企业🤖AI智能体构建引擎,智能编排和调试,一键部署,支持私有化部署方案 广告
# 实现单元测试 测试代码可以加快原型设计速度,提高调试效率,加快更改速度,并且可以更轻松地共享代码。在 TensorFlow 中有许多简单的方法可以实现单元测试,我们将在本文中介绍它们。 ## 做好准备 在编写 TensorFlow 模型时,有助于进行单元测试以检查程序的功能。这有助于我们,因为当我们想要对程序单元进行更改时,测试将确保这些更改不会以未知方式破坏模型。在这个秘籍中,我们将创建一个依赖于`MNIST`数据的简单 CNN 网络。有了它,我们将实现三种不同类型的单元测试来说明如何在 TensorFlow 中编写它们。 > 请注意,Python 有一个很棒的测试库,名为 Nose。 TensorFlow 还具有内置测试功能,我们将在其中查看,这样可以更轻松地测试 Tensor 对象的值,而无需评估会话中的值。 1. 首先,我们需要加载必要的库并格式化数据,如下所示: ```py import sys import numpy as np import tensorflow as tf from tensorflow.python.framework import ops ops.reset_default_graph() # Start a graph session sess = tf.Session() # Load data data_dir = 'temp' mnist = tf.keras.datasets.mnist (train_xdata, train_labels), (test_xdata, test_labels) = mnist.load_data() train_xdata = train_xdata / 255.0 test_xdata = test_xdata / 255.0 # Set model parameters batch_size = 100 learning_rate = 0.005 evaluation_size = 100 image_width = train_xdata[0].shape[0] image_height = train_xdata[0].shape[1] target_size = max(train_labels) + 1 num_channels = 1 # greyscale = 1 channel generations = 100 eval_every = 5 conv1_features = 25 conv2_features = 50 max_pool_size1 = 2 # NxN window for 1st max pool layer max_pool_size2 = 2 # NxN window for 2nd max pool layer fully_connected_size1 = 100 dropout_prob = 0.75 ``` 1. 然后,我们需要声明我们的占位符,变量和模型公式,如下所示: ```py # Declare model placeholders x_input_shape = (batch_size, image_width, image_height, num_channels) x_input = tf.placeholder(tf.float32, shape=x_input_shape) y_target = tf.placeholder(tf.int32, shape=(batch_size)) eval_input_shape = (evaluation_size, image_width, image_height, num_channels) eval_input = tf.placeholder(tf.float32, shape=eval_input_shape) eval_target = tf.placeholder(tf.int32, shape=(evaluation_size)) dropout = tf.placeholder(tf.float32, shape=()) # Declare model parameters conv1_weight = tf.Variable(tf.truncated_normal([4, 4, num_channels, conv1_features], stddev=0.1, dtype=tf.float32)) conv1_bias = tf.Variable(tf.zeros([conv1_features], dtype=tf.float32)) conv2_weight = tf.Variable(tf.truncated_normal([4, 4, conv1_features, conv2_features], stddev=0.1, dtype=tf.float32)) conv2_bias = tf.Variable(tf.zeros([conv2_features], dtype=tf.float32)) # fully connected variables resulting_width = image_width // (max_pool_size1 * max_pool_size2) resulting_height = image_height // (max_pool_size1 * max_pool_size2) full1_input_size = resulting_width * resulting_height * conv2_features full1_weight = tf.Variable(tf.truncated_normal([full1_input_size, fully_connected_size1], stddev=0.1, dtype=tf.float32)) full1_bias = tf.Variable(tf.truncated_normal([fully_connected_size1], stddev=0.1, dtype=tf.float32)) full2_weight = tf.Variable(tf.truncated_normal([fully_connected_size1, target_size], stddev=0.1, dtype=tf.float32)) full2_bias = tf.Variable(tf.truncated_normal([target_size], stddev=0.1, dtype=tf.float32)) # Initialize Model Operations def my_conv_net(input_data): # First Conv-ReLU-MaxPool Layer conv1 = tf.nn.conv2d(input_data, conv1_weight, strides=[1, 1, 1, 1], padding='SAME') relu1 = tf.nn.relu(tf.nn.bias_add(conv1, conv1_bias)) max_pool1 = tf.nn.max_pool(relu1, ksize=[1, max_pool_size1, max_pool_size1, 1], strides=[1, max_pool_size1, max_pool_size1, 1], padding='SAME') # Second Conv-ReLU-MaxPool Layer conv2 = tf.nn.conv2d(max_pool1, conv2_weight, strides=[1, 1, 1, 1], padding='SAME') relu2 = tf.nn.relu(tf.nn.bias_add(conv2, conv2_bias)) max_pool2 = tf.nn.max_pool(relu2, ksize=[1, max_pool_size2, max_pool_size2, 1], strides=[1, max_pool_size2, max_pool_size2, 1], padding='SAME') # Transform Output into a 1xN layer for next fully connected layer final_conv_shape = max_pool2.get_shape().as_list() final_shape = final_conv_shape[1] * final_conv_shape[2] * final_conv_shape[3] flat_output = tf.reshape(max_pool2, [final_conv_shape[0], final_shape]) # First Fully Connected Layer fully_connected1 = tf.nn.relu(tf.add(tf.matmul(flat_output, full1_weight), full1_bias)) # Second Fully Connected Layer final_model_output = tf.add(tf.matmul(fully_connected1, full2_weight), full2_bias) # Add dropout final_model_output = tf.nn.dropout(final_model_output, dropout) return final_model_output model_output = my_conv_net(x_input) test_model_output = my_conv_net(eval_input) ``` 1. 接下来,我们创建我们的损失函数以及我们的预测和精确操作。