Python 张量流重塑张量
我尝试使用Python 张量流重塑张量,python,machine-learning,neural-network,artificial-intelligence,tensorflow,Python,Machine Learning,Neural Network,Artificial Intelligence,Tensorflow,我尝试使用tf.nn.sparse\u softmax\u cross\u entropy\u和_logits,我已经按照用户Olivier Moindrot的答案[here][1]进行了操作,但是我得到了一个维度错误 我正在建立一个分割网络,所以输入图像是200x200,输出图像是200x200。分类是二元的,前景和背景也是如此 在我构建CNNpred=conv_net(x,权重,偏差,keep_prob) pred看起来像这样 CNN有两个conv层,然后是一个完全连接的层。完全连接的层是4
tf.nn.sparse\u softmax\u cross\u entropy\u和_logits
,我已经按照用户Olivier Moindrot的答案[here][1]进行了操作,但是我得到了一个维度错误
我正在建立一个分割网络,所以输入图像是200x200,输出图像是200x200。分类是二元的,前景和背景也是如此
在我构建CNNpred=conv_net(x,权重,偏差,keep_prob)
pred
看起来像这样
CNN有两个conv层,然后是一个完全连接的层。完全连接的层是40000,因为它是200x200平坦的
根据上面的链接,我将pred
进行如下重塑
(旁注:我还试着将两个pred(如上所述)打包在一起,但我认为这是错误的)
pred=tf.重塑(pred,[-12002002])
…因此有两种分类。继续上面的链接
temp_pred = tf.reshape(pred, [-1,2])
temp_y = tf.reshape(y, [-1])
cost = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(temp_pred, temp_y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
我有以下占位符和批处理数据
x = tf.placeholder(tf.float32, [None, 200, 200])
y = tf.placeholder(tf.int64, [None, 200, 200])
(Pdb) batch_x.shape
(10, 200, 200)
(Pdb) batch_y.shape
(10, 200, 200)
当我运行培训课程时,我得到以下维度错误:
tensorflow.python.framework.errors.InvalidArgumentError: logits first
dimension must match labels size. logits shape=[3200000,2] labels
shape=[400000]
我的完整代码如下所示:
import tensorflow as tf
import pdb
import numpy as np
# Import MINST data
# from tensorflow.examples.tutorials.mnist import input_data
# mnist = input_data.read_data_sets("/tmp/data/", one_hot=True)
# Parameters
learning_rate = 0.001
training_iters = 200000
batch_size = 10
display_step = 1
# Network Parameters
n_input = 200 # MNIST data input (img shape: 28*28)
n_classes = 2 # MNIST total classes (0-9 digits)
n_output = 40000
#n_input = 200
dropout = 0.75 # Dropout, probability to keep units
# tf Graph input
x = tf.placeholder(tf.float32, [None, n_input, n_input])
y = tf.placeholder(tf.int64, [None, n_input, n_input])
keep_prob = tf.placeholder(tf.float32) #dropout (keep probability)
# Create some wrappers for simplicity
def conv2d(x, W, b, strides=1):
# Conv2D wrapper, with bias and relu activation
x = tf.nn.conv2d(x, W, strides=[1, strides, strides, 1], padding='SAME')
x = tf.nn.bias_add(x, b)
return tf.nn.relu(x)
def maxpool2d(x, k=2):
# MaxPool2D wrapper
return tf.nn.max_pool(x, ksize=[1, k, k, 1], strides=[1, k, k, 1],
padding='SAME')
# Create model
def conv_net(x, weights, biases, dropout):
# Reshape input picture
x = tf.reshape(x, shape=[-1, 200, 200, 1])
# Convolution Layer
conv1 = conv2d(x, weights['wc1'], biases['bc1'])
# Max Pooling (down-sampling)
# conv1 = tf.nn.local_response_normalization(conv1)
# conv1 = maxpool2d(conv1, k=2)
# Convolution Layer
conv2 = conv2d(conv1, weights['wc2'], biases['bc2'])
# Max Pooling (down-sampling)
# conv2 = tf.nn.local_response_normalization(conv2)
# conv2 = maxpool2d(conv2, k=2)
# Convolution Layer
conv3 = conv2d(conv2, weights['wc3'], biases['bc3'])
