Question

我正在参加CS 20SI：来自斯坦福大学的深度学习研究的Tensorflow。我对以下代码有疑问：

import time
import numpy as np
import tensorflow as tf
from tensorflow.examples.tutorials.mnist import input_data
# Step 1: Read in data
# using TF Learn's built in function to load MNIST data to the folder data/mnist
MNIST = input_data.read_data_sets("/data/mnist", one_hot=True)

# Batched logistic regression
learning_rate = 0.01
batch_size = 128
n_epochs = 25

X = tf.placeholder(tf.float32, [batch_size, 784], name = 'image')
Y = tf.placeholder(tf.float32, [batch_size, 10], name = 'label')

#w = tf.Variable(tf.random_normal(shape = [int(shape[1]), int(Y.shape[1])], stddev = 0.01), name='weights')
#b = tf.Variable(tf.zeros(shape = [1, int(Y.shape[1])]), name='bias')

w = tf.Variable(tf.random_normal(shape=[784, 10], stddev=0.01), name="weights")
b = tf.Variable(tf.zeros([1, 10]), name="bias")

logits = tf.matmul(X,w) + b

entropy = tf.nn.softmax_cross_entropy_with_logits( logits=logits, labels=Y)
loss = tf.reduce_mean(entropy) #computes the mean over examples in the batch

optimizer = tf.train.GradientDescentOptimizer(learning_rate = learning_rate).minimize(loss)

init = tf.global_variables_initializer()

with tf.Session() as sess:
    sess.run(init)
    n_batches = int(MNIST.train.num_examples/batch_size)
    for i in range(n_epochs):
        start_time = time.time()
        for _ in range(n_batches):
            X_batch, Y_batch = MNIST.train.next_batch(batch_size)
            opt, loss_ = sess.run([optimizer, loss], feed_dict = {X: X_batch, Y:Y_batch})
        end_time = time.time() 
        print('Epoch %d took %f'%(i, end_time - start_time))

在此代码上，执行具有MNIST数据集的逻辑回归。作者说：

在我的Mac上运行批量大小为128的模型的批量版本以0.5秒的速度运行

然而，当我运行它时，每个纪元大约需要2秒，总执行时间约为一分钟。这个例子花了那么多时间是否合理？目前我有一台没有OC（3.0GHz）的Ryzen 1700和没有OC的GPU Gtx 1080。

Answer 1

我在GTX Titan X（麦克斯韦尔）上尝试了这个代码，每个时期大约0.5秒。我希望GTX 1080应该能够得到类似的结果。

尝试使用最新的tensorflow和cuda / cudnn版本。确保没有限制（哪些GPU可见，内存张量流可以使用多少等）环境变量设置。您可以尝试运行微基准测试，以确保您可以实现卡的规定FLOPS，例如Testing GPU with tensorflow matrix multiplication

具有张量流的MNIST的Logistic回归速度

1 个答案: