset\n","# This will require you doing a lot of data preprocessing because\n","# the dataset isn't split into training and validation for you\n","# This code block has all the required inputs\n","import os\n","import zipfile\n","import random\n","import tensorflow as tf\n","from tensorflow.keras.optimizers import RMSprop\n","from tensorflow.keras.preprocessing.image import ImageDataGenerator\n","from shutil import copyfile"],"execution_count":0,"outputs":[]},{"metadata":{"id":"3sd9dQWa23aj","colab_type":"code","colab":{}},"cell_type":"code","source":["# This code block downloads the full Cats-v-Dogs dataset and stores it as \n","# cats-and-dogs.zip. It then unzips it to /tmp\n","# which will create a tmp/PetImages directory containing subdirectories\n","# called 'Cat' and 'Dog' (that's how the original researchers structured it)\n","# If the URL doesn't work, \n","# .   visit https://www.microsoft.com/en-us/download/confirmation.aspx?id=54765\n","# And right click on the 'Download Manually' link to get a new URL\n","\n","!wget --no-check-certificate \\\n","    \"https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip\" \\\n","    -O \"/tmp/cats-and-dogs.zip\"\n","\n","local_zip = '/tmp/cats-and-dogs.zip'\n","zip_ref = zipfile.ZipFile(local_zip, 'r')\n","zip_ref.extractall('/tmp')\n","zip_ref.close()\n"],"execution_count":0,"outputs":[]},{"metadata":{"id":"gi3yD62a6X3S","colab_type":"code","colab":{}},"cell_type":"code","source":["print(len(os.listdir('/tmp/PetImages/Cat/')))\n","print(len(os.listdir('/tmp/PetImages/Dog/')))\n","\n","# Expected Output:\n","# 12501\n","# 12501"],"execution_count":0,"outputs":[]},{"metadata":{"id":"F-QkLjxpmyK2","colab_type":"code","colab":{}},"cell_type":"code","source":["# Use os.mkdir to create your directories\n","# You will need a directory for cats-v-dogs, and subdirectories for training\n","# and testing. These in turn will need subdirectories for 'cats' and 'dogs'\n","try:\n","    #YOUR CODE GOES HERE\n","except OSError:\n","    pass"],"execution_count":0,"outputs":[]},{"metadata":{"id":"zvSODo0f9LaU","colab_type":"code","colab":{}},"cell_type":"code","source":["# Write a python function called split_data which takes\n","# a SOURCE directory containing the files\n","# a TRAINING directory that a portion of the files will be copied to\n","# a TESTING directory that a portion of the files will be copie to\n","# a SPLIT SIZE to determine the portion\n","# The files should also be randomized, so that the training set is a random\n","# X% of the files, and the test set is the remaining files\n","# SO, for example, if SOURCE is PetImages/Cat, and SPLIT SIZE is .9\n","# Then 90% of the images in PetImages/Cat will be copied to the TRAINING dir\n","# and 10% of the images will be copied to the TESTING dir\n","# Also -- All images should be checked, and if they have a zero file length,\n","# they will not be copied over\n","#\n","# os.listdir(DIRECTORY) gives you a listing of the contents of that directory\n","# os.path.getsize(PATH) gives you the size of the file\n","# copyfile(source, destination) copies a file from source to destination\n","# random.sample(list, len(list)) shuffles a list\n","def split_data(SOURCE, TRAINING, TESTING, SPLIT_SIZE):\n","# YOUR CODE STARTS HERE\n","# YOUR CODE ENDS HERE\n","\n","\n","CAT_SOURCE_DIR = \"/tmp/PetImages/Cat/\"\n","TRAINING_CATS_DIR = \"/tmp/cats-v-dogs/training/cats/\"\n","TESTING_CATS_DIR = \"/tmp/cats-v-dogs/testing/cats/\"\n","DOG_SOURCE_DIR = \"/tmp/PetImages/Dog/\"\n","TRAINING_DOGS_DIR = \"/tmp/cats-v-dogs/training/dogs/\"\n","TESTING_DOGS_DIR = \"/tmp/cats-v-dogs/testing/dogs/\"\n","\n","split_size = .9\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","# Expected output\n","# 666.jpg is zero length, so ignoring\n","# 11702.jpg is zero length, so ignoring"],"execution_count":0,"outputs":[]},{"metadata":{"id":"luthalB76ufC","colab_type":"code","colab":{}},"cell_type":"code","source":["print(len(os.listdir('/tmp/cats-v-dogs/training/cats/')))\n","print(len(os.listdir('/tmp/cats-v-dogs/training/dogs/')))\n","print(len(os.listdir('/tmp/cats-v-dogs/testing/cats/')))\n","print(len(os.listdir('/tmp/cats-v-dogs/testing/dogs/')))\n","\n","# Expected output:\n","# 11250\n","# 11250\n","# 1250\n","# 1250"],"execution_count":0,"outputs":[]},{"metadata":{"id":"-BQrav4anTmj","colab_type":"code","colab":{}},"cell_type":"code","source":["# DEFINE A KERAS MODEL TO CLASSIFY CATS V DOGS\n","# USE AT LEAST 3 CONVOLUTION LAYERS\n","model = tf.keras.models.Sequential([\n","# YOUR CODE HERE\n","])\n","\n","model.compile(optimizer=RMSprop(lr=0.001), loss='binary_crossentropy', metrics=['acc'])"],"execution_count":0,"outputs":[]},{"metadata":{"id":"mlNjoJ5D61N6","colab_type":"code","colab":{}},"cell_type":"code","source":["TRAINING_DIR = #YOUR CODE HERE\n","train_datagen = #YOUR CODE HERE\n","train_generator = #YOUR CODE HERE\n","\n","VALIDATION_DIR = #YOUR CODE HERE\n","validation_datagen = #YOUR CODE HERE\n","validation_generator = #YOUR CODE HERE\n","\n","\n","\n","# Expected Output:\n","# Found 22498 images belonging to 2 classes.