ClassifAI_ 3 - Intro NN

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"name":"ClassifAI: 3 - Intro NN","provenance":[{"file_id":"14EZ1rv3KjsiGl_rmUbzpcqxJ5bwDz53x","timestamp":1653863951047},{"file_id":"1OpQ1_boCAqH46UKtP3WQqAyXlAlEp9Wk","timestamp":1634465676258}],"collapsed_sections":[]},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU"},"cells":[{"cell_type":"code","metadata":{"id":"ORw2oq4tcjKh","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1660526030077,"user_tz":420,"elapsed":6017,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"dba9d3c9-a544-4085-895b-4ab4182e1320"},"source":["!pip install tensorflow\n","!pip3 install keras-visualizer"],"execution_count":5,"outputs":[{"output_type":"stream","name":"stdout","text":["Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Requirement already satisfied: tensorflow in /usr/local/lib/python3.7/dist-packages (2.8.2+zzzcolab20220719082949)\n","Requirement already satisfied: flatbuffers>=1.12 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (2.0)\n","Requirement already satisfied: libclang>=9.0.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (14.0.6)\n","Requirement already satisfied: google-pasta>=0.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (0.2.0)\n","Requirement already satisfied: opt-einsum>=2.3.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (3.3.0)\n","Requirement already satisfied: numpy>=1.20 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.21.6)\n","Requirement already satisfied: tensorflow-estimator<2.9,>=2.8 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (2.8.0)\n","Requirement already satisfied: setuptools in /usr/local/lib/python3.7/dist-packages (from tensorflow) (57.4.0)\n","Requirement already satisfied: grpcio<2.0,>=1.24.3 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.47.0)\n","Requirement already satisfied: keras-preprocessing>=1.1.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.1.2)\n","Requirement already satisfied: gast>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (0.5.3)\n","Requirement already satisfied: tensorboard<2.9,>=2.8 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (2.8.0)\n","Requirement already satisfied: keras<2.9,>=2.8.0rc0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (2.8.0)\n","Requirement already satisfied: absl-py>=0.4.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.2.0)\n","Requirement already satisfied: wrapt>=1.11.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.14.1)\n","Requirement already satisfied: tensorflow-io-gcs-filesystem>=0.23.1 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (0.26.0)\n","Requirement already satisfied: protobuf<3.20,>=3.9.2 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (3.17.3)\n","Requirement already satisfied: typing-extensions>=3.6.6 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (4.1.1)\n","Requirement already satisfied: astunparse>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.6.3)\n","Requirement already satisfied: termcolor>=1.1.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.1.0)\n","Requirement already satisfied: six>=1.12.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (1.15.0)\n","Requirement already satisfied: h5py>=2.9.0 in /usr/local/lib/python3.7/dist-packages (from tensorflow) (3.1.0)\n","Requirement already satisfied: wheel<1.0,>=0.23.0 in /usr/local/lib/python3.7/dist-packages (from astunparse>=1.6.0->tensorflow) (0.37.1)\n","Requirement already satisfied: cached-property in /usr/local/lib/python3.7/dist-packages (from h5py>=2.9.0->tensorflow) (1.5.2)\n","Requirement already satisfied: google-auth<3,>=1.6.3 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (1.35.0)\n","Requirement already satisfied: requests<3,>=2.21.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (2.23.0)\n","Requirement already satisfied: tensorboard-plugin-wit>=1.