{"metadata":{"kernelspec":{"language":"python","display_name":"Python 3","name":"python3"},"language_info":{"pygments_lexer":"ipython3","nbconvert_exporter":"python","version":"3.6.4","file_extension":".py","codemirror_mode":{"name":"ipython","version":3},"name":"python","mimetype":"text/x-python"}},"nbformat_minor":4,"nbformat":4,"cells":[{"cell_type":"markdown","source":"\"Open","metadata":{"id":"view-in-github"}},{"cell_type":"code","source":"import os\nimport zipfile\nimport shutil\nfrom tqdm import tqdm","metadata":{"id":"sJEBnGc1rbEs","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Extrair os ZIPs\nwith zipfile.ZipFile(\"../input/dogs-vs-cats/train.zip\", \"r\") as unzip:\n unzip.extractall(\".\")\n\n \nwith zipfile.ZipFile(\"../input/dogs-vs-cats/test1.zip\", \"r\") as unzip:\n unzip.extractall(\".\")","metadata":{"id":"q73xb4iYrQJP","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"os.makedirs(\"my_train/dogs\", exist_ok=True)\nos.makedirs(\"my_train/cats\", exist_ok=True)","metadata":{"id":"AFFB_BDvtKmg","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"root = \"train\"\nimgs = os.walk(root).__next__()[2]\nfolders = {\n \"cat\": \"my_train/cats\",\n \"dog\": \"my_train/dogs\"\n}\n\nfor img in tqdm(imgs):\n label = img.split(\".\")[0]\n \n old_path = os.path.join(root, img)\n new_path = os.path.join(folders[label], img)\n \n shutil.move(old_path, new_path)","metadata":{"id":"id8BOS2HuL6c","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"import matplotlib.pyplot as plt\nimport seaborn as sns\nimport cv2\nimport os\nimport pickle\nfrom sklearn.model_selection import train_test_split\nimport sklearn.linear_model\nimport numpy as np\n# from dnn_utils_v2 import sigmoid, sigmoid_backward, relu, relu_backward","metadata":{"id":"_ODbx7qJyOCz","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"labels = ['cats', 'dogs']\nimg_size = 128\ndef get_data(data_dir):\n data = []\n counter = 0\n for label in labels:\n path = os.path.join(data_dir, label)\n class_num = labels.index(label)\n for img in os.listdir(path):\n try:\n img_arr = cv2.imread(os.path.join(path, img))[...,::-1] #convert BGR to RGB format\n resized_arr = cv2.resize(img_arr, (img_size, img_size)) # Reshaping images to preferred size\n data.append([resized_arr, class_num])\n counter+= 1\n # print(counter) # uncomment this if you want to know how many images have been loaded till now.\n if counter >4000: #since the dataset is huge i just made it so it takes first 3000 entries from each category\n counter=0\n break;\n except Exception as e:\n print(e)\n return np.array(data)","metadata":{"id":"Oj3bnGq9yQvA","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def get_test_data(data_dir):\n data = []\n path = os.path.join(data_dir)\n counter = 0\n for img in os.listdir(path):\n try:\n img_arr = cv2.imread(os.path.join(path, img))[...,::-1] #convert BGR to RGB format\n resized_arr = cv2.resize(img_arr, (img_size, img_size)) # Reshaping images to preferred size\n data.append([resized_arr])\n counter+= 1\n print(counter)\n if counter >300:\n break;\n except Exception as e:\n print(e)\n return np.array(data)","metadata":{"id":"XDtNzAIDqB5m","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# # Now we can easily fetch our train and validation data.\ntrain = get_data('./my_train')\n# # test = get_test_data('/content/drive/MyDrive/Datasets/CatsVsDogs/test1')","metadata":{"id":"9QpagD8Wygns","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"train.shape","metadata":{"trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize = (5,5))\nplt.imshow(train[2500][0])\nplt.title(labels[train[0][1]])","metadata":{"id":"TyPoUxL3zONi","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"plt.figure(figsize = (5,5))\nplt.imshow(train[-3001][0])\nplt.title(labels[train[-1][1]])","metadata":{"id":"ndf81fwhSld1","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Write to a pickled