第二课第三周 deeplaerning.ai编程实现
来源:互联网 发布:战争游戏红龙 知乎 编辑:程序博客网 时间:2024/06/14 10:46
前面该课程关于tensorflow的具体函数填写已经不再细说,在本程序中,仅仅包含的是第二个关于用tensorflow实现一个图片手势判断的三层多分类神经网络,该次代码分为两个部分,第一部分是原有代码,存在文件tf_utils.py中,第二部分代码时编程作业的实现。
第一部分代码如下:
import h5pyimport numpy as npimport tensorflow as tfimport mathdef load_dataset(): train_dataset = h5py.File('datasets/train_signs.h5', "r") train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels test_dataset = h5py.File('datasets/test_signs.h5', "r") test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels classes = np.array(test_dataset["list_classes"][:]) # the list of classes train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0])) test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0])) return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classesdef random_mini_batches(X, Y, mini_batch_size = 64, seed = 0): """ Creates a list of random minibatches from (X, Y) Arguments: X -- input data, of shape (input size, number of examples) Y -- true "label" vector (containing 0 if cat, 1 if non-cat), of shape (1, number of examples) mini_batch_size - size of the mini-batches, integer seed -- this is only for the purpose of grading, so that you're "random minibatches are the same as ours. Returns: mini_batches -- list of synchronous (mini_batch_X, mini_batch_Y) """ m = X.shape[1] # number of training examples mini_batches = [] np.random.seed(seed) # Step 1: Shuffle (X, Y) permutation = list(np.random.permutation(m)) shuffled_X = X[:, permutation] shuffled_Y = Y[:, permutation].reshape((Y.shape[0],m)) # Step 2: Partition (shuffled_X, shuffled_Y). Minus the end case. num_complete_minibatches = math.floor(m/mini_batch_size) # number of mini batches of size mini_batch_size in your partitionning for k in range(0, num_complete_minibatches): mini_batch_X = shuffled_X[:, k * mini_batch_size : k * mini_batch_size + mini_batch_size] mini_batch_Y = shuffled_Y[:, k * mini_batch_size : k * mini_batch_size + mini_batch_size] mini_batch = (mini_batch_X, mini_batch_Y) mini_batches.append(mini_batch) # Handling the end case (last mini-batch < mini_batch_size) if m % mini_batch_size != 0: mini_batch_X = shuffled_X[:, num_complete_minibatches * mini_batch_size : m] mini_batch_Y = shuffled_Y[:, num_complete_minibatches * mini_batch_size : m] mini_batch = (mini_batch_X, mini_batch_Y) mini_batches.append(mini_batch) return mini_batchesdef convert_to_one_hot(Y, C): Y = np.eye(C)[Y.reshape(-1)].T return Ydef predict(X, parameters): W1 = tf.convert_to_tensor(parameters["W1"]) b1 = tf.convert_to_tensor(parameters["b1"]) W2 = tf.convert_to_tensor(parameters["W2"]) b2 = tf.convert_to_tensor(parameters["b2"]) W3 = tf.convert_to_tensor(parameters["W3"]) b3 = tf.convert_to_tensor(parameters["b3"]) params = {"W1": W1, "b1": b1, "W2": W2, "b2": b2, "W3": W3, "b3": b3} x = tf.placeholder("float", [12288, 1]) z3 = forward_propagation_for_predict(x, params) p = tf.argmax(z3) sess = tf.Session() prediction = sess.run(p, feed_dict = {x: X}) return predictiondef forward_propagation_for_predict(X, parameters): """ Implements the forward propagation for the model: LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAX Arguments: X -- input dataset placeholder, of shape (input size, number of examples) parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3" the