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (1.8.1)\n","Requirement already satisfied: werkzeug>=0.11.15 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (1.0.1)\n","Requirement already satisfied: markdown>=2.6.8 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (3.4.1)\n","Requirement already satisfied: google-auth-oauthlib<0.5,>=0.4.1 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (0.4.6)\n","Requirement already satisfied: tensorboard-data-server<0.7.0,>=0.6.0 in /usr/local/lib/python3.7/dist-packages (from tensorboard<2.9,>=2.8->tensorflow) (0.6.1)\n","Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow) (0.2.8)\n","Requirement already satisfied: cachetools<5.0,>=2.0.0 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow) (4.2.4)\n","Requirement already satisfied: rsa<5,>=3.1.4 in /usr/local/lib/python3.7/dist-packages (from google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow) (4.9)\n","Requirement already satisfied: requests-oauthlib>=0.7.0 in /usr/local/lib/python3.7/dist-packages (from google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow) (1.3.1)\n","Requirement already satisfied: importlib-metadata>=4.4 in /usr/local/lib/python3.7/dist-packages (from markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow) (4.12.0)\n","Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.7/dist-packages (from importlib-metadata>=4.4->markdown>=2.6.8->tensorboard<2.9,>=2.8->tensorflow) (3.8.1)\n","Requirement already satisfied: pyasn1<0.5.0,>=0.4.6 in /usr/local/lib/python3.7/dist-packages (from pyasn1-modules>=0.2.1->google-auth<3,>=1.6.3->tensorboard<2.9,>=2.8->tensorflow) (0.4.8)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (2022.6.15)\n","Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (3.0.4)\n","Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (2.10)\n","Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.7/dist-packages (from requests<3,>=2.21.0->tensorboard<2.9,>=2.8->tensorflow) (1.24.3)\n","Requirement already satisfied: oauthlib>=3.0.0 in /usr/local/lib/python3.7/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<0.5,>=0.4.1->tensorboard<2.9,>=2.8->tensorflow) (3.2.0)\n","Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n","Requirement already satisfied: keras-visualizer in /usr/local/lib/python3.7/dist-packages (2.4)\n"]}]},{"cell_type":"markdown","metadata":{"id":"Ov3GzLiQiRvh"},"source":[""]},{"cell_type":"code","metadata":{"id":"vI3-fr4mcqQG","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1660526030078,"user_tz":420,"elapsed":25,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"9750d2ca-1a24-42a3-8427-60bf0b4ce064"},"source":["%tensorflow_version 2.x"],"execution_count":6,"outputs":[{"output_type":"stream","name":"stdout","text":["Colab only includes TensorFlow 2.x; %tensorflow_version has no effect.\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"lAecUByCczdt","executionInfo":{"status":"ok","timestamp":1660526030078,"user_tz":420,"elapsed":20,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"5a5df2d5-1b01-4b2e-f167-edd892141fbf"},"source":["import numpy as np\n","import tensorflow as tf\n","print(tf.version)"],"execution_count":7,"outputs":[{"output_type":"stream","name":"stdout","text":["<module 'tensorflow._api.v2.version' from '/usr/local/lib/python3.7/dist-packages/tensorflow/_api/v2/version/__init__.py'>\n"]}]},{"cell_type":"markdown","metadata":{"id":"KyKf29jtdUP7"},"source":["###Tensors \n","Tensors are a higher dimensional vector in different shapes. All these tensors are scalar, having one value\n"]},{"cell_type":"code","metadata":{"id":"76VyfkqVc7Qa","executionInfo":{"status":"ok","timestamp":1660526030079,"user_tz":420,"elapsed":19,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}}},"source":["string = tf.Variable(\"str\", tf.string)\n","number = tf.Variable(15, tf.int16)\n","flt = tf.Variable(3.1415, tf.int64)"],"execution_count":8,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"1IywSsfve0yu"},"source":["### Rank of Tensors\n","The rank of tensors is dependant on the linear algebra definition of rank in a matrix or the deepest level of a nested list."]},{"cell_type":"code","metadata":{"id":"KSpN1gawehxX","executionInfo":{"status":"ok","timestamp":1660526030079,"user_tz":420,"elapsed":18,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}}},"source":["rank_1 = tf.Variable([\"one\",\"two\", \"three\"], tf.string)\n","rank_2 = tf.Variable([[\"one\",\"two\", \"three\"], [\"four\", \"five\", \"six\"]], tf.string)"],"execution_count":9,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"dqEVbp2DeiMK","executionInfo":{"status":"ok","timestamp":1660526030080,"user_tz":420,"elapsed":18,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"69813846-7956-4965-8a4a-d883480c7255"},"source":["tf.rank(rank_2)"],"execution_count":10,"outputs":[{"output_type":"execute_result","data":{"text/plain":["<tf.Tensor: shape=(), dtype=int32, numpy=2>"]},"metadata":{},"execution_count":10}]},{"cell_type":"markdown","metadata":{"id":"FuNSoCECfXCR"},"source":["### Shape of Tensors\n","The shape of a tensor is how many values it has in each dimension. If there is only one dimension, then the shape function will only output one number."]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"_ImdCMrDfwIP","executionInfo":{"status":"ok","timestamp":1660526030080,"user_tz":420,"elapsed":16,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"b40ffdfe-a79b-4071-98ac-fc4c97c86b87"},"source":["rank_2.shape"],"execution_count":11,"outputs":[{"output_type":"execute_result","data":{"text/plain":["TensorShape([2, 3])"]},"metadata":{},"execution_count":11}]},{"cell_type":"markdown","metadata":{"id":"uGX1gAbFf3gJ"},"source":["### Manipulating Tensors"]},{"cell_type":"code","metadata":{"id":"zCCDw1VTjtjN","executionInfo":{"status":"ok","timestamp":1660526030080,"user_tz":420,"elapsed":14,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}}},"source":["first = tf.ones([1,2,3])\n","second = tf.reshape(first, [2,3,1])\n","third = tf.reshape(second, [3, -1]) #-1 tells the tensor to calculate the size of the dimension in that place\n","#the number of elements in the reshaped tensor must be the same as the original tensor"],"execution_count":12,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"lwuOxPYGkAaL","executionInfo":{"status":"ok","timestamp":1660526030081,"user_tz":420,"elapsed":14,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"42a790a5-8d2c-478a-d702-8dc6521dfc73"},"source":["print(first)\n","print(second)\n","print(third)"],"execution_count":13,"outputs":[{"output_type":"stream","name":"stdout","text":["tf.Tensor(\n","[[[1. 1. 1.]\n","  [1. 1. 1.]]], shape=(1, 2, 3), dtype=float32)\n","tf.Tensor(\n","[[[1.]\n","  [1.]\n","  [1.]]\n","\n"," [[1.]\n","  [1.]\n","  [1.]]], shape=(2, 3, 1), dtype=float32)\n","tf.Tensor(\n","[[1. 1.]\n"," [1. 1.]\n"," [1. 1.]], shape=(3, 2), dtype=float32)\n"]}]},{"cell_type":"markdown","metadata":{"id":"s7HZlH6qnf03"},"source":["### Neural Network Time"]},{"cell_type":"code","metadata":{"id":"-QVKXHNSkp3n","executionInfo":{"status":"ok","timestamp":1660526030081,"user_tz":420,"elapsed":13,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}}},"source":["from tensorflow import keras\n","import numpy as np\n","import matplotlib.pyplot as plt\n","from keras import models  \n","from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Activation  \n","from keras_visualizer import visualizer \n","from keras import layers \n"],"execution_count":14,"outputs":[]},{"cell_type":"code","metadata":{"id":"A9UTQFD9nkjQ","executionInfo":{"status":"ok","timestamp":1660526030918,"user_tz":420,"elapsed":850,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"colab":{"base_uri":"https://localhost:8080/"},"outputId":"168c8c3e-5df2-4065-b185-a4904a9cce30"},"source":["fashion_mnist = keras.datasets.fashion_mnist  # load dataset\n","\n","(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()  # split into tetsing and training"],"execution_count":15,"outputs":[{"output_type":"stream","name":"stdout","text":["Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-labels-idx1-ubyte.gz\n","32768/29515 [=================================] - 0s 0us/step\n","40960/29515 [=========================================] - 0s 0us/step\n","Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/train-images-idx3-ubyte.gz\n","26427392/26421880 [==============================] - 0s 0us/step\n","26435584/26421880 [==============================] - 0s 0us/step\n","Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-labels-idx1-ubyte.gz\n","16384/5148 [===============================================================================================] - 0s 0us/step\n","Downloading data from https://storage.googleapis.com/tensorflow/tf-keras-datasets/t10k-images-idx3-ubyte.gz\n","4423680/4422102 [==============================] - 0s 0us/step\n","4431872/4422102 [==============================] - 0s 0us/step\n"]}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"sCP2U4QhnqOu","executionInfo":{"status":"ok","timestamp":1660526030919,"user_tz":420,"elapsed":19,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"f74ab28b-9777-4b5d-d95f-dfc0ffceb94e"},"source":["train_labels.shape"],"execution_count":16,"outputs":[{"output_type":"execute_result","data":{"text/plain":["(60000,)"]},"metadata":{},"execution_count":16}]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"5Wru9VEMnsbq","executionInfo":{"status":"ok","timestamp":1660526030920,"user_tz":420,"elapsed":17,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"057d032f-d572-4cd3-a426-136d112e4e1f"},"source":["train_images[0,23,23]  # let's have a look at one pixel"],"execution_count":17,"outputs":[{"output_type":"execute_result","data":{"text/plain":["194"]},"metadata":{},"execution_count":17}]},{"cell_type":"markdown","metadata":{"id":"P84bEEManxKW"},"source":["Our pixel values are between 0 and 255, 0 being black and 255 being white. This means we have a grayscale image as there are no color channels."]