dataset.","metadata":{"id":"gc6tT-Cj7waC"}},{"cell_type":"code","source":"# this one holds the pickled data with image size as 224\n# os.chdir('/content/drive/MyDrive/Datasets/CatsVsDogs')\nwith open ('train.pkl','wb') as f:\n pickle.dump(train, f)\n\n# pickling a new dataset with 64*64 image size due to unavailability of RAM\n# os.chdir('./')\n# with open ('train2.pkl','wb') as f:\n# pickle.dump(train, f)\n\n# with open ('val.pkl','wb') as f:#\n# pickle.dump(val, f)","metadata":{"id":"tG5ElBu8WAyx","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"markdown","source":"Read from the pickled dataset.","metadata":{"id":"CYwlpxGS7z3j"}},{"cell_type":"code","source":"os.chdir('./')\nwith open ('train.pkl','rb') as f:\n train=pickle.load(f)\n # print(train.shape)","metadata":{"id":"xt4bNh_tdny0","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def sigmoid(Z):\n \"\"\"\n Implements the sigmoid activation in numpy\n \n Arguments:\n Z -- numpy array of any shape\n \n Returns:\n A -- output of sigmoid(z), same shape as Z\n cache -- returns Z as well, useful during backpropagation\n \"\"\"\n \n A = 1/(1+np.exp(-Z))\n cache = Z\n \n return A, cache","metadata":{"id":"XOngfQXn0JSe","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def relu(Z):\n \"\"\"\n Implement the RELU function.\n Arguments:\n Z -- Output of the linear layer, of any shape\n Returns:\n A -- Post-activation parameter, of the same shape as Z\n cache -- a python dictionary containing \"A\" ; stored for computing the backward pass efficiently\n \"\"\"\n \n A = np.maximum(0,Z)\n \n assert(A.shape == Z.shape)\n \n cache = Z \n return A, cache","metadata":{"id":"znvQPqWn0qwh","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def relu_backward(dA, cache):\n \"\"\"\n Implement the backward propagation for a single RELU unit.\n Arguments:\n dA -- post-activation gradient, of any shape\n cache -- 'Z' where we store for computing backward propagation efficiently\n Returns:\n dZ -- Gradient of the cost with respect to Z\n \"\"\"\n \n Z = cache\n dZ = np.array(dA, copy=True) # just converting dz to a correct object.\n \n # When z <= 0, you should set dz to 0 as well. \n dZ[Z <= 0] = 0\n \n assert (dZ.shape == Z.shape)\n \n return dZ","metadata":{"id":"Xytd8eXo2y1u","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def sigmoid_backward(dA, cache):\n \"\"\"\n Implement the backward propagation for a single SIGMOID unit.\n Arguments:\n dA -- post-activation gradient, of any shape\n cache -- 'Z' where we store for computing backward propagation efficiently\n Returns:\n dZ -- Gradient of the cost with respect to Z\n \"\"\"\n \n Z = cache\n \n s = 1/(1+np.exp(-Z))\n dZ = dA * s * (1-s)\n \n assert (dZ.shape == Z.shape)\n \n return dZ","metadata":{"id":"E2USDbK021mb","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef initialize_parameters(n_x, n_h, n_y):\n \"\"\"\n Argument:\n n_x -- size of the input layer\n n_h -- size of the hidden layer\n n_y -- size of the output layer\n \n Returns:\n parameters -- python dictionary containing your parameters:\n W1 -- weight matrix of shape (n_h, n_x)\n b1 -- bias vector of shape (n_h, 1)\n W2 -- weight matrix of shape (n_y, n_h)\n b2 -- bias vector of shape (n_y, 1)\n \"\"\"\n \n np.random.seed(1)\n \n W1 = np.random.randn(n_h, n_x)*0.01\n b1 = np.zeros((n_h, 1))\n W2 = np.random.randn(n_y, n_h)*0.01\n b2 = np.zeros((n_y, 1))\n \n assert(W1.shape == (n_h, n_x))\n assert(b1.shape == (n_h, 1))\n assert(W2.shape == (n_y, n_h))\n assert(b2.shape == (n_y, 1))\n \n parameters = {\"W1\": W1,\n \"b1\": b1,\n \"W2\": W2,\n \"b2\": b2}\n \n return parameters ","metadata":{"id":"xSmmv-u5p4ZW","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"parameters = initialize_parameters(3,2,1)\nprint(\"W1 = \" + str(parameters[\"W1\"]))\nprint(\"b1 = \" + str(parameters[\"b1\"]))\nprint(\"W2 = \" + str(parameters[\"W2\"]))\nprint(\"b2 = \" + str(parameters[\"b2\"]))","metadata":{"id":"OAc0OWROp-5O","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def initialize_parameters_deep(layer_dims):\n \"\"\"\n Arguments:\n layer_dims -- python array (list) containing the dimensions of each layer in our network\n \n Returns:\n parameters -- python dictionary containing your parameters \"W1\", \"b1\", ..., \"WL\", \"bL\":\n Wl -- weight matrix of shape (layer_dims[l], layer_dims[l-1])\n bl -- bias vector of shape (layer_dims[l], 1)\n \"\"\"\n \n np.random.seed(3)\n parameters = {}\n L = len(layer_dims) # number of layers in the network\n\n for l in range(1, L):\n parameters['W' + str(l)] = np.random.randn(layer_dims[l], layer_dims[l-1])*0.01\n parameters['b' + str(l)] = np.zeros((layer_dims[l],1))\n \n assert(parameters['W' + str(l)].shape == (layer_dims[l], layer_dims[l-1]))\n assert(parameters['b' + str(l)].shape == (layer_dims[l], 1))\n\n \n return parameters","metadata":{"id":"6yvsz9EsqUT7","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"parameters = initialize_parameters_deep([5,4,3])\nprint(\"W1 = \" + str(parameters[\"W1\"]))\nprint(\"b1 = \" + str(parameters[\"b1\"]))\nprint(\"W2 = \" + str(parameters[\"W2\"]))\nprint(\"b2 = \" + str(parameters[\"b2\"]))","metadata":{"id":"HF6eZbZCqZof","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def linear_forward(A, W, b):\n \"\"\"\n Implement the linear part of a layer's forward propagation.\n\n Arguments:\n A -- activations from previous layer (or input data): (size of previous layer, number of examples)\n W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)\n b -- bias vector, numpy array of shape (size of the current layer, 1)\n\n Returns:\n Z -- the input of the activation function, also called pre-activation parameter \n cache -- a python tuple containing \"A\", \"W\" and \"b\" ; stored for computing the backward pass efficiently\n \"\"\"\n \n Z = np.dot(W, A)+b\n\n assert(Z.shape == (W.shape[0], A.shape[1]))\n cache = (A, W, b)\n \n return Z, cache","metadata":{"id":"U2s3ZwuIq4L4","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def linear_activation_forward(A_prev, W, b, activation):\n \"\"\"\n Implement the forward propagation for the LINEAR->ACTIVATION layer\n\n Arguments:\n A_prev -- activations from previous layer (or input data): (size of previous layer, number of examples)\n W -- weights matrix: numpy array of shape (size of current layer, size of previous layer)\n b -- bias vector, numpy array of shape (size of the current layer, 1)\n activation -- the activation to be used in this layer, stored as a text string: \"sigmoid\" or \"relu\"\n\n Returns:\n A -- the output of the activation function, also called the post-activation value \n cache -- a python tuple containing \"linear_cache\" and \"activation_cache\";\n stored for computing the backward pass efficiently\n \"\"\"\n \n if activation == \"sigmoid\":\n # Inputs: \"A_prev, W, b\". Outputs: \"A, activation_cache\".\n Z, linear_cache = linear_forward(A_prev, W, b)\n A, activation_cache = sigmoid(Z)\n \n elif activation == \"relu\":\n # Inputs: \"A_prev, W, b\". Outputs: \"A, activation_cache\".\n Z, linear_cache = linear_forward(A_prev, W, b)\n A, activation_cache = relu(Z)\n \n assert (A.shape == (W.shape[0], A_prev.shape[1]))\n cache = (linear_cache, activation_cache)\n\n return A, cache","metadata":{"id":"kNWTqx8prRYu","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def L_model_forward(X, parameters):\n \"\"\"\n Implement forward propagation for the [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID computation\n \n Arguments:\n X -- data, numpy array of shape (input size, number of examples)\n parameters -- output of initialize_parameters_deep()\n \n Returns:\n AL -- last post-activation value\n caches -- list of caches containing:\n every cache of linear_activation_forward() (there are L-1 of them, indexed from 0 to L-1)\n \"\"\"\n\n caches = []\n A = X\n L = len(parameters) // 2 # number of layers in the neural network\n \n # Implement [LINEAR -> RELU]*(L-1). Add \"cache\" to the \"caches\" list.