# # Max Pooling (down-sampling)
# conv3 = tf.nn.local_response_normalization(conv3)
# conv3 = maxpool2d(conv3, k=2)
# return conv3
# Fully connected layer
# Reshape conv2 output to fit fully connected layer input
fc1 = tf.reshape(conv2, [-1, weights['wd1'].get_shape().as_list()[0]])
fc1 = tf.add(tf.matmul(fc1, weights['wd1']), biases['bd1'])
fc1 = tf.nn.relu(fc1)
# Apply Dropout
fc1 = tf.nn.dropout(fc1, dropout)
return tf.add(tf.matmul(fc1, weights['out']), biases['out'])
# Output, class prediction
# output = []
# for i in xrange(2):
# # output.append(tf.nn.softmax(tf.add(tf.matmul(fc1, weights['out']), biases['out'])))
# output.append((tf.add(tf.matmul(fc1, weights['out']), biases['out'])))
#
# return output
# Store layers weight & bias
weights = {
# 5x5 conv, 1 input, 32 outputs
'wc1': tf.Variable(tf.random_normal([5, 5, 1, 32])),
# 5x5 conv, 32 inputs, 64 outputs
'wc2': tf.Variable(tf.random_normal([5, 5, 32, 64])),
# 5x5 conv, 32 inputs, 64 outputs
'wc3': tf.Variable(tf.random_normal([5, 5, 64, 128])),
# fully connected, 7*7*64 inputs, 1024 outputs
'wd1': tf.Variable(tf.random_normal([50*50*64, 1024])),
# 1024 inputs, 10 outputs (class prediction)
'out': tf.Variable(tf.random_normal([1024, n_output]))
}
biases = {
'bc1': tf.Variable(tf.random_normal([32])),
'bc2': tf.Variable(tf.random_normal([64])),
'bc3': tf.Variable(tf.random_normal([128])),
'bd1': tf.Variable(tf.random_normal([1024])),
'out': tf.Variable(tf.random_normal([n_output]))
}
# Construct model
pred = conv_net(x, weights, biases, keep_prob)
pdb.set_trace()
# pred = tf.pack(tf.transpose(pred,[1,2,0]))
pred = tf.reshape(pred, [-1, n_input, n_input, 2])
temp_pred = tf.reshape(pred, [-1,2])
temp_y = tf.reshape(y, [-1])
# Define loss and optimizer
cost = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(temp_pred, temp_y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
# Evaluate model
# correct_pred = tf.equal(tf.argmax(pred, 1), tf.argmax(y, 1))
temp_pred2 = tf.reshape(pred, [-1,n_input,n_input])
correct_pred = tf.equal(tf.cast(y,tf.float32),tf.sub(temp_pred2,tf.cast(y,tf.float32)))
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
# Initializing the variables
init = tf.initialize_all_variables()
# Launch the graph
with tf.Session() as sess:
sess.run(init)
summ = tf.train.SummaryWriter('/tmp/logdir/', sess.graph_def)
step = 1
from tensorflow.contrib.learn.python.learn.datasets.scroll import scroll_data
data = scroll_data.read_data('/home/kendall/Desktop/')
# Keep training until reach max iterations
while step * batch_size < training_iters:
batch_x, batch_y = data.train.next_batch(batch_size)
# Run optimization op (backprop)
batch_x = batch_x.reshape((batch_size, n_input, n_input))
batch_y = batch_y.reshape((batch_size, n_input, n_input))
batch_y = np.int64(batch_y)
# y = tf.reshape(y, [-1,n_input,n_input])
pdb.set_trace()
sess.run(optimizer, feed_dict={x: batch_x, y: batch_y, keep_prob: dropout})
if step % display_step == 0:
# Calculate batch loss and accuracy
pdb.set_trace()
loss, acc = sess.run([cost, accuracy], feed_dict={x: batch_x, y: batch_y, keep_prob: 1.})
print "Iter " + str(step*batch_size) + ", Minibatch Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc)
step += 1
print "Optimization Finished!"