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"NIClz7MKnwXD","executionInfo":{"status":"ok","timestamp":1660526030921,"user_tz":420,"elapsed":14,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"b2048056-9b1e-40e5-f9b6-fd5618cf0064"},"source":["train_labels[:10]  # let's have a look at the first 10 training labels"],"execution_count":18,"outputs":[{"output_type":"execute_result","data":{"text/plain":["array([9, 0, 0, 3, 0, 2, 7, 2, 5, 5], dtype=uint8)"]},"metadata":{},"execution_count":18}]},{"cell_type":"code","metadata":{"id":"jpllCYp5n2CQ","executionInfo":{"status":"ok","timestamp":1660526030921,"user_tz":420,"elapsed":10,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}}},"source":["class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n","               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']"],"execution_count":19,"outputs":[]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/","height":265},"id":"NvpXecbXn3wS","executionInfo":{"status":"ok","timestamp":1660526031387,"user_tz":420,"elapsed":232,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"c6c4b18a-05b6-4078-ce44-dbef1eaef95c"},"source":["plt.figure()\n","plt.imshow(train_images[10], cmap='gray')\n","plt.colorbar()\n","plt.grid(False)\n","plt.show()"],"execution_count":20,"outputs":[{"output_type":"display_data","data":{"text/plain":["<Figure size 432x288 with 2 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}}]},{"cell_type":"markdown","metadata":{"id":"3Gkz-tten7OI"},"source":["###Data Preprocessing\n","We want values to be between 0 and 1 as opposed to being between 0 and 255"]},{"cell_type":"code","metadata":{"id":"4Wbbu5dyn564","executionInfo":{"status":"ok","timestamp":1660526034381,"user_tz":420,"elapsed":409,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}}},"source":["train_images = train_images / 255.0\n","\n","test_images = test_images / 255.0"],"execution_count":21,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"0j_xEohKoGbS"},"source":["#Building the Model"]},{"cell_type":"code","metadata":{"id":"6Y8cO5qioJUz","executionInfo":{"status":"ok","timestamp":1660526042673,"user_tz":420,"elapsed":1038,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}}},"source":["model = keras.Sequential([\n","    keras.layers.Flatten(input_shape=(28, 28)),  # input layer (1)\n","    keras.layers.Dense(128, activation='relu'),  # hidden layer (2)\n","    keras.layers.Dense(128, activation='relu'),\n","    keras.layers.Dense(10, activation='softmax') # output layer (3)\n","])"],"execution_count":22,"outputs":[]},{"cell_type":"markdown","metadata":{"id":"IvX_AFI8oMP-"},"source":["#Compiling and Training the Model"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"OcAcZWq2oOU1","executionInfo":{"status":"ok","timestamp":1660526140088,"user_tz":420,"elapsed":97023,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"67cae10d-b043-48f1-cdb1-8196300ea121"},"source":["model.compile(optimizer='adam',\n","              loss='sparse_categorical_crossentropy',\n","              metrics=['accuracy'])\n","model.fit(train_images, train_labels, epochs=20)  # we pass the data, labels and epochs and watch the magic!"],"execution_count":23,"outputs":[{"output_type":"stream","name":"stdout","text":["Epoch 1/20\n","1875/1875 [==============================] - 8s 2ms/step - loss: 0.4870 - accuracy: 0.8264\n","Epoch 2/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.3659 - accuracy: 0.8657\n","Epoch 3/20\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.3295 - accuracy: 0.8793\n","Epoch 4/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.3070 - accuracy: 0.8862\n","Epoch 5/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.2905 - accuracy: 0.8922\n","Epoch 6/20\n","1875/1875 [==============================] - 5s 2ms/step - loss: 0.2726 - accuracy: 0.8979\n","Epoch 7/20\n","1875/1875 [==============================] - 5s 2ms/step - loss: 0.2617 - accuracy: 0.9017\n","Epoch 8/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.2515 - accuracy: 0.9055\n","Epoch 