做者:chen_h
微信號 & QQ:862251340
微信公衆號:coderpai
簡書地址:https://www.jianshu.com/p/d6a...git
當咱們要使用神經網絡來構建一個多分類模型時,咱們通常都會採用 softmax 函數來做爲最後的分類函數。softmax 函數對每個分類結果都會分配一個機率,咱們把比較高的那個機率對應的類別做爲模型的輸出。這就是爲何咱們能從模型中推導出具體分類結果。爲了訓練模型,咱們使用 softmax 函數進行反向傳播,進行訓練。咱們最後輸出的就是一個 0-1 向量。github
在這篇文章中,咱們不會去解釋什麼是 softmax 迴歸或者什麼是 CNN。這篇文章的主要工做是如何在 TensorFlow 上面設計一個 L2 約束的 softmax 函數,咱們使用的數據集是 MNIST。完整的理論分析能夠查看這篇論文。算法
在具體實現以前,咱們先來弄清楚一些概念。微信
softmax 損失函數能夠定義以下:網絡
其中各個參數定義以下:架構
帶約束的損失函數定義幾乎和以前的同樣,咱們的目的仍是最小化這個損失函數。app
可是,咱們須要對 f(x) 函數進行修改。ide
咱們不是直接計算最後層權重與前一層網絡輸出 f(x) 之間的乘積,而是對前一層的 f(x) 先作一次歸一化,而後對這個歸一化的值進行 α 倍數的放大,最後咱們進行常規的 softmax 函數進行計算。函數
也就是說,損失函數是受到以下約束:性能
因此,咱們的架構看起來是以下圖(這也是我想要實現的架構圖):
C 表示卷積層,P 表示池化層,FC 表示全鏈接層,L2-Norm 層和Scale 層是咱們重點要實現的層。
爲了實現這個模型,咱們使用這個代碼庫 進行學習。
在應用 dropout 以前,咱們先對 N-1 層的輸出進行正則化,而後把正則化以後的結果乘以參數 alpha,而後進行 softmax 函數計算。下面是具體的代碼展現:
fc1 = alpha * tf.divide(fc1, tf.norm(fc1, ord='euclidean'))
若是咱們把 alpha 設置爲 0,那麼這就是常規的 softmax 函數,不然就是一個 L2 約束。
完整代碼以下:
# Actual Code : https://github.com/aymericdamien/TensorFlow-Examples/blob/master/notebooks/3_NeuralNetworks/convolutional_network.ipynb # Modified By: Manash from __future__ import division, print_function, absolute_import # Import MNIST data from tensorflow.examples.tutorials.mnist import input_data mnist = input_data.read_data_sets("/tmp/data/", one_hot=False) import tensorflow as tf import matplotlib.pyplot as plt import numpy as np # Training Parameters learning_rate = 0.001 num_steps = 100 batch_size = 20 # Network Parameters num_input = 784 # MNIST data input (img shape: 28*28) num_classes = 10 # MNIST total classes (0-9 digits) dropout = 0.75 # Dropout, probability to keep units # Create the neural network def conv_net(x_dict, n_classes, dropout, reuse, is_training, alpha=5): # Define a scope for reusing the variables with tf.variable_scope('ConvNet', reuse=reuse): # TF Estimator input is a dict, in case of multiple inputs x = x_dict['images'] # MNIST data input is a 1-D vector of 784 features (28*28 pixels) # Reshape to match picture format [Height x Width x Channel] # Tensor input become 4-D: [Batch Size, Height, Width, Channel] x = tf.reshape(x, shape=[-1, 28, 28, 1]) # Convolution Layer with 32 filters and a kernel size of 5 conv1 = tf.layers.conv2d(x, 32, 5, activation=tf.nn.relu) # Max Pooling (down-sampling) with strides of 2 and kernel size of 2 conv1 = tf.layers.max_pooling2d(conv1, 2, 2) # Convolution Layer with 32 filters and a kernel size of 5 conv2 = tf.layers.conv2d(conv1, 64, 3, activation=tf.nn.relu) # Max Pooling (down-sampling) with strides of 2 and kernel size of 2 conv2 = tf.layers.max_pooling2d(conv2, 2, 2) # Flatten the data to a 1-D vector for the fully connected layer fc1 = tf.contrib.layers.flatten(conv2) # Fully connected layer (in tf contrib folder for now) fc1 = tf.layers.dense(fc1, 1024) # If alpha is not zero then perform the l2-Normalization then scaling up if alpha != 0: fc1 = alpha * tf.divide(fc1, tf.norm(fc1, ord='euclidean')) # Apply Dropout (if is_training is False, dropout is not applied) fc1 = tf.layers.dropout(fc1, rate=dropout, training=is_training) # Output layer, class prediction out = tf.layers.dense(fc1, n_classes) return out # Define the model function (following TF Estimator Template) def model_fn(features, labels, mode): # Set alpha alph = 50 # Build the neural network # Because Dropout have different behavior at training and prediction time, we # need to create 2 distinct computation graphs that still share the same weights. logits_train = conv_net(features, num_classes, dropout, reuse=False, is_training=True, alpha=alph) # At test time we don't need to normalize or scale, it's redundant as per paper : https://arxiv.org/abs/1703.09507 logits_test = conv_net(features, num_classes, dropout, reuse=True, is_training=False, alpha=0) # Predictions pred_classes = tf.argmax(logits_test, axis=1) pred_probas = tf.nn.softmax(logits_test) # If prediction mode, early return if mode == tf.estimator.ModeKeys.PREDICT: return tf.estimator.EstimatorSpec(mode, predictions=pred_classes) # Define loss and optimizer loss_op = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits( logits=logits_train, labels=tf.cast(labels, dtype=tf.int32))) optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate) train_op = optimizer.minimize(loss_op, global_step=tf.train.get_global_step()) # Evaluate the accuracy of the model acc_op = tf.metrics.accuracy(labels=labels, predictions=pred_classes) # TF Estimators requires to return a EstimatorSpec, that specify # the different ops for training, evaluating, ... estim_specs = tf.estimator.EstimatorSpec( mode=mode, predictions=pred_classes, loss=loss_op, train_op=train_op, eval_metric_ops={'accuracy': acc_op}) return estim_specs # Build the Estimator model = tf.estimator.Estimator(model_fn) # Define the input function for training input_fn = tf.estimator.inputs.numpy_input_fn( x={'images': mnist.train.images}, y=mnist.train.labels, batch_size=batch_size, num_epochs=None, shuffle=False) # Train the Model model.train(input_fn, steps=num_steps) # Evaluate the Model # Define the input function for evaluating input_fn = tf.estimator.inputs.numpy_input_fn( x={'images': mnist.test.images}, y=mnist.test.labels, batch_size=batch_size, shuffle=False) # Use the Estimator 'evaluate' method model.evaluate(input_fn) # Predict single images n_images = 4 # Get images from test set test_images = mnist.test.images[:n_images] # Prepare the input data input_fn = tf.estimator.inputs.numpy_input_fn( x={'images': test_images}, shuffle=False) # Use the model to predict the images class preds = list(model.predict(input_fn)) # Display for i in range(n_images): plt.imshow(np.reshape(test_images[i], [28, 28]), cmap='gray') plt.show() print("Model prediction:", preds[i])
這個真的能提升性能嗎?是的,並且效果很是好,它能提升大約 1% 的性能。我沒有計算不少的迭代,主要是我沒有很好的電腦。若是你對這個性能有你疑惑,你能夠本身試試看。
如下是不一樣 alpha 值對應的模型性能:
橘黃色的線表示用常規的 softmax 函數,藍色的線是用 L2 約束的 softmax 函數。
做者:chen_h
微信號 & QQ:862251340
簡書地址:https://www.jianshu.com/p/d6a...
CoderPai 是一個專一於算法實戰的平臺,從基礎的算法到人工智能算法都有設計。若是你對算法實戰感興趣,請快快關注咱們吧。加入AI實戰微信羣,AI實戰QQ羣,ACM算法微信羣,ACM算法QQ羣。長按或者掃描以下二維碼,關注 「CoderPai」 微信號(coderpai)