\n","# Found 2500 images belonging to 2 classes."],"execution_count":0,"outputs":[]},{"metadata":{"id":"KyS4n53w7DxC","colab_type":"code","colab":{}},"cell_type":"code","source":["history = model.fit_generator(train_generator,\n","                              epochs=15,\n","                              verbose=1,\n","                              validation_data=validation_generator)\n","\n","# The expectation here is that the model will train, and that accuracy will be > 95% on both training and validation\n","# i.e. acc:A1 and val_acc:A2 will be visible, and both A1 and A2 will be > .9"],"execution_count":0,"outputs":[]},{"metadata":{"id":"MWZrJN4-65RC","colab_type":"code","colab":{}},"cell_type":"code","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['acc']\n","val_acc=history.history['val_acc']\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', \"Training Accuracy\")\n","plt.plot(epochs, val_acc, 'b', \"Validation Accuracy\")\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 :)"],"execution_count":0,"outputs":[]},{"metadata":{"id":"LqL6FYUrtXpf","colab_type":"code","colab":{}},"cell_type":"code","source":["# Here's a codeblock just for fun. You should be able to upload an image here \n","# and have it classified without crashing\n","\n","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=(# YOUR CODE HERE))\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\")"],"execution_count":0,"outputs":[]}]}
+{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"Exercise 6 - Question.ipynb","version":"0.3.2","provenance":[{"file_id":"1dGHF5_gCd_iW3blaWG-kNce153CHvM-I","timestamp":1550529081161}],"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"accelerator":"GPU"},"cells":[{"metadata":{"id":"dn-6c02VmqiN","colab_type":"code","colab":{}},"cell_type":"code","source":["# In this exercise you will train a CNN on the FULL Cats-v-dogs dataset\n","# This will require you doing a lot of data preprocessing because\n","# the dataset isn't split into training and validation for you\n","# This code block has all the required inputs\n","import os\n","import zipfile\n","import random\n","import tensorflow as tf\n","from tensorflow.keras.optimizers import RMSprop\n","from tensorflow.keras.preprocessing.image import ImageDataGenerator\n","from shutil import copyfile"],"execution_count":0,"outputs":[]},{"metadata":{"id":"3sd9dQWa23aj","colab_type":"code","colab":{}},"cell_type":"code","source":["# This code block downloads the full Cats-v-Dogs dataset and stores it as \n","# cats-and-dogs.zip. It then unzips it to /tmp\n","# which will create a tmp/PetImages directory containing subdirectories\n","# called 'Cat' and 'Dog' (that's how the original researchers structured it)\n","# If the URL doesn't work, \n","# .   visit https://www.microsoft.com/en-us/download/confirmation.aspx?id=54765\n","# And right click on the 'Download Manually' link to get a new URL\n","\n","!wget --no-check-certificate \\\n","    \"https://download.microsoft.com/download/3/E/1/3E1C3F21-ECDB-4869-8368-6DEBA77B919F/kagglecatsanddogs_3367a.zip\" \\\n","    -O \"/tmp/cats-and-dogs.zip\"\n","\n","local_zip = '/tmp/cats-and-dogs.zip'\n","zip_ref = zipfile.ZipFile(local_zip, 'r')\n","zip_ref.extractall('/tmp')\n","zip_ref.close()\n"],"execution_count":0,"outputs":[]},{"metadata":{"id":"gi3yD62a6X3S","colab_type":"code","colab":{}},"cell_type":"code","source":["print(len(os.listdir('/tmp/PetImages/Cat/')))\n","print(len(os.listdir('/tmp/PetImages/Dog/')))\n","\n","# Expected Output:\n","# 12501\n","# 12501"],"execution_count":0,"outputs":[]},{"metadata":{"id":"F-QkLjxpmyK2","colab_type":"code","colab":{}},"cell_type":"code","source":["# Use os.mkdir to create your directories\n","# You will need a directory for cats-v-dogs, and subdirectories for training\n","# and testing. These in turn will need subdirectories for 'cats' and 'dogs'\n","try:\n","    #YOUR CODE GOES HERE\n","except OSError:\n","    