我使用tensorflow来构建基于CNN的oin RGB图像，其大小为224 * 172。这是我建立的网络：
'use strict'
const webshot = require('webshot');
console.log('generating');
webshot('<html><head></head><body><img src="c:\\images\\mushrooms.png"/></body></html>', 'output.png', {siteType: 'html'}, function(err) {
console.log(err);
});
/*
webshot('<html><head></head><body><img src="https://s10.postimg.org/pr6zy8249/mushrooms.png"/></body></html>', 'output.png', {siteType: 'html'}, function(err) {
console.log(err);
});
*/
当我尝试训练我的网络时，我得到了这个错误：
def deepnn(x):
"""deepnn builds the graph for a deep net for classifying digits.
Args:
x: an input tensor with the dimensions (N_examples, 784), where 784 is the
number of pixels in a standard MNIST image.
Returns:
A tuple (y, keep_prob). y is a tensor of shape (N_examples, 10), with values
equal to the logits of classifying the digit into one of 10 classes (the
digits 0-9). keep_prob is a scalar placeholder for the probability of
dropout.
"""
# Reshape to use within a convolutional neural net.
# Last dimension is for "features" - there is only one here, since images are
# grayscale -- it would be 3 for an RGB image, 4 for RGBA, etc.
depth = 3
with tf.name_scope('reshape'):
x_image = tf.reshape(x, [-1, 224, 172, depth])
# First convolutional layer - maps one grayscale image to 32 feature maps.
with tf.name_scope('conv1'):
W_conv1 = weight_variable([5, 5, depth, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
# Pooling layer - downsamples by 2X.
with tf.name_scope('pool1'):
h_pool1 = max_pool_2x2(h_conv1)
# Second convolutional layer -- maps 32 feature maps to 64.
with tf.name_scope('conv2'):
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
# Second pooling layer.
with tf.name_scope('pool2'):
h_pool2 = max_pool_2x2(h_conv2)
# Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
# is down to 7x7x64 feature maps -- maps this to 1024 features.
with tf.name_scope('fc1'):
# W_fc1 = weight_variable([7 * 7 * 64, 1024])
W_fc1 = weight_variable([56 * 42 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 56 * 42 * 64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Dropout - controls the complexity of the model, prevents co-adaptation of
# features.
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Map the 1024 features to 10 classes, one for each digit
with tf.name_scope('fc2'):
W_fc2 = weight_variable([1024, 1])
b_fc2 = bias_variable([1])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
return y_conv, keep_prob
def conv2d(x, W):
"""conv2d returns a 2d convolution layer with full stride."""
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
"""max_pool_2x2 downsamples a feature map by 2X."""
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
def weight_variable(shape):
"""weight_variable generates a weight variable of a given shape."""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
"""bias_variable generates a bias variable of a given shape."""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def main(_):
# Import data
V0Dataset = dr.read_data_sets(FLAGS.data_dir, one_hot=True)
# Create the model
x = tf.placeholder(tf.float32, [None, 224*172*3])
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 1])
# Build the graph for the deep net
y_conv, keep_prob = deepnn(x)
我认为我的结构形状存在问题，或者更可能是我的数据集形状存在问题。
在该部分代码中出现了问题：
Cannot feed value of shape (10, 1, 1, 1) for Tensor 'Placeholder_1:0', which has shape '(?, 1)'
编辑：这是我所做的修改的更新。
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(100):
batch = V0Dataset.train.next_batch(10)
train_step.run(feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5}) ##### error
我得到的错误：
with tf.name_scope('reshape'):
x_image = tf.reshape(x, [-1, 224, 172, 1])#(x, [-1, 28, 28, 1])
# First convolutional layer - maps one grayscale image to 32 feature maps.
with tf.name_scope('conv1'):
W_conv1 = weight_variable([5, 5, 1, 32])#([5, 5, 1, 32])
b_conv1 = bias_variable([32])
h_conv1 = tf.nn.relu(conv2d(x_image, W_conv1) + b_conv1)
# Pooling layer - downsamples by 2X.
with tf.name_scope('pool1'):
h_pool1 = max_pool_2x2(h_conv1)
# Second convolutional layer -- maps 32 feature maps to 64.
with tf.name_scope('conv2'):
W_conv2 = weight_variable([5, 5, 32, 64])
b_conv2 = bias_variable([64])
h_conv2 = tf.nn.relu(conv2d(h_pool1, W_conv2) + b_conv2)
# Second pooling layer.
with tf.name_scope('pool2'):
h_pool2 = max_pool_2x2(h_conv2)
