TF Learn : 基于Scikit-learn和TensorFlow的深度学习利器
Scikit-learn 是最常用的 Python 机器学习框架,在各大互联网公司做算法的工程师在实现单机版本的算法的时候或多或少都会用到 Scikit-learn 。TensorFlow 就更是大名鼎鼎,做深度学习的人都不可能不知道 TensorFlow。
下面我们先来看一段样例,这段样例是传统的机器学习算法逻辑回归的实现:
可以看到,样例中仅仅使用了 3 行代码就完成了逻辑回归的主要功能。下面我们来看一下如果用 TensorFlow 来实现同样的代码,需要多少行?下面的代码来自 GitHub :
''' A logistic regression learning algorithm example using TensorFlow library. This example is using the MNIST database of handwritten digits (http://yann.lecun.com/exdb/mnist/) Author: Aymeric Damien Project: https://github.com/aymericdamien/TensorFlow-Examples/ ''' from __future__ import print_function import tensorflow as tf # Import MNIST data from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("/tmp/data/", one_hot=True) # Parameters learning_rate = 0.01 training_epochs = 25 batch_size = 100 display_step = 1 # tf Graph Input x = tf.placeholder(tf.float32, [None, 784]) # mnist data image of shape 28*28=784 y = tf.placeholder(tf.float32, [None, 10]) # 0-9 digits recognition => 10 classes # Set model weights W = tf.Variable(tf.zeros([784, 10])) b = tf.Variable(tf.zeros([10])) # Construct model pred = tf.nn.softmax(tf.matmul(x, W) + b) # Softmax # Minimize error using cross entropy cost = tf.reduce_mean(-tf.reduce_sum(y*tf.log(pred), reduction_indices=1)) # Gradient Descent optimizer = tf.train.GradientDescentOptimizer(learning_rate).minimize(cost) # Initialize the variables (i.e. assign their default value) init = tf.global_variables_initializer() # Start training with tf.Session() as sess: # Run the initializer sess.run(init) # Training cycle for epoch in range(training_epochs): avg_cost = 0. total_batch = int(mnist.train.num_examples/batch_size) # Loop over all batches for i in range(total_batch): batch_xs, batch_ys = mnist.train.next_batch(batch_size) # Run optimization op (backprop) and cost op (to get loss value) _, c = sess.run([optimizer, cost], feed_dict={x: batch_xs, y: batch_ys}) # Compute average loss avg_cost += c / total_batch # Display logs per epoch step if (epoch+1) % display_step == 0: print("Epoch:", '%04d' % (epoch+1), "cost=", "{:.9f}".format(avg_cost)) print("Optimization Finished!") # Test model correct_prediction = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1)) # Calculate accuracy accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32)) print("Accuracy:", accuracy.eval({x: mnist.test.images, y: mnist.test.labels}))
一个相对来说比较简单的机器学习算法,用 Tensorflow 来实现却花费了大量的篇幅。然而 Scikit-learn 本身没有 Tensorflow 那样丰富的深度学习的功能。有没有什么办法,能够在保证 Scikit-learn 的简单易用性的前提下,能够让 Scikit-learn 像 Tensorflow 那样支持深度学习呢?答案是有的,那就是 Scikit-Flow 开源项目。该项目后来被集成到了 Tensorflow 项目里,变成了现在的 TF Learn 模块。
我们来看一个 TF Learn 实现线性回归的样例:
""" Linear Regression Example """ from __future__ import absolute_import, division, print_function import tflearn # Regression data X = [3.3,4.4,5.5,6.71,6.93,4.168,9.779,6.182,7.59,2.167,7.042,10.791,5.313,7.997,5.654,9.27,3.1] Y = [1.7,2.76,2.09,3.19,1.694,1.573,3.366,2.596,2.53,1.221,2.827,3.465,1.65,2.904,2.42,2.94,1.3] # Linear Regression graph input_ = tflearn.input_data(shape=[None]) linear = tflearn.single_unit(input_) regression = tflearn.regression(linear, optimizer='sgd', loss='mean_square', metric='R2', learning_rate=0.01) m = tflearn.DNN(regression) m.fit(X, Y, n_epoch=1000, show_metric=True, snapshot_epoch=False) print("\nRegression result:") print("Y = " + str(m.get_weights(linear.W)) + "*X + " + str(m.get_weights(linear.b))) print("\nTest prediction for x = 3.2, 3.3, 3.4:") print(m.predict([3.2, 3.3, 3.4]))
我们可以看到,TF Learn 继承了 Scikit-Learn 的简洁编程风格,在处理传统的机器学习方法的时候非常的方便。下面我们看一段 TF Learn 实现 CNN (MNIST数据集)的样例:
""" Convolutional Neural Network for MNIST dataset classification task. References: Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. "Gradient-based learning applied to document recognition." Proceedings of the IEEE, 86(11):2278-2324, November 1998. Links: [MNIST Dataset] http://yann.lecun.com/exdb/mnist/ """ from __future__ import division, print_function, absolute_import import tflearn from tflearn.layers.core import input_data, dropout, fully_connected from tflearn.layers.conv import conv_2d, max_pool_2d from tflearn.layers.normalization import local_response_normalization from tflearn.layers.estimator import regression # Data loading and preprocessing import tflearn.datasets.mnist as mnist X, Y, testX, testY = mnist.load_data(one_hot=True) X = X.reshape([-1, 28, 28, 1]) testX = testX.reshape([-1, 28, 28, 1]) # Building convolutional network network = input_data(shape=[None, 28, 28, 1], name='input') network = conv_2d(network, 32, 3, activation='relu', regularizer="L2") network = max_pool_2d(network, 2) network = local_response_normalization(network) network = conv_2d(network, 64, 3, activation='relu', regularizer="L2") network = max_pool_2d(network, 2) network = local_response_normalization(network) network = fully_connected(network, 128, activation='tanh') network = dropout(network, 0.8) network = fully_connected(network, 256, activation='tanh') network = dropout(network, 0.8) network = fully_connected(network, 10, activation='softmax') network = regression(network, optimizer='adam', learning_rate=0.01, loss='categorical_crossentropy', name='target') # Training model = tflearn.DNN(network, tensorboard_verbose=0) model.fit({'input': X}, {'target': Y}, n_epoch=20, validation_set=({'input': testX}, {'target': testY}), snapshot_step=100, show_metric=True, run_id='convnet_mnist')
可以看到,基于 TF Learn 的深度学习代码也是非常的简洁。
TF Learn 是 TensorFlow 的高层次类 Scikit-Learn 封装,提供了原生版 TensorFlow 和 Scikit-Learn 之外的又一种选择。对于熟悉了 Scikit-Learn 和厌倦了 TensorFlow 冗长代码的用户来说,不啻为一种福音,也值得机器学习和数据挖掘的从业者认真学习和掌握。