\n for l in range(1, L):\n A_prev = A \n A, cache = linear_activation_forward(A_prev, parameters['W' + str(l)], parameters['b' + str(l)], \"relu\")\n caches.append(cache)\n \n # Implement LINEAR -> SIGMOID. Add \"cache\" to the \"caches\" list.\n AL, cache = linear_activation_forward(A, parameters['W' + str(L)], parameters['b' + str(L)], \"sigmoid\")\n caches.append(cache)\n \n assert(AL.shape == (1,X.shape[1]))\n \n return AL, caches","metadata":{"id":"Zx52BmKOrZIl","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def compute_cost(AL, Y):\n \"\"\"\n Implement the cost function defined by equation (7).\n\n Arguments:\n AL -- probability vector corresponding to your label predictions, shape (1, number of examples)\n Y -- true \"label\" vector (for example: containing 0 if non-cat, 1 if cat), shape (1, number of examples)\n\n Returns:\n cost -- cross-entropy cost\n \"\"\"\n \n m = Y.shape[1]\n\n # Compute loss from aL and y.\n cost = (-1/m)*np.sum(Y*np.log(AL)+(1-Y)*np.log(1-AL))\n \n cost = np.squeeze(cost) # To make sure your cost's shape is what we expect (e.g. this turns [[17]] into 17).\n assert(cost.shape == ())\n \n return cost","metadata":{"id":"TFWDF2acryOx","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def linear_backward(dZ, cache):\n \"\"\"\n Implement the linear portion of backward propagation for a single layer (layer l)\n\n Arguments:\n dZ -- Gradient of the cost with respect to the linear output (of current layer l)\n cache -- tuple of values (A_prev, W, b) coming from the forward propagation in the current layer\n\n Returns:\n dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev\n dW -- Gradient of the cost with respect to W (current layer l), same shape as W\n db -- Gradient of the cost with respect to b (current layer l), same shape as b\n \"\"\"\n A_prev, W, b = cache\n m = A_prev.shape[1]\n\n dW = (1/m)*np.dot(dZ, A_prev.T)\n db = (1/m)*np.sum(dZ, axis=1, keepdims=True)\n dA_prev = np.dot(W.T, dZ)\n \n assert (dA_prev.shape == A_prev.shape)\n assert (dW.shape == W.shape)\n assert (db.shape == b.shape)\n \n return dA_prev, dW, db","metadata":{"id":"mX2FGkULuyqg","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def linear_activation_backward(dA, cache, activation):\n \"\"\"\n Implement the backward propagation for the LINEAR->ACTIVATION layer.\n \n Arguments:\n dA -- post-activation gradient for current layer l \n cache -- tuple of values (linear_cache, activation_cache) we store for computing backward propagation efficiently\n activation -- the activation to be used in this layer, stored as a text string: \"sigmoid\" or \"relu\"\n \n Returns:\n dA_prev -- Gradient of the cost with respect to the activation (of the previous layer l-1), same shape as A_prev\n dW -- Gradient of the cost with respect to W (current layer l), same shape as W\n db -- Gradient of the cost with respect to b (current layer l), same shape as b\n \"\"\"\n linear_cache, activation_cache = cache\n \n if activation == \"relu\":\n dZ = relu_backward(dA, activation_cache)\n dA_prev, dW, db = linear_backward(dZ, linear_cache)\n \n elif activation == \"sigmoid\":\n dZ = sigmoid_backward(dA, activation_cache)\n dA_prev, dW, db = linear_backward(dZ, linear_cache)\n \n return dA_prev, dW, db","metadata":{"id":"GKEoO2y5u48J","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def L_model_backward(AL, Y, caches):\n \"\"\"\n Implement the backward propagation for the [LINEAR->RELU] * (L-1) -> LINEAR -> SIGMOID group\n \n Arguments:\n AL -- probability vector, output of the forward propagation (L_model_forward())\n Y -- true \"label\" vector (containing 0 if non-cat, 1 if cat)\n caches -- list of caches containing:\n every cache of linear_activation_forward() with \"relu\" (it's caches[l], for l in range(L-1) i.e l = 0...L-2)\n the cache of linear_activation_forward() with \"sigmoid\" (it's caches[L-1])\n \n Returns:\n grads -- A dictionary with the gradients\n grads[\"dA\" + str(l)] = ... \n grads[\"dW\" + str(l)] = ...