pass"],"execution_count":0,"outputs":[]},{"metadata":{"id":"zvSODo0f9LaU","colab_type":"code","colab":{}},"cell_type":"code","source":["# Write a python function called split_data which takes\n","# a SOURCE directory containing the files\n","# a TRAINING directory that a portion of the files will be copied to\n","# a TESTING directory that a portion of the files will be copie to\n","# a SPLIT SIZE to determine the portion\n","# The files should also be randomized, so that the training set is a random\n","# X% of the files, and the test set is the remaining files\n","# SO, for example, if SOURCE is PetImages/Cat, and SPLIT SIZE is .9\n","# Then 90% of the images in PetImages/Cat will be copied to the TRAINING dir\n","# and 10% of the images will be copied to the TESTING dir\n","# Also -- All images should be checked, and if they have a zero file length,\n","# they will not be copied over\n","#\n","# os.listdir(DIRECTORY) gives you a listing of the contents of that directory\n","# os.path.getsize(PATH) gives you the size of the file\n","# copyfile(source, destination) copies a file from source to destination\n","# random.sample(list, len(list)) shuffles a list\n","def split_data(SOURCE, TRAINING, TESTING, SPLIT_SIZE):\n","# YOUR CODE STARTS HERE\n","# YOUR CODE ENDS HERE\n","\n","\n","CAT_SOURCE_DIR = \"/tmp/PetImages/Cat/\"\n","TRAINING_CATS_DIR = \"/tmp/cats-v-dogs/training/cats/\"\n","TESTING_CATS_DIR = \"/tmp/cats-v-dogs/testing/cats/\"\n","DOG_SOURCE_DIR = \"/tmp/PetImages/Dog/\"\n","TRAINING_DOGS_DIR = \"/tmp/cats-v-dogs/training/dogs/\"\n","TESTING_DOGS_DIR = \"/tmp/cats-v-dogs/testing/dogs/\"\n","\n","split_size = .9\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","# Expected output\n","# 666.jpg is zero length, so ignoring\n","# 11702.jpg is zero length, so ignoring"],"execution_count":0,"outputs":[]},{"metadata":{"id":"luthalB76ufC","colab_type":"code","colab":{}},"cell_type":"code","source":["print(len(os.listdir('/tmp/cats-v-dogs/training/cats/')))\n","print(len(os.listdir('/tmp/cats-v-dogs/training/dogs/')))\n","print(len(os.listdir('/tmp/cats-v-dogs/testing/cats/')))\n","print(len(os.listdir('/tmp/cats-v-dogs/testing/dogs/')))\n","\n","# Expected output:\n","# 11250\n","# 11250\n","# 1250\n","# 1250"],"execution_count":0,"outputs":[]},{"metadata":{"id":"-BQrav4anTmj","colab_type":"code","colab":{}},"cell_type":"code","source":["# DEFINE A KERAS MODEL TO CLASSIFY CATS V DOGS\n","# USE AT LEAST 3 CONVOLUTION LAYERS\n","model = tf.keras.models.Sequential([\n","# YOUR CODE HERE\n","])\n","\n","model.compile(optimizer=RMSprop(lr=0.001), loss='binary_crossentropy', metrics=['acc'])"],"execution_count":0,"outputs":[]},{"metadata":{"id":"mlNjoJ5D61N6","colab_type":"code","colab":{}},"cell_type":"code","source":["TRAINING_DIR = #YOUR CODE HERE\n","train_datagen = #YOUR CODE HERE\n","train_generator = #YOUR CODE HERE\n","\n","VALIDATION_DIR = #YOUR CODE HERE\n","validation_datagen = #YOUR CODE HERE\n","validation_generator = #YOUR CODE HERE\n","\n","\n","\n","# Expected Output:\n","# Found 22498 images belonging to 2 classes.\n","# Found 2500 images belonging to 2 classes."],"execution_count":0,"outputs":[]},{"metadata":{"id":"KyS4n53w7DxC","colab_type":"code","colab":{}},"cell_type":"code","source":["history = model.fit_generator(train_generator,\n","                              epochs=15,\n","                              verbose=1,\n","                              validation_data=validation_generator)\n","\n","# The expectation here is that the model will train, and that accuracy will be > 95% on both training and validation\n","# i.e. acc:A1 and val_acc:A2 will be visible, and both A1 and A2 will be > .9"],"execution_count":0,"outputs":[]},{"metadata":{"id":"MWZrJN4-65RC","colab_type":"code","colab":{}},"cell_type":"code","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['acc']\n","val_acc=history.history['val_acc']\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', \"Training Accuracy\")\n","plt.plot(epochs, val_acc, 'b', \"Validation Accuracy\")\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 :)"],"execution_count":0,"outputs":[]},{"metadata":{"id":"LqL6FYUrtXpf","colab_type":"code","colab":{}},"cell_type":"code","source":["# Here's a codeblock just for fun. You should be able to upload an image here \n","# and have it classified without crashing\n","\n","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=(# YOUR CODE HERE))\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\")"],"execution_count":0,"outputs":[]}]}