然后,我们初始化以下模型变量: ```py # Declare Loss Function (softmax cross entropy) loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(model_output, y_target)) # Create a prediction function prediction = tf.nn.softmax(model_output) test_prediction = tf.nn.softmax(test_model_output) # Create accuracy function def get_accuracy(logits, targets): batch_predictions = np.argmax(logits, axis=1) num_correct = np.sum(np.equal(batch_predictions, targets)) return 100\. * num_correct/batch_predictions.shape[0] # Create an optimizer my_optimizer = tf.train.MomentumOptimizer(learning_rate, 0.9) train_step = my_optimizer.minimize(loss) # Initialize Variables init = tf.global_variables_initializer() sess.run(init) ``` 1. 对于我们的第一个单元测试,我们使用类`tf.test.TestCase`并创建一种方法来测试占位符(或变量)的值。对于此测试用例,我们确保损失概率(用于保持)大于`0.25`,因此模型不会更改为尝试训练超过 75%的损失,如下所示: ```py # Check values of tensors! class DropOutTest(tf.test.TestCase): # Make sure that we don't drop too much def dropout_greaterthan(self): with self.test_session(): self.assertGreater(dropout.eval(), 0.25) ``` 1. 接下来,我们需要测试我们的`accuracy`函数是否按预期运行。为此,我们创建一个概率样本数组和我们期望的样本,然后确保测试精度返回 100%,如下所示: ```py # Test accuracy function class AccuracyTest(tf.test.TestCase): # Make sure accuracy function behaves correctly def accuracy_exact_test(self): with self.test_session(): test_preds = [[0.9, 0.1],[0.01, 0.99]] test_targets = [0, 1] test_acc = get_accuracy(test_preds, test_targets) self.assertEqual(test_acc.eval(), 100.) ``` 1. 我们还可以确保 Tensor 对象是我们期望的形状。要通过`target_size`测试模型输出是`batch_size`的预期形状,请输入以下代码: ```py # Test tensorshape class ShapeTest(tf.test.TestCase): # Make sure our model output is size [batch_size, num_classes] def output_shape_test(self): with self.test_session(): numpy_array = np.ones([batch_size, target_size]) self.assertShapeEqual(numpy_array, model_output) ``` 1. 现在我们需要在脚本中使用`main()`函数告诉 TensorFlow 我们正在运行哪个应用。脚本如下: ```py def main(argv): # Start training loop train_loss = [] train_acc = [] test_acc = [] for i in range(generations): rand_index = np.random.choice(len(train_xdata), size=batch_size) rand_x = train_xdata[rand_index] rand_x = np.expand_dims(rand_x, 3) rand_y = train_labels[rand_index] train_dict = {x_input: rand_x, y_target: rand_y, dropout: dropout_prob} sess.run(train_step, feed_dict=train_dict) temp_train_loss, temp_train_preds = sess.run([loss, prediction], feed_dict=train_dict) temp_train_acc = get_accuracy(temp_train_preds, rand_y) if (i + 1) % eval_every == 0: eval_index = np.random.choice(len(test_xdata), size=evaluation_size) eval_x = test_xdata[eval_index] eval_x = np.expand_dims(eval_x, 3) eval_y = test_labels[eval_index] test_dict = {eval_input: eval_x, eval_target: eval_y, dropout: 1.0} test_preds = sess.run(test_prediction, feed_dict=test_dict) temp_test_acc = get_accuracy(test_preds, eval_y) # Record and print results train_loss.append(temp_train_loss) train_acc.append(temp_train_acc) test_acc.append(temp_test_acc) acc_and_loss = [(i + 1), temp_train_loss, temp_train_acc, temp_test_acc] acc_and_loss = [np.round(x, 2) for x in acc_and_loss] print('Generation # {}. Train Loss: {:.2f}. Train Acc (Test Acc): {:.2f} ({:.2f})'.format(*acc_and_loss)) ``` 1. 要让我们的脚本执行测试或训练,我们需要以不同的方式从命令行调用它。以下代码段是主程序代码。如果程序收到参数`test`,它将执行测试;否则,它将运行训练: ```py if __name__ == '__main__': cmd_args = sys.argv if len(cmd_args) > 1 and cmd_args[1] == 'test': # Perform unit-tests tf.test.main(argv=cmd_args[1:]) else: # Run the TensorFlow app tf.app.run(main=None, argv=cmd_args) ``` 1. 如果我们在命令行上运行程序,我们应该得到以下输出: ```py $ python3 implementing_unit_tests.py test ... ---------------------------------------------------------------------- Ran 3 tests in 0.001s OK ``` 前面步骤中描述的完整程序可以在 [h](https://github.com/nfmcclure/tensorflow_cookbook/) [ttps://github.com/nfmcclure/tensorflow_cookbook/](https://github.com/nfmcclure/tensorflow_cookbook/) 的书籍 GitHub 仓库和 Packt 仓库中找到: [https://github.com/PacktPublishing/TensorFlow-Machine-Learning-Cookbook-Second-Edition](https://github.com/PacktPublishing/TensorFlow-Machine-Learning-Cookbook-Second-Edition) 。 ## 工作原理 在本节中,我们实现了三种类型的单元测试:张量值,操作输出和张量形状。 TensorFlow 有更多类型的单元测试函数,可在此处找到: [https://www.tensorflow.org/versions/master/api_docs/python/test.html](https://www.tensorflow.org/versions/master/api_docs/python/test.html) 。 请记住,单元测试有助于确保代码能够按预期运行,为共享代码提供信心,并使再现性更易于访问。