\n grads[\"db\" + str(l)] = ... \n \"\"\"\n grads = {}\n L = len(caches) # the number of layers\n m = AL.shape[1]\n Y = Y.reshape(AL.shape) # after this line, Y is the same shape as AL\n \n # Initializing the backpropagation\n dAL = - (np.divide(Y, AL) - np.divide(1 - Y, 1 - AL))\n \n # Lth layer (SIGMOID -> LINEAR) gradients. Inputs: \"dAL, current_cache\". Outputs: \"grads[\"dAL-1\"], grads[\"dWL\"], grads[\"dbL\"]\n current_cache = caches[L-1]\n grads[\"dA\" + str(L-1)], grads[\"dW\" + str(L)], grads[\"db\" + str(L)] = linear_activation_backward(dAL, current_cache, \"sigmoid\")\n \n # Loop from l=L-2 to l=0\n for l in reversed(range(L-1)):\n # lth layer: (RELU -> LINEAR) gradients.\n # Inputs: \"grads[\"dA\" + str(l + 1)], current_cache\". Outputs: \"grads[\"dA\" + str(l)] , grads[\"dW\" + str(l + 1)] , grads[\"db\" + str(l + 1)] \n current_cache = caches[l]\n dA_prev_temp, dW_temp, db_temp = linear_activation_backward(grads[\"dA\"+str(l+1)], current_cache, \"relu\")\n grads[\"dA\" + str(l)] = dA_prev_temp\n grads[\"dW\" + str(l + 1)] = dW_temp\n grads[\"db\" + str(l + 1)] = db_temp\n\n return grads","metadata":{"id":"HSbVGItKu-Va","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def update_parameters(parameters, grads, learning_rate):\n \"\"\"\n Update parameters using gradient descent\n \n Arguments:\n parameters -- python dictionary containing your parameters \n grads -- python dictionary containing your gradients, output of L_model_backward\n \n Returns:\n parameters -- python dictionary containing your updated parameters \n parameters[\"W\" + str(l)] = ... \n parameters[\"b\" + str(l)] = ...\n \"\"\"\n \n L = len(parameters) // 2 # number of layers in the neural network\n\n # Update rule for each parameter. Use a for loop.\n for l in range(L):\n parameters[\"W\" + str(l+1)] = parameters[\"W\" + str(l+1)]- (learning_rate*grads[\"dW\" + str(l+1)])\n parameters[\"b\" + str(l+1)] = parameters[\"b\" + str(l+1)]- (learning_rate*grads[\"db\" + str(l+1)])\n return parameters","metadata":{"id":"xbkT1JpRvG2x","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"x_train=[]\ny_train=[]\nfor feature, label in train:\n x_train.append(feature)\n y_train.append(label)\n\nx_train = np.array(x_train)\ny_train = np.array(y_train).reshape(len(y_train),1)","metadata":{"id":"y8eQb92VwGIs","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# split into train test sets\ntrain_x_orig, test_x_orig, train_y, test_y = train_test_split(x_train, y_train, test_size=0.33)\ntrain_y, test_y = train_y.T, test_y.T\nprint(train_x_orig.shape, test_x_orig.shape, train_y.shape, test_y.shape)","metadata":{"id":"qUjyBJhxvcY7","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"(unique, counts) = np.unique(test_y, return_counts=True)\nfrequencies = np.asarray((unique, counts)).T\nfrequencies","metadata":{"id":"F0EJuaWqbOaS","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Explore your dataset \nm_train = train_x_orig.shape[0]\nnum_px = train_x_orig.shape[1]\nm_test = test_x_orig.shape[0]\n\nprint (\"Number of training examples: \" + str(m_train))\nprint (\"Number of testing examples: \" + str(m_test))\nprint (\"Each image is of size: (\" + str(num_px) + \", \" + str(num_px) + \", 3)\")\nprint (\"train_x_orig shape: \" + str(train_x_orig.shape))\nprint (\"train_y shape: \" + str(train_y.shape))\nprint (\"test_x_orig shape: \" + str(test_x_orig.shape))\nprint (\"test_y shape: \" + str(test_y.shape))","metadata":{"id":"WNbJBJV7vjU1","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"# Reshape the training and test examples \ntrain_x_flatten = train_x_orig.reshape(train_x_orig.shape[0], -1).T # The \"-1\" makes reshape flatten the remaining dimensions\ntest_x_flatten = test_x_orig.reshape(test_x_orig.shape[0], -1).T\n\n# Standardize data to have feature values between 0 and 1.