shapes are given in initialize_parameters Returns: Z3 -- the output of the last LINEAR unit """ # Retrieve the parameters from the dictionary "parameters" W1 = parameters['W1'] b1 = parameters['b1'] W2 = parameters['W2'] b2 = parameters['b2'] W3 = parameters['W3'] b3 = parameters['b3'] # Numpy Equivalents: Z1 = tf.add(tf.matmul(W1, X), b1) # Z1 = np.dot(W1, X) + b1 A1 = tf.nn.relu(Z1) # A1 = relu(Z1) Z2 = tf.add(tf.matmul(W2, A1), b2) # Z2 = np.dot(W2, a1) + b2 A2 = tf.nn.relu(Z2) # A2 = relu(Z2) Z3 = tf.add(tf.matmul(W3, A2), b3) # Z3 = np.dot(W3,Z2) + b3 return Z3
第二部分代码如下:
import mathimport numpy as npimport h5pyimport matplotlib.pyplot as pltimport tensorflow as tffrom tensorflow.python.framework import opsfrom tf_utils import load_dataset, random_mini_batches, convert_to_one_hot, predict#%matplotlib inlinenp.random.seed(1)X_train_orig, Y_train_orig, X_test_orig, Y_test_orig, classes = load_dataset()# Flatten the training and test imagesX_train_flatten = X_train_orig.reshape(X_train_orig.shape[0], -1).TX_test_flatten = X_test_orig.reshape(X_test_orig.shape[0], -1).T# Normalize image vectorsx_train = X_train_flatten/255.x_test = X_test_flatten/255.# Convert training and test labels to one hot matricesy_train = convert_to_one_hot(Y_train_orig, 6)y_test = convert_to_one_hot(Y_test_orig, 6)print ("number of training examples = " + str(x_train.shape[1]))print ("number of test examples = " + str(x_test.shape[1]))print ("X_train shape: " + str(x_train.shape))print ("Y_train shape: " + str(y_train.shape))print ("X_test shape: " + str(x_test.shape))print ("Y_test shape: " + str(y_test.shape))def create_placeholders(n_x, n_y): """ Creates the placeholders for the tensorflow session. Arguments: n_x -- scalar, size of an image vector (num_px * num_px = 64 * 64 * 3 = 12288) n_y -- scalar, number of classes (from 0 to 5, so -> 6) Returns: X -- placeholder for the data input, of shape [n_x, None] and dtype "float" Y -- placeholder for the input labels, of shape [n_y, None] and dtype "float" Tips: - You will use None because it let's us be flexible on the number of examples you will for the placeholders. In fact, the number of examples during test/train is different. """ ### START CODE HERE ### (approx. 2 lines) X = tf.placeholder(tf.float32,[n_x,None]) Y = tf.placeholder(tf.float32,[n_y,None]) ### END CODE HERE ### return X, Ydef initialize_parameters(): """ Initializes parameters to build a neural network with tensorflow. The shapes are: W1 : [25, 12288] b1 : [25, 1] W2 : [12, 25] b2 : [12, 1] W3 : [6, 12] b3 : [6, 1] Returns: parameters -- a dictionary of tensors containing W1, b1, W2, b2, W3, b3 """ tf.set_random_seed(1) # so that your "random" numbers match ours ### START CODE HERE ### (approx. 6 lines of code) #W1 = tf.get_variable("W1", [25,12288], initializer = tf.contrib.layers.xavier_initializer(seed = 1)) W1 = tf.get_variable('W1', [25,12288], initializer = tf.contrib.layers.xavier_initializer(seed = 1)) b1 = tf.get_variable("b1",[25,1],initializer=tf.zeros_initializer()) W2 = tf.get_variable("W2",[12,25],initializer=tf.contrib.layers.xavier_initializer(seed=1)) b2 = tf.get_variable("b2",[12,1],initializer=tf.zeros_initializer()) W3 = tf.get_variable("W3",[6,12],initializer=tf.contrib.layers.xavier_initializer(seed=1)) b3 = tf.get_variable("b3",[6,1],initializer=tf.zeros_initializer()) ### END CODE HERE ### parameters = {"W1": W1, "b1": b1, "W2": W2, "b2": b2, "W3": W3, "b3": b3} return parameters# GRADED FUNCTION: forward_propagationdef forward_propagation(X, parameters): """ Implements the forward propagation for the model: LINEAR -> RELU -> LINEAR -> RELU -> LINEAR -> SOFTMAX Arguments: X -- input dataset placeholder, of shape (input size, number of examples) parameters -- python dictionary containing your parameters "W1", "b1", "W2", "b2", "W3", "b3" the shapes are given in initialize_parameters Returns: Z3 -- the output of the last LINEAR unit """ # Retrieve the parameters from the dictionary "parameters" W1 = parameters['W1'] b1 = parameters['b1'] W2 = parameters['W2'] b2 = parameters['b2'] W3 = parameters['W3'] b3 = parameters['b3'] ### START CODE HERE ### (approx. 5 lines) # Numpy Equivalents: Z1 = tf.add(tf.matmul(W1,X),b1) # Z1 = np.dot(W1, X) + b1 A1 = tf.nn.relu(Z1) # A1 = relu(Z1) Z2 = tf.add(tf.matmul(W2,A1),b2) # Z2 = np.dot(W2, a1) + b2 A2 = tf.nn.relu(Z2) # A2 = relu(Z2) Z3 = tf.add(tf.matmul(W3,A2),b3) # Z3 = np.dot(W3,Z2) + b3 ### END CODE HERE ### return Z3def compute_cost(Z3, Y): """ Computes the cost Arguments: Z3 -- output of forward propagation (output of the last LINEAR unit), of shape (6, number of examples) Y -- "true" labels vector placeholder, same shape as Z3 Returns: cost - Tensor of the cost function """ # to fit the tensorflow requirement for tf.nn.softmax_cross_entropy_with_logits(...,...) 转置 logits = tf.transpose(Z3) #m * nL(num of classes ) [batch_size num_classes] labels = tf.transpose(Y) #m * nL( num of classes) [batch_size num_classes] ### START CODE HERE ### (1 line of code) cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=logits,labels=labels)) ### END CODE HERE ### return costdef model(X_train, Y_train, X_test, Y_test, learning_rate = 0.0001, num_epochs = 1500, minibatch_size = 32, print_cost = True): """ Implements a three-layer tensorflow neural network: LINEAR->RELU->LINEAR->RELU->LINEAR->SOFTMAX. Arguments: X_train -- training set, of shape (input size = 12288, number of training examples = 1080) Y_train -- test set, of shape (output size = 6, number of training examples = 1080) X_test -- training set, of shape (input size = 12288, number of training examples = 120) Y_test -- test set, of shape (output size = 6, number of test examples = 120) learning_rate -- learning rate of the optimization num_epochs -- number of epochs of the optimization loop minibatch_size -- size of a minibatch print_cost -- True to print the cost every 100 epochs Returns: parameters -- parameters learnt by the model. They can then be used to predict. """ ops.reset_default_graph() # to be able to rerun the model without overwriting tf variables tf.set_random_seed(1) # to keep consistent results seed = 3 # to keep consistent results (n_x, m) = X_train.shape # (n_x: input size, m : number of examples in the train set) n_y = Y_train.shape[0] # n_y : output size costs = [] # To keep track of the cost # Create Placeholders of shape (n_x, n_y) ### START CODE HERE ### (1 line) X, Y = create_placeholders(n_x, n_y) #mini_batch = tf.placeholder([n_x,n_y]) ### END CODE HERE ### # Initialize parameters ### START CODE HERE ### (1 line) parameters = initialize_parameters() ### END CODE HERE ### # Forward propagation: Build the forward propagation in the tensorflow graph ### START CODE HERE ### (1 line) Z3 = forward_propagation(X,parameters) ### END CODE HERE ### # Cost function: Add cost function to tensorflow graph ### START CODE HERE ### (1 line) cost = compute_cost(Z3,Y) ### END CODE HERE ### # Backpropagation: Define the tensorflow optimizer. Use an AdamOptimizer. ### START CODE HERE ### (1 line) optimizer = tf.train.AdamOptimizer(learning_rate).minimize(cost) ### END CODE HERE ### # Initialize all the variables init = tf.global_variables_initializer() # Start the session to compute the tensorflow graph with tf.Session() as sess: # Run the initialization sess.run(init) # Do the training loop for epoch in range(num_epochs): epoch_cost = 0. # Defines a cost related to an epoch num_minibatches = int(m / minibatch_size) # number of minibatches of size minibatch_size in the train set seed = seed + 1 minibatches = random_mini_batches(X_train, Y_train, minibatch_size, seed) for minibatch in minibatches: # Select a minibatch (minibatch_X, minibatch_Y) = minibatch # IMPORTANT: The line that runs the graph on a minibatch. # Run the session to execute the "optimizer" and the "cost", the feedict should contain a minibatch for (X,Y). ### START CODE HERE ### (1 line) _ , minibatch_cost = sess.run([optimizer,cost],feed_dict={X:minibatch_X,Y:minibatch_Y}) ### END CODE HERE ### epoch_cost += minibatch_cost / num_minibatches # Print the cost every epoch if print_cost == True and epoch % 100 == 0: print ("Cost after epoch %i: %f" % (epoch, epoch_cost)) if print_cost == True and epoch % 5 == 0: costs.append(epoch_cost) # plot the cost plt.plot(np.squeeze(costs)) plt.ylabel('cost') plt.xlabel('iterations (per tens)') plt.title("Learning rate =" + str(learning_rate)) plt.show() # lets save the parameters in a variable parameters = sess.run(parameters) print ("Parameters have been trained!") # Calculate the correct predictions correct_prediction = tf.equal(tf.argmax(Z3), tf.argmax(Y)) # Calculate accuracy on the test set accuracy = tf.reduce_mean(tf.cast(correct_prediction, "float")) print ("Train Accuracy:", accuracy.eval({X: X_train, Y: Y_train})) print ("Test Accuracy:", accuracy.eval({X: X_test, Y: Y_test})) return parametersparameters = model(x_train, y_train, x_test, y_test)
阅读全文
0 0
- 第二课第三周 deeplaerning.ai编程实现
- 第三周第二课
- Coursera 深度学习 deep learning.ai 吴恩达 第三课 结构化机器学习项目 第二周 测试题目 Autonomous driving
- deelplearning.ai 第二课第二周作业代码
- deeplearning.ai 第四课第二周 resnet 50层神经网络实现
- 第二节课第三周
- deeplearning.ai 第四课第二周,keras导航
- [原创][Python 技术培训] 第三周讲义.网络编程 (第二版)
- 第三周第二课--线性表
- Coursera 深度学习 deep learning.ai 吴恩达 神经网络和深度学习 第一课 第二周 编程作业 Python Basics with Numpy
- 第三周第二项
- 第三周第二章
- 第三周第二天
- 第三周第二节
- 人工智能(AI)第二节课总结
- Coursera 吴恩达 Deep Learning 第二课 改善神经网络 Improving Deep Neural Networks 第三周 编程作业代码 Tensorflow Tutorial
- 北大AI公开课 第二讲 嵌入式人工智能
- 【deeplearning.ai笔记第二课】2.4 batch normalization
- Apache Commons Text示例
- Jupyter Notebook
- android的特殊文字与Titanic的特效
- 数据结构实验之查找六:顺序查找
- 第十五周项目1
- 第二课第三周 deeplaerning.ai编程实现
- Python入门学习小记
- WIN7 +Python2.7.14 + pip + Djanggo1.9
- Spark 以及 spark streaming 核心原理及实践
- pwnable.kr
- [二维区间DP?] Atcoder ARC004E. Salvage Robots
- C语言中的堆和栈
- 字节缓冲流
- Codeforces Round #450 (Div. 2) A-C题解