9/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.2406 - accuracy: 0.9093\n","Epoch 10/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.2296 - accuracy: 0.9135\n","Epoch 11/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.2231 - accuracy: 0.9154\n","Epoch 12/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.2124 - accuracy: 0.9197\n","Epoch 13/20\n","1875/1875 [==============================] - 8s 4ms/step - loss: 0.2075 - accuracy: 0.9209\n","Epoch 14/20\n","1875/1875 [==============================] - 5s 2ms/step - loss: 0.2017 - accuracy: 0.9234\n","Epoch 15/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.1950 - accuracy: 0.9257\n","Epoch 16/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.1875 - accuracy: 0.9275\n","Epoch 17/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.1836 - accuracy: 0.9297\n","Epoch 18/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.1803 - accuracy: 0.9309\n","Epoch 19/20\n","1875/1875 [==============================] - 5s 3ms/step - loss: 0.1712 - accuracy: 0.9344\n","Epoch 20/20\n","1875/1875 [==============================] - 4s 2ms/step - loss: 0.1676 - accuracy: 0.9355\n"]},{"output_type":"execute_result","data":{"text/plain":["<keras.callbacks.History at 0x7f04667a8090>"]},"metadata":{},"execution_count":23}]},{"cell_type":"markdown","metadata":{"id":"y0S_DO7_oWX7"},"source":["#Evaluating the Model"]},{"cell_type":"code","metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"bb5zq1xGoYx2","executionInfo":{"status":"ok","timestamp":1660526655958,"user_tz":420,"elapsed":1105,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"ac637478-b7c6-472a-d10f-eff5b4aafa08"},"source":["test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=1) \n"," \n","print('Test accuracy:', test_acc)"],"execution_count":24,"outputs":[{"output_type":"stream","name":"stdout","text":["313/313 [==============================] - 1s 2ms/step - loss: 0.3880 - accuracy: 0.8868\n","Test accuracy: 0.8867999911308289\n"]}]},{"cell_type":"markdown","metadata":{"id":"DUOqhBAcwjnY"},"source":["###Why do you think the test accuracy is different than the  training accuracy? (It should be lower)"]},{"cell_type":"markdown","metadata":{"id":"vU6SszEmpLe6"},"source":["#Making Predictions"]},{"cell_type":"code","metadata":{"id":"Hxu1nVXfpNuO","colab":{"base_uri":"https://localhost:8080/","height":399},"executionInfo":{"status":"ok","timestamp":1660526708096,"user_tz":420,"elapsed":49770,"user":{"displayName":"Leo Huang","userId":"16558901284710269921"}},"outputId":"4e989b8a-4e0d-4513-8dbd-d8eae073dc27"},"source":["predictions = model.predict(test_images)\n","COLOR = 'white'\n","plt.rcParams['text.color'] = COLOR\n","plt.rcParams['axes.labelcolor'] = COLOR\n","\n","def predict(model, image, correct_label):\n","  class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',\n","               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']\n","  prediction = model.predict(np.array([image]))\n","  print(prediction)\n","  predicted_class = class_names[np.argmax(prediction)]\n","  print(predicted_class)\n","\n","  show_image(image, class_names[correct_label], predicted_class)\n","\n","\n","def show_image(img, label, guess):\n","  plt.figure()\n","  plt.imshow(img, cmap=plt.cm.binary)\n","  plt.title(\"Expected: \" + label)\n","  plt.xlabel(\"Guess: \" + guess)\n","  plt.colorbar()\n","  plt.grid(False)\n","  plt.show()\n","  print(\"Expected: \" + label)\n","  print(\"Guess: \" + guess)\n","\n","\n","def get_number():\n","  while True:\n","    num = input(\"Pick a number: \")\n","    if num.isdigit():\n","      num = int(num)\n","      if 0 <= num <= 1000:\n","        return int(num)\n","    else:\n","      print(\"Try again...\")\n","\n","num = get_number()\n","image = test_images[num]\n","label = test_labels[num]\n","predict(model, image, label)"],"execution_count":25,"outputs":[{"output_type":"stream","name":"stdout","text":["Pick a number: 9\n","[[3.0168400e-15 1.4688141e-10 4.5059637e-11 3.4800697e-13 3.6843372e-11\n","  2.9466041e-09 4.5187184e-11 1.0000000e+00 3.9343149e-13 2.3113718e-11]]\n","Sneaker\n"]},{"output_type":"display_data","data":{"text/plain":["<Figure size 432x288 with 2 Axes>"],"image/png":"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\n"},"metadata":{"needs_background":"light"}},{"output_type":"stream","name":"stdout","text":["Expected: Sneaker\n","Guess: Sneaker\n"]}]},{"cell_type":"code","source":[""],"metadata":{"id":"bTK7K14-SLVH"},"execution_count":null,"outputs":[]}]}