\ntrain_x = train_x_flatten/255.\ntest_x = test_x_flatten/255.\n\nprint (\"train_x's shape: \" + str(train_x.shape))\nprint (\"test_x's shape: \" + str(test_x.shape))\n","metadata":{"id":"_n0hwCT3yXk5","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"### CONSTANTS DEFINING THE MODEL ####\nn_x = 49152 # num_px * num_px * 3\nn_h = 7\nn_y = 1\nlayers_dims = (n_x, n_h, n_y)","metadata":{"id":"21YHL4oCymrC","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef two_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):\n \"\"\"\n Implements a two-layer neural network: LINEAR->RELU->LINEAR->SIGMOID.\n \n Arguments:\n X -- input data, of shape (n_x, number of examples)\n Y -- true \"label\" vector (containing 1 if cat, 0 if non-cat), of shape (1, number of examples)\n layers_dims -- dimensions of the layers (n_x, n_h, n_y)\n num_iterations -- number of iterations of the optimization loop\n learning_rate -- learning rate of the gradient descent update rule\n print_cost -- If set to True, this will print the cost every 100 iterations \n \n Returns:\n parameters -- a dictionary containing W1, W2, b1, and b2\n \"\"\"\n \n np.random.seed(1)\n grads = {}\n costs = [] # to keep track of the cost\n m = X.shape[1] # number of examples\n (n_x, n_h, n_y) = layers_dims\n \n # Initialize parameters dictionary, by calling one of the functions you'd previously implemented\n parameters = initialize_parameters(n_x, n_h, n_y)\n \n # Get W1, b1, W2 and b2 from the dictionary parameters.\n W1 = parameters[\"W1\"]\n b1 = parameters[\"b1\"]\n W2 = parameters[\"W2\"]\n b2 = parameters[\"b2\"]\n \n # Loop (gradient descent)\n\n for i in range(0, num_iterations):\n\n # Forward propagation: LINEAR -> RELU -> LINEAR -> SIGMOID. Inputs: \"X, W1, b1, W2, b2\". Output: \"A1, cache1, A2, cache2\".\n A1, cache1 = linear_activation_forward(X, W1, b1, \"relu\")\n A2, cache2 = linear_activation_forward(A1, W2, b2, \"sigmoid\")\n \n # Compute cost\n cost = compute_cost(A2, Y)\n \n # Initializing backward propagation\n dA2 = - (np.divide(Y, A2) - np.divide(1 - Y, 1 - A2))\n \n # Backward propagation. Inputs: \"dA2, cache2, cache1\". Outputs: \"dA1, dW2, db2; also dA0 (not used), dW1, db1\".\n dA1, dW2, db2 = linear_activation_backward(dA2, cache2, \"sigmoid\")\n dA0, dW1, db1 = linear_activation_backward(dA1, cache1, \"relu\")\n \n # Set grads['dWl'] to dW1, grads['db1'] to db1, grads['dW2'] to dW2, grads['db2'] to db2\n grads['dW1'] = dW1\n grads['db1'] = db1\n grads['dW2'] = dW2\n grads['db2'] = db2\n \n # Update parameters.\n parameters = update_parameters(parameters, grads, learning_rate)\n\n # Retrieve W1, b1, W2, b2 from parameters\n W1 = parameters[\"W1\"]\n b1 = parameters[\"b1\"]\n W2 = parameters[\"W2\"]\n b2 = parameters[\"b2\"]\n \n # Print the cost every 100 training example\n if print_cost and i % 100 == 0:\n print(\"Cost after iteration {}: {}\".format(i, np.squeeze(cost)))\n if print_cost and i % 100 == 0:\n costs.append(cost)\n \n # plot the cost\n\n plt.plot(np.squeeze(costs))\n plt.ylabel('cost')\n plt.xlabel('iterations (per hundreds)')\n plt.title(\"Learning rate =\" + str(learning_rate))\n plt.show()\n \n return parameters","metadata":{"id":"KLSKnrSVy179","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"parameters = two_layer_model(train_x, train_y, layers_dims = (n_x, n_h, n_y), num_iterations = 2500, print_cost=True)","metadata":{"id":"Np9t9LXGzDxn","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def predict(X, y, parameters):\n \"\"\"\n This function is used to predict the results of a L-layer neural network.\n \n Arguments:\n X -- data set of examples you would like to label\n parameters -- parameters of the trained model\n \n Returns:\n p -- predictions for the given dataset X\n \"\"\"\n \n m = X.shape[1]\n n = len(parameters) // 2 # number of layers in the neural network\n p = np.zeros((1,m))\n \n # Forward propagation\n probas, caches = L_model_forward(X, parameters)\n\n \n # convert probas to 0/1 predictions\n for i in range(0, probas.shape[1]):\n if probas[0,i] > 0.5:\n p[0,i] = 1\n else:\n p[0,i] = 0\n \n #print results\n #print (\"predictions: \" + str(p))\n #print (\"true labels: \" + str(y))\n print(\"Accuracy: \" + str(np.sum((p == y)/m)))\n \n return p","metadata":{"id":"ZTVt_Uxz9IR9","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"\ndef print_mislabeled_images(classes, X, y, p):\n \"\"\"\n Plots images where predictions and truth were different.\n X -- dataset\n y -- true labels\n p -- predictions\n \"\"\"\n a = p + y\n mislabeled_indices = np.asarray(np.where(a == 1))\n plt.rcParams['figure.figsize'] = (40.0, 40.0) # set default size of plots\n num_images = len(mislabeled_indices[0])\n for i in range(num_images):\n index = mislabeled_indices[1][i]\n \n plt.subplot(2, num_images, i + 1)\n plt.imshow(X[:,index].reshape(64,64,3), interpolation='nearest')\n plt.axis('off')\n plt.title(\"Prediction: \" + classes[int(p[0,index])].decode(\"utf-8\") + \" \\n Class: \" + classes[y[0,index]].decode(\"utf-8\"))","metadata":{"id":"pQ3G0D7u9Led","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions_train = predict(train_x, train_y, parameters)","metadata":{"id":"uj9PLPhm5Dsq","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"predictions_test = predict(test_x, test_y, parameters)","metadata":{"id":"askJXiIo5H_M","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"layers_dims = [49152, 20, 7, 5, 1] # 4-layer model","metadata":{"id":"V2w6dpcE5Ntd","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"def L_layer_model(X, Y, layers_dims, learning_rate = 0.0075, num_iterations = 3000, print_cost=False):#lr was 0.009\n \"\"\"\n Implements a L-layer neural network: [LINEAR->RELU]*(L-1)->LINEAR->SIGMOID.\n \n Arguments:\n X -- data, numpy array of shape (num_px * num_px * 3, number of examples)\n Y -- true \"label\" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples)\n layers_dims -- list containing the input size and each layer size, of length (number of layers + 1).\n learning_rate -- learning rate of the gradient descent update rule\n num_iterations -- number of iterations of the optimization loop\n print_cost -- if True, it prints the cost every 100 steps\n \n Returns:\n parameters -- parameters learnt by the model. They can then be used to predict.\n \"\"\"\n\n np.random.seed(1)\n costs = [] # keep track of cost\n \n # Parameters initialization. (≈ 1 line of code)\n parameters = initialize_parameters_deep(layers_dims)\n \n # Loop (gradient descent)\n for i in range(0, num_iterations):\n\n # Forward propagation: [LINEAR -> RELU]*(L-1) -> LINEAR -> SIGMOID.\n AL, caches = L_model_forward(X, parameters)\n \n # Compute cost.\n cost = compute_cost(AL, Y)\n \n # Backward propagation.\n grads = L_model_backward(AL, Y, caches)\n \n # Update parameters.\n parameters = update_parameters(parameters, grads, learning_rate)\n \n # Print the cost every 100 training example\n if print_cost and i % 100 == 0:\n print (\"Cost after iteration %i: %f\" %(i, cost))\n if print_cost and i % 100 == 0:\n costs.append(cost)\n \n # plot the cost\n plt.plot(np.squeeze(costs))\n plt.ylabel('cost')\n plt.xlabel('iterations (per hundreds)')\n plt.title(\"Learning rate =\" + str(learning_rate))\n plt.show()\n \n return parameters","metadata":{"id":"ZvwqPT8r5XsW","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"parameters = L_layer_model(train_x, train_y, layers_dims, num_iterations = 2500, print_cost = True)","metadata":{"id":"9nLaESYI5aqt","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_train = predict(train_x, train_y, parameters)","metadata":{"id":"mOmskv-o5dML","trusted":true},"execution_count":null,"outputs":[]},{"cell_type":"code","source":"pred_test = predict(test_x, test_y, parameters)","metadata":{"id":"OUEkOEGZ5fGj","trusted":true},"execution_count":null,"outputs":[]}]}