1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 | # -*- coding: utf-8 -*- """ML_Day04_shallow_neural-net.ipynb Automatically generated by Colaboratory. Original file is located at """ from google.colab import drive drive.mount('/gdrive') PATH = "/gdrive/My Drive/Colab Notebooks/resources/" """# Planar data classification with one hidden layer Welcome to your week 3 programming assignment. It's time to build your first neural network, which will have a hidden layer. You will see a big difference between this model and the one you implemented using logistic regression. def layer_sizes(X, Y): """ Arguments: X -- input dataset of shape (input size, number of examples) Y -- labels of shape (output size, number of examples) Returns: n_x -- the size of the input layer n_h -- the size of the hidden layer n_y -- the size of the output layer """ ### START CODE HERE ### (≈ 3 lines of code) n_x = X.shape[0] n_h = 4 n_y = Y.shape[0] ### END CODE HERE ### return (n_x, n_h, n_y) def initialize_parameters(n_x, n_h, n_y): """ Argument: n_x -- size of the input layer n_h -- size of the hidden layer n_y -- size of the output layer Returns: params -- python dictionary containing your parameters: W1 -- weight matrix of shape (n_h, n_x) b1 -- bias vector of shape (n_h, 1) W2 -- weight matrix of shape (n_y, n_h) b2 -- bias vector of shape (n_y, 1) """ np.random.seed(2) # we set up a seed so that your output matches ours although the initialization is random. ### START CODE HERE ### (≈ 4 lines of code) print(type(n_h), type(n_x)) W1 = np.random.randn(n_h,n_x) * 0.01 b1 = np.zeros((n_h,1)) W2 = np.random.randn(n_y, n_h) * 0.01 b2 = np.zeros((n_y,1)) ### END CODE HERE ### assert (W1.shape == (n_h, n_x)) assert (b1.shape == (n_h, 1)) assert (W2.shape == (n_y, n_h)) assert (b2.shape == (n_y, 1)) parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2} return parameters def forward_propagation(X, parameters): """ Argument: X -- input data of size (n_x, m) parameters -- python dictionary containing your parameters (output of initialization function) Returns: A2 -- The sigmoid output of the second activation cache -- a dictionary containing "Z1", "A1", "Z2" and "A2" """ # Retrieve each parameter from the dictionary "parameters" ### START CODE HERE ### (≈ 4 lines of code) W1 = parameters['W1'] b1 = parameters['b1'] W2 = parameters['W2'] b2 = parameters['b2'] ### END CODE HERE ### # Implement Forward Propagation to calculate A2 (probabilities) ### START CODE HERE ### (≈ 4 lines of code) Z1 = W1 @ X + b1 A1 = np.tanh(Z1) Z2 = W2 @ A1 + b2 A2 = sigmoid(Z2) ### END CODE HERE ### assert(A2.shape == (1, X.shape[1])) cache = {"Z1": Z1, "A1": A1, "Z2": Z2, "A2": A2} return A2, cache # GRADED FUNCTION: compute_cost def compute_cost(A2, Y, parameters): """ Computes the cross-entropy cost given in equation (13) Arguments: A2 -- The sigmoid output of the second activation, of shape (1, number of examples) Y -- "true" labels vector of shape (1, number of examples) parameters -- python dictionary containing your parameters W1, b1, W2 and b2 [Note that the parameters argument is not used in this function, but the auto-grader currently expects this parameter. Future version of this notebook will fix both the notebook and the auto-grader so that `parameters` is not needed. For now, please include `parameters` in the function signature, and also when invoking this function.] Returns: cost -- cross-entropy cost given equation (13) """ m = Y.shape[1] # number of example # Compute the cross-entropy cost ### START CODE HERE ### (≈ 2 lines of code) logprobs = np.multiply(np.log(A2),Y) cost = - np.sum(logprobs) ### END CODE HERE ### cost = float(np.squeeze(cost)) # makes sure cost is the dimension we expect. # E.g., turns [[17]] into 17 assert(isinstance(cost, float)) return cost # GRADED FUNCTION: backward_propagation def backward_propagation(parameters, cache, X, Y): """ Implement the backward propagation using the instructions above. Arguments: parameters -- python dictionary containing our parameters cache -- a dictionary containing "Z1", "A1", "Z2" and "A2". X -- input data of shape (2, number of examples) Y -- "true" labels vector of shape (1, number of examples) Returns: grads -- python dictionary containing your gradients with respect to different parameters """ m = X.shape[1] # First, retrieve W1 and W2 from the dictionary "parameters". ### START CODE HERE ### (≈ 2 lines of code) W1 = parameters['W1'] W2 = parameters['W2'] ### END CODE HERE ### # Retrieve also A1 and A2 from dictionary "cache". ### START CODE HERE ### (≈ 2 lines of code) A1 = cache['A1'] A2 = cache['A2'] ### END CODE HERE ### # Backward propagation: calculate dW1, db1, dW2, db2. ### START CODE HERE ### (≈ 6 lines of code, corresponding to 6 equations on slide above) dZ2 = A2 - Y dW2 = dZ2 @ A1.T * (1 / m) db2 = np.sum(dZ2 , axis = 1 , keepdims = True) * ( 1 / m ) dZ1 = W2.T @ dZ2 * (1 - np.power(A1, 2)) dW1 = dZ1 @ X.T * ( 1 / m) db1 = np.sum(dZ1, axis = 1 , keepdims = True) * ( 1 / m) ### END CODE HERE ### grads = {"dW1": dW1, "db1": db1, "dW2": dW2, "db2": db2} return grads # GRADED FUNCTION: update_parameters def update_parameters(parameters, grads, learning_rate = 1.9): """ Updates parameters using the gradient descent update rule given above Arguments: parameters -- python dictionary containing your parameters grads -- python dictionary containing your gradients Returns: parameters -- python dictionary containing your updated parameters """ # Retrieve each parameter from the dictionary "parameters" ### START CODE HERE ### (≈ 4 lines of code) W1 = parameters['W1'] b1 = parameters['b1'] W2 = parameters['W2'] b2 = parameters['b2'] ### END CODE HERE ### # Retrieve each gradient from the dictionary "grads" ### START CODE HERE ### (≈ 4 lines of code) dW1 = grads['dW1'] db1 = grads['db1'] dW2 = grads['dW2'] db2 = grads['db2'] ## END CODE HERE ### # Update rule for each parameter ### START CODE HERE ### (≈ 4 lines of code) W1 = W1 - learning_rate * dW1 b1 = b1 - learning_rate * db1 W2 = W2 - learning_rate * dW2 b2 = b2 - learning_rate * db2 ### END CODE HERE ### parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2} return parameters # GRADED FUNCTION: nn_model def nn_model(X, Y, n_h, num_iterations = 10000, print_cost=False): """ Arguments: X -- dataset of shape (2, number of examples) Y -- labels of shape (1, number of examples) n_h -- size of the hidden layer num_iterations -- Number of iterations in gradient descent loop print_cost -- if True, print the cost every 1000 iterations Returns: parameters -- parameters learnt by the model. They can then be used to predict. """ np.random.seed(3) n_x = layer_sizes(X, Y)[0] n_y = layer_sizes(X, Y)[2] # Initialize parameters ### START CODE HERE ### (≈ 1 line of code) parameters = initialize_parameters(n_h = n_h, n_x = n_x, n_y = n_y) ### END CODE HERE ### # Loop (gradient descent) for i in range(0, num_iterations): ### START CODE HERE ### (≈ 4 lines of code) # Forward propagation. Inputs: "X, parameters". Outputs: "A2, cache". A2, cache = forward_propagation(X, parameters) # Cost function. Inputs: "A2, Y, parameters". Outputs: "cost". cost = compute_cost(A2, Y, parameters) # Backpropagation. Inputs: "parameters, cache, X, Y". Outputs: "grads". grads = backward_propagation(parameters, cache, X, Y) # Gradient descent parameter update. Inputs: "parameters, grads". Outputs: "parameters". parameters = update_parameters(parameters, grads, learning_rate = 1.5) ### END CODE HERE ### # Print the cost every 1000 iterations if print_cost and i % 1000 == 0: print ("Cost after iteration %i: %f" %(i, cost)) return parameters # GRADED FUNCTION: predict def predict(parameters, X): """ Using the learned parameters, predicts a class for each example in X Arguments: parameters -- python dictionary containing your parameters X -- input data of size (n_x, m) Returns predictions -- vector of predictions of our model (red: 0 / blue: 1) """ # Computes probabilities using forward propagation, and classifies to 0/1 using 0.5 as the threshold. ### START CODE HERE ### (≈ 2 lines of code) A2, cache = forward_propagation(parameters = parameters, X = X) predictions = np.where( A2 > 0.5 , 1 , 0 ) ### END CODE HERE ### return predictions | cs |
출처 및 참고자료 : Andrew Ng / Neural Networks and Deep Learning Week 3. programming assignment
'Python Library > Machine Learning' 카테고리의 다른 글
CUDA error: no kernel image is available for execution on the device 에러 해결 (0) | 2021.05.18 |
---|---|
[DNN] Day 03_Logistic_Classification_With_Vectorized_Algorithm (0) | 2019.07.28 |
[CNN] Day 03_vision03_Multiclass_Classification (0) | 2019.07.27 |
[CNN] Day 03_vision02_Model_Transfer_With_Augmentation (0) | 2019.07.27 |
[CNN] Day 02_vision01_basicOfCNN (0) | 2019.07.27 |