【发布时间】:2017-07-01 03:04:24
【问题描述】:
对不起,我的英语不好。
我正在尝试使用 TensorFlow 构建自己的全卷积网络。 但是我用自己的图像数据训练这个模型有困难,而 MNIST 数据工作正常。
这是我的 FCN 模型代码:(未使用预训练或预构建模型)
import tensorflow as tf
import numpy as np
加载 MNIST 数据
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
images_flatten = tf.placeholder(tf.float32, shape=[None, 784])
images = tf.reshape(images_flatten, [-1,28,28,1]) # CNN deals with 3 dimensions
labels = tf.placeholder(tf.float32, shape=[None, 10])
keep_prob = tf.placeholder(tf.float32) # Dropout Ratio
卷积层
# Conv. Layer #1
W1 = tf.Variable(tf.truncated_normal([3, 3, 1, 4], stddev = 0.1))
b1 = tf.Variable(tf.truncated_normal([4], stddev = 0.1))
FMA = tf.nn.conv2d(images, W1, strides=[1,1,1,1], padding='SAME')
# FMA stands for Fused Multiply Add, which means convolution
RELU = tf.nn.relu(tf.add(FMA, b1))
POOL = tf.nn.max_pool(RELU, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
# Conv. Layer #2
W2 = tf.Variable(tf.truncated_normal([3, 3, 4, 8], stddev = 0.1))
b2 = tf.Variable(tf.truncated_normal([8], stddev = 0.1))
FMA = tf.nn.conv2d(POOL, W2, strides=[1,1,1,1], padding='SAME')
RELU = tf.nn.relu(tf.add(FMA, b2))
POOL = tf.nn.max_pool(RELU, ksize=[1,2,2,1], strides=[1,2,2,1], padding='SAME')
# Conv. Layer #3
W3 = tf.Variable(tf.truncated_normal([7, 7, 8, 16], stddev = 0.1))
b3 = tf.Variable(tf.truncated_normal([16], stddev = 0.1))
FMA = tf.nn.conv2d(POOL, W3, strides=[1,1,1,1], padding='VALID')
RELU = tf.nn.relu(tf.add(FMA, b3))
# Dropout
Dropout = tf.nn.dropout(RELU, keep_prob)
# Conv. Layer #4
W4 = tf.Variable(tf.truncated_normal([1, 1, 16, 10], stddev = 0.1))
b4 = tf.Variable(tf.truncated_normal([10], stddev = 0.1))
FMA = tf.nn.conv2d(Dropout, W4, strides=[1,1,1,1], padding='SAME')
LAST_RELU = tf.nn.relu(tf.add(FMA, b4))
总结:[Conv-ReLU-Pool] - [Conv-ReLU-Pool] - [Conv-ReLU] - [Dropout] - [Conv-ReLU]
定义损失、准确度
prediction = tf.squeeze(LAST_RELU)
# Because FCN returns (1 x 1 x class_num) in training
loss = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(prediction, labels))
# First arg is 'logits=' and the other one is 'labels='
optimizer = tf.train.AdamOptimizer(0.001)
train = optimizer.minimize(loss)
label_max = tf.argmax(labels, 1)
pred_max = tf.argmax(prediction, 1)
correct_pred = tf.equal(pred_max, label_max)
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
训练模型
sess = tf.Session()
sess.run(tf.global_variables_initializer())
for i in range(10000):
image_batch, label_batch = mnist.train.next_batch(100)
sess.run(train, feed_dict={images: image_batch, labels: label_batch, keep_prob: 0.8})
if i % 10 == 0:
tr = sess.run([loss, accuracy], feed_dict={images: image_batch, labels: label_batch, keep_prob: 1.0})
print("Step %d, Loss %g, Accuracy %g" % (i, tr[0], tr[1]))
损失:0.784(大约)
准确度:94.8%(大约)
问题是,用 MNIST 数据训练这个模型效果很好,但是用我自己的数据,损失总是相同的(0.6319),输出层总是 0。
除了第三个卷积层的过滤器大小外,代码没有区别。此过滤器大小和由先前池化层压缩的输入大小必须具有相同的宽度和高度。这就是为什么这一层的过滤器大小是[7,7]。
我的模型有什么问题?..
两种情况(MNIST,我自己的数据)之间唯一不同的代码是:
占位符
我自己的数据有 (128 x 64 x 1),标签是 'eyes', 'not_eyes'
images = tf.placeholder(tf.float32, [None, 128, 64, 1])
labels = tf.placeholder(tf.int32, [None, 2])
第三卷积层
W3 = tf.Variable(tf.truncated_normal([32, 16, 8, 16], stddev = 0.1))
投料(批量)
image_data, label_data = input_data.get_batch(TRAINING_FILE, 10)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(sess=sess, coord=coord)
for i in range(10000):
image_batch, label_batch = sess.run([image_data, label_data])
sess.run(train, feed_dict={images: image_batch, labels: label_batch, keep_prob: 0.8})
if i % 10 == 0: ... # Validation part is almost same, too...
coord.request_stop()
coord.join(threads)
这里的“input_data”是同目录下的另一个python文件,“get_batch(TRAINING_FILE, 10)”是返回批处理数据的函数。代码是:
def get_input_queue(txtfile_name):
images = []
labels = []
for line in open(txtfile_name, 'r'): # Here txt file has data's path, label, label number
cols = re.split(',|\n', line)
labels.append(int(cols[2]))
images.append(tf.image.decode_jpeg(tf.read_file(cols[0]), channels = 1))
input_queue = tf.train.slice_input_producer([images, labels], shuffle = True)
return input_queue
def get_batch(txtfile_name, batch_size):
input_queue = get_input_queue(txtfile_name)
image = input_queue[0]
label = input_queue[1]
image = tf.reshape(image, [128, 64, 1])
batch_image, batch_label = tf.train.batch([image, label], batch_size)
batch_label_one_hot = tf.one_hot(tf.to_int64(batch_label), 2, on_value=1.0, off_value=0.0)
return batch_image, batch_label_one_hot
似乎没有任何问题.. :( 请帮帮我..!!
【问题讨论】:
-
尝试缩放输入(-1 到 1)并将权重的
stddev设置为较低的值,例如 0.01。output always zero指向deadReLU。 -
“缩放输入(-1 到 1)”是什么意思?
标签: tensorflow