# Calculate accuracy for 256 mnist test images
print "Testing Accuracy:", \
sess.run(accuracy, feed_dict={x: data.test.images[:256],
y: data.test.labels[:256],
keep_prob: 1.})
[1]: http://stackoverflow.com/questions/35317029/how-to-implement-pixel-wise-classification-for-scene-labeling-in-tensorflow/37294185?noredirect=1#comment63253577_37294185
将tensorflow导入为tf
导入pdb
将numpy作为np导入
#导入明斯特数据
#从tensorflow.examples.tutorials.mnist导入输入数据
#mnist=输入数据。读取数据集(“/tmp/data/”,one\u hot=True)
#参数
学习率=0.001
培训费用=200000
批量大小=10
显示步骤=1
#网络参数
n#u输入=200#m列表数据输入(img形状:28*28)
n#u类=2#n列出总类数(0-9位)
n_输出=40000
#n_输入=200
辍学率=0.75#辍学率,保留单位的概率
#tf图形输入
x=tf.placeholder(tf.float32,[None,n\u输入,n\u输入])
y=tf.placeholder(tf.int64,[None,n\u输入,n\u输入])
keep_prob=tf.placeholder(tf.float32)#辍学(keep probability)
#为简单起见,创建一些包装
def conv2d(x,W,b,步幅=1):
#Conv2D包装,带有偏置和relu激活
x=tf.nn.conv2d(x,W,步幅=[1,步幅,步幅,1],padding='SAME')
x=tf.nn.bias_add(x,b)
返回tf.nn.relu(x)
def maxpool2d(x,k=2):
#MaxPool2D包装器
返回tf.nn.max_pool(x,ksize=[1,k,k,1],步长=[1,k,k,1],
填充(“相同”)
#创建模型
def conv_净值(x、重量、偏差、损耗):
#重塑输入图片
x=tf.重塑(x,shape=[-12002001])
#卷积层
conv1=conv2d(x,权重['wc1'],偏差['bc1'])
#最大池(下采样)
#conv1=tf.nn.local\u response\u normalization(conv1)
#conv1=maxpool2d(conv1,k=2)
#卷积层
conv2=conv2d(conv1,权重['wc2'],偏差['bc2'])
#最大池(下采样)
#conv2=tf.nn.local\u response\u normalization(conv2)
#conv2=maxpool2d(conv2,k=2)
#卷积层
conv3=conv2d(conv2,权重['wc3'],偏差['bc3'])
##最大池(下采样)
#conv3=tf.nn.local\u response\u normalization(conv3)
#conv3=maxpool2d(conv3,k=2)
#返回conv3
#全连通层
#重塑conv2输出以适应完全连接的图层输入
fc1=tf.重塑(conv2,[-1,权重['wd1'].获取形状().作为列表()[0]]))
fc1=tf.add(tf.matmul(fc1,权重['wd1']),偏差['bd1']))
fc1=tf.nn.relu(fc1)
#申请退学
fc1=tf.nn.辍学(fc1,辍学)
返回tf.add(tf.matmul(fc1,权重['out']),偏差['out']))
#输出,类预测
#输出=[]
#对于X范围内的i(2):
##output.append(tf.nn.softmax(tf.add(tf.matmul(fc1,权重['out'))、偏差['out']))
#output.append((tf.add(tf.matmul(fc1,权重['out']),偏差['out']))
#
#返回输出
#存储层重量和偏差
权重={
#5x5转换,1个输入,32个输出
“wc1”:tf.Variable(tf.random_normal([5,5,1,32]),
#5x5转换,32个输入,64个输出
“wc2”:tf.Variable(tf.random_normal([5,5,32,64]),
#5x5转换,32个输入,64个输出
“wc3”:tf.Variable(tf.random_normal([5,5,64,128]),
#完全连接,7*7*64输入,1024输出
'wd1':tf.变量(tf.random_normal([50*50*641024]),
#1024个输入,10个输出(类预测)
'out':tf.Variable(tf.random\u normal([1024,n\u输出])
}
偏差={
“bc1”:tf.Variable(tf.random_normal([32]),
“bc2”:tf.Variable(tf.random_normal([64]),
“bc3”:tf.Variable(tf.random_normal([128]),
'bd1':tf.Variable(tf.random_normal([1024]),
'out':tf.Variable(tf.random\u normal([n\u output]))
}
#构造模型
pred=转换网络(x、权重、偏差、保持概率)
pdb.set_trace()
#pred=tf.pack(tf.transpose(pred[1,2,0]))
pred=tf.重塑(pred,[-1,n_输入,n_输入,2])
温度pred=tf.重塑(pred,[-1,2])
温度y=tf.重塑(y,[-1])
#定义损失和优化器
成本=tf.减少平均值(tf.nn.稀疏\u softmax\u交叉\u熵\u与逻辑(temp\u pred,temp\u y))
优化器=tf.train.AdamOptimizer(学习率=学习率)。最小化(成本)
#评价模型
#正确的pred=tf.equal(tf.argmax(pred,1),tf.argmax(y,1))
temp_pred2=tf.重塑(pred,[-1,n_输入,n_输入])
修正pred=tf.equal(tf.cast(y,tf.float32),tf.sub(temp_pred2,tf.cast(y,tf.float32)))
准确度=tf.reduce_平均值(tf.cast(correct_pred,tf.float32))
#初始化变量
初始化所有变量()
#启动图表
使用tf.Session()作为sess:
sess.run(初始化)
summ=tf.train.SummaryWriter('/tmp/logdir/',sess.graph_def)
步骤=1
从tensorflow.contrib.learn.python.learn.datasets.scroll导入scroll_数据
data=滚动数据。读取数据('/home/kendall/Desktop/'))
#继续训练直到达到最大迭代次数
步骤*批量大小<培训内容:
批次x,批次y=数据.训练.下一批次(批次大小)
#运行优化op(backprop)
批次x=批次x.重塑((批次大小,n输入,n输入))
批次y=批次y.重塑((批次大小,n输入,n输入))
批次y=np.int64(批次y)
#y=