时间戳

首页 > 解决方案 > TensorFlow 和 Keras 中神经网络的性能有何不同？

python - TensorFlow 和 Keras 中神经网络的性能有何不同？

问题描述

我是机器学习（ML）的新手，我正在尝试实现算法来理解 ML 框架等的基本语法。现在我正在研究手写数字数据集的 MNIST 数据库。

我只实现了一层（我的意思是：输入层有 784 个输入，隐藏层有 512 个节点，输出层有 10 个输出）使用 TensorFlow 框架的神经网络，没有数据预处理，128 个批量大小，10 个 epoch，ADAM 优化器。该算法在训练集上达到了大约 0.95 的准确度。

之后我尝试在 Keras 中实现完全相同的架构。但是，准确度（训练集）约为 0.3。我试图在互联网上找到许多不同的实现，但我仍然找不到问题出在哪里。我相信这是愚蠢的（一如既往）：-/

我认为 Keras 中的相同架构应该给出与 TensorFlow 中的实现相同的结果，对吗？

我的 Keras 实现是：

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf
from keras.layers import Input, Dense
from keras.models import Model
from keras.utils.np_utils import to_categorical

df_train = pd.read_csv('datasets/MNIST_train.csv', delimiter=',', header=0)
Y_train, X_train = np.split(df_train.values, [1], axis=1)

m, n_x = X_train.shape
n_y = len(np.unique(Y_train))
n_layer1 = 512
batch_size = 128
num_epochs = 10

Y_train = to_categorical(Y_train)

X_input = Input(shape=(n_x,), name='input')
X = Dense(n_layer1, activation='relu', name='hidden')(X_input)
X = Dense(n_y, activation='softmax', name='output')(X)

model = Model(inputs=X_input, outputs=X, name='Neural Network')

model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])

model.fit(X_train, Y_train, epochs=num_epochs, batch_size=batch_size)

我的 TensorFlow 实现是：

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf

def one_hot(a, num_classes):
  return np.eye(num_classes)[a.reshape(-1)]

def get_minibatches(batch_size, m, X, Y):
    output_batches = []

    for index in range(0, m, batch_size):
        index_end = index + batch_size
        batch = [X[index:index_end], Y[index:index_end]]
        output_batches.append(batch)

    return output_batches

def dense_layer(input, channels_in, channels_out, activation=None):
   initializer = tf.contrib.layers.xavier_initializer()
   w = tf.Variable(initializer([channels_in, channels_out]), name="w")
   b = tf.Variable(tf.zeros([1, channels_out]), name="b")

   if (activation == 'relu'):
       a = tf.nn.relu(tf.matmul(input, w) + b)
       return a
   else:
       z = tf.matmul(input, w) + b
       return z

df_train = pd.read_csv('datasets/MNIST_train.csv', delimiter=',', header=0)
Y_train, X_train = np.split(df_train.values, [1], axis=1)

m, n_x = X_train.shape
n_y = len(np.unique(Y_train))
n_layer1 = 512
batch_size = 128
num_epochs = 10

Y_train = one_hot(Y_train, n_y)

X = tf.placeholder(tf.float32, [None, n_x], name="X")
Y = tf.placeholder(tf.float32, [None, n_y], name="Y")

hidden = dense_layer(X, n_x, n_layer1, 'relu')
output = dense_layer(hidden, n_layer1, n_y)

loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=output, labels=Y))

optimizer = tf.train.AdamOptimizer().minimize(loss)

predict = tf.argmax(output, 1)
correct_prediction = tf.equal(predict, tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))

minibatches = get_minibatches(batch_size, m, X_train, Y_train)

with tf.Session() as sess:        
    sess.run(tf.global_variables_initializer())

    current_cost = sess.run(loss, feed_dict={X: X_train, Y: Y_train})
    train_accuracy = sess.run(accuracy, feed_dict={X: X_train, Y: Y_train})
    print('Epoch: {:<4} - Loss: {:<8.3} Train Accuracy: {:<5.3} '.format(0, current_cost, train_accuracy))

    for epoch in range(num_epochs):            
        for minibatch in minibatches:
            minibatch_X, minibatch_Y = minibatch

            sess.run(optimizer, feed_dict={ X: minibatch_X, Y: minibatch_Y })

        current_cost = sess.run(loss, feed_dict={X: X_train, Y: Y_train})
        train_accuracy = sess.run(accuracy, feed_dict={X: X_train, Y: Y_train})
        print('Epoch: {:<4} - Loss: {:<8.3} Train Accuracy: {:<5.3} '.format(epoch + 1, current_cost, train_accuracy))

你能帮助我并建议我做错了什么吗？谢谢彼得

标签： pythontensorflowmachine-learningneural-networkkeras

解决方案

我想到了。至少部分。我标准化了输入 ((x - xmean) / xstd)，Keras 实现已经开始返回与 TensorFlow 实现相似的结果……</p>

推荐阅读