我是Tensorflow的新手,所以这个问题可能真的很傻。
我一直在尝试使用Tensorflow为MNIST手写数字数据集编写一个简单的CNN。问题是优化器不会更新参数(由Tensorboard摘要监控) 图表似乎没问题,即使Layers API创建的范围看起来很奇怪。从每个层计算梯度。 请帮助!
我正在使用此处的培训数据:http://yann.lecun.com/exdb/mnist/
这是代码
import tensorflow as tf
DATA = 'train-images.idx3-ubyte'
LABELS = 'train-labels.idx1-ubyte'
NUM_EPOCHS = 2
BATCH_SIZE = 15
#Data definition
data_queue = tf.train.string_input_producer([DATA,])
label_queue = tf.train.string_input_producer([LABELS,])
reader_data = tf.FixedLengthRecordReader(record_bytes=28*28, header_bytes = 16)
reader_labels = tf.FixedLengthRecordReader(record_bytes=1, header_bytes = 8)
(_,data_rec) = reader_data.read(data_queue)
(_,label_rec) = reader_labels.read(label_queue)
image = tf.decode_raw(data_rec, tf.uint8)
image = tf.reshape(image, [28, 28, 1])
label = tf.decode_raw(label_rec, tf.uint8)
label = tf.reshape(label, [1])
image_batch, label_batch = tf.train.shuffle_batch([image, label],
batch_size=BATCH_SIZE,
capacity=100,
min_after_dequeue = 30)
#Layers definition
conv = tf.layers.conv2d(
inputs=tf.cast(image_batch, tf.float32),
filters=15,
kernel_size=[5,5],
padding='same',
activation=tf.nn.relu)
conv1 = tf.layers.conv2d(
inputs=conv,
filters=15,
kernel_size=[3,3],
padding='same',
activation=tf.nn.relu)
pool_flat = tf.reshape(conv1, [BATCH_SIZE, -1])
dense1 = tf.layers.dense(inputs=pool_flat, units=30, activation=tf.nn.relu)
output = tf.nn.softmax(tf.layers.dense(inputs=dense1, units=10))
#train operation definition
onehot_labels = tf.one_hot(indices=tf.cast(tf.reshape(label_batch,[-1]), tf.int32), depth=10)
loss = tf.losses.softmax_cross_entropy(onehot_labels=onehot_labels,
logits=output)
global_step = tf.Variable(0,name='global_step',trainable=False)
train_op = tf.train.GradientDescentOptimizer(0.05).minimize(loss, global_step = global_step)
#Summaries definition
for var in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='conv2d'):
tf.summary.histogram(var.name, var)
for var in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='conv2d_1'):
tf.summary.histogram(var.name, var)
for var in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='dense'):
tf.summary.histogram(var.name, var)
for var in tf.get_collection(tf.GraphKeys.GLOBAL_VARIABLES, scope='dense_1'):
tf.summary.histogram(var.name, var)
tf.summary.image("inp", image_batch, max_outputs =1)
loss_summary = tf.summary.scalar("loss", loss)
summaries = tf.summary.merge_all()
#init
sess = tf.Session()
summary_writer = tf.summary.FileWriter('log_simple_stats', sess.graph)
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord, sess=sess)
sess.run(tf.global_variables_initializer())
#loop
for i in range((60000*NUM_EPOCHS)//BATCH_SIZE):
sess.run(train_op)
if(i%100):
merged = sess.run(summaries)
summary_writer.add_summary(merged, i)
coord.request_stop()
coord.join(threads)
EDIT 自定义图层会产生相同的结果。
自定义图层定义:
def convol(input, inp, outp, name="conv"):
with tf.name_scope(name):
w = tf.Variable(tf.truncated_normal([5, 5, inp, outp], stddev=0.1),name="W")
b = tf.Variable(tf.constant(0.1, shape=[outp]), name="B")
filtered = tf.nn.conv2d(input, w, strides=[1,1,1,1], padding="SAME", name="conv2d")
activation = tf.nn.relu(features=(filtered+b), name="activation")
tf.summary.histogram(name=w.name, values=w)
tf.summary.histogram(name=b.name, values=b)
tf.summary.histogram(name=activation.name, values=activation)
return activation
def dense(input, inp, outp, name="dense"):
with tf.name_scope(name):
w = tf.Variable(tf.truncated_normal([inp, outp], stddev=0.1), name="W")
b = tf.Variable(tf.constant(0.1, shape=[outp]), name="B")
act = tf.matmul(input, w) + b
tf.summary.histogram(name=w.name, values=w)
tf.summary.histogram(name=b.name, values=b)
tf.summary.histogram(name="activation", values=act)
return act
编辑:
所以经过一段时间搞乱这个和MNIST的例子,我注意到没有学习权重。我处理数据读取的方式搞砸了一些关于梯度计算的东西。我刚刚录制了将MNIST数据集读入我的代码的类,它可以100%运行,不需要对参数进行任何调整。
答案 0 :(得分:0)
我的回忆录也遇到了同样的问题,对我而言,原因只是以下几个方面的结合:
为了获得更好的调试,尝试使用Tensorboard可视化您的过滤器,这个要点帮了我很多:
https://gist.github.com/kukuruza/03731dc494603ceab0c5
您的任何一种方法(tf.layers
和手动创建的变量)都应该正确连接到train_op
,所以我认为这不会有问题。