# Fully connected layer 1 -- after 2 round of downsampling, our 28x28 image
# is down to 7x7x64 feature maps -- maps this to 1024 features.
with tf.name_scope('fc1'):
W_fc1 = weight_variable([28 * 43 * 64, 1024])
b_fc1 = bias_variable([1024])
h_pool2_flat = tf.reshape(h_pool2, [-1, 28*43*64])
h_fc1 = tf.nn.relu(tf.matmul(h_pool2_flat, W_fc1) + b_fc1)
# Dropout - controls the complexity of the model, prevents co-adaptation of
# features.
with tf.name_scope('dropout'):
keep_prob = tf.placeholder(tf.float32)
h_fc1_drop = tf.nn.dropout(h_fc1, keep_prob)
# Map the 1024 features to 10 classes, one for each digit
with tf.name_scope('fc2'):
W_fc2 = weight_variable([1024, 2])
b_fc2 = bias_variable([2])
y_conv = tf.matmul(h_fc1_drop, W_fc2) + b_fc2
return y_conv, keep_prob
def conv2d(x, W):
"""conv2d returns a 2d convolution layer with full stride."""
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')
def max_pool_2x2(x):
"""max_pool_2x2 downsamples a feature map by 2X."""
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
strides=[1, 2, 2, 1], padding='SAME')
def weight_variable(shape):
"""weight_variable generates a weight variable of a given shape."""
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
def bias_variable(shape):
"""bias_variable generates a bias variable of a given shape."""
initial = tf.constant(0.1, shape=shape)
return tf.Variable(initial)
def main(_):
# Import data
V0Dataset = dr.read_data_sets(FLAGS.data_dir, one_hot=True)
# Create the model
x = tf.placeholder(tf.float32, [None, 224*172])
# Define loss and optimizer
y_ = tf.placeholder(tf.float32, [None, 2])
print("logits shape {}".format(y_))
# Build the graph for the deep net
y_conv, keep_prob = deepnn(x)
with tf.name_scope('loss'):
cross_entropy = tf.nn.softmax_cross_entropy_with_logits(labels=y_,
logits=y_conv)
cross_entropy = tf.reduce_mean(cross_entropy)
with tf.name_scope('adam_optimizer'):
train_step = tf.train.AdamOptimizer(1e-4).minimize(cross_entropy)
with tf.name_scope('accuracy'):
correct_prediction = tf.equal(tf.argmax(y_conv, 1), tf.argmax(y_, 1))
correct_prediction = tf.cast(correct_prediction, tf.float32)
accuracy = tf.reduce_mean(correct_prediction)
graph_location = tempfile.mkdtemp()
print('Saving graph to: %s' % graph_location)
train_writer = tf.summary.FileWriter("/tmp/tensorflow/")
train_writer.add_graph(tf.get_default_graph())
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
for i in range(100):
batch = V0Dataset.train.next_batch(10)
# print("----size0 {}".format(batch[0]))
# print("----size1 {}".format(batch[1]))
# print("----size2 {}".format(len(batch[0][0])))
# print("batch {}".format(batch))
# if i % 100 == 0:
# train_accuracy = accuracy.eval(feed_dict={
# x: batch[0], y_: batch[1], keep_prob: 1.0})
# print('step %d, training accuracy %g' % (i, train_accuracy))
# print("batch {}".format(batch[1]))
# batch1 = batch[1].reshape(20,2)
# print("batch {}".format(batch1))
a = batch[1];
a = a.reshape(10,2)
train_step.run(feed_dict={x: batch[0], y_: a, keep_prob: 0.5})
# print('test accuracy %g' % accuracy.eval(feed_dict={
# x: V0Dataset.test.images, y_: V0Dataset.test.labels, keep_prob: 1.0}))
if __name__ == '__main__':
parser = argparse.ArgumentParser()
parser.add_argument('--data_dir', type=str,
default='/tmp/tensorflow/mnist/input_data',
help='Directory for storing input data')
FLAGS, unparsed = parser.parse_known_args()
tf.app.run(main=main, argv=[sys.argv[0]] + unparsed)
编辑：
我找到了解决方案。显然，输入尺寸必须具有相同的宽度和高度。我把width = height = 100，现在它可以工作。
答案 0 :(得分：1)
错误是由于您正在加入占位符 y _ 的张量不匹配。
V0Dataset = dr.read_data_sets(FLAGS.data_dir, one_hot=True)
在上面一行中，您启用了one_hot编码，因此如果您正在执行多类分类，那么在执行batch = V0Dataset.train.next_batch(10)后，您将获得批量“ 1 x class_size ”的列表[1]。
例如，如果您正在进行10路分类，则在next_batch（）调用之后输出y_将类似于[1,0,0,0,0,0,0,0,0,0]，表明这一点输入属于第一类。
所以改变这行代码y_ = tf.placeholder(tf.float32, [None, 1])。将此1替换为输出类别数。
答案 1 :(得分：0)
您的标签似乎形状错误。然后重新塑造numpy。
labels = np.reshape(batch[1],(10,1))