python - Tensorflow reshape 张量

Question

我正在尝试使用tf.nn.sparse_softmax_cross_entropy_with_logits我已遵循用户 Olivier Moindrot [此处][1] 的回答，但出现尺寸错误

我正在构建一个分割网络，因此输入图像为 200x200，输出图像为 200x200。分类是二元的，即前景和背景。

在我构建 CNN 之后 pred = conv_net(x, weights, biases, keep_prob)

pred看起来像这样 <tf.Tensor 'Add_1:0' shape=(?, 40000) dtype=float32>

CNN 有几个卷积层，后面跟着一个全连接层。全连接层为 40000，因为它是 200x200 展平的。

根据上面的链接，我 reshape pred就像这样...

(旁注:我也尝试将 tf.pack() 两个 pred 打包在一起 - 就像上面一样，但我认为这是错误的)

pred = tf.reshape(pred, [-1, 200, 200, 2])

...这样就有 2 个分类。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)

当我运行训练类(class)时，出现以下尺寸错误:

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

Answer 1

让我们忘记 softmax，并在此处使用更简单的 tf.nn.sigmoid_cross_entropy_with_logits:

• 使用 sigmoid，每个像素只需要一次预测
  • 如果 pred[pixel] > 0.5，则预测为 1
  • 如果 pred[pixel] < 0.5，则预测为 0
• 预测和目标的形状应为[batch_size, 40000]

pred = conv_net(x, weights, biases, keep_prob)  # shape [batch_size, 40000]
flattened_y = tf.reshape(y, [-1, 40000])  # shape [batch_size, 40000]

loss = tf.nn.sigmoid_cross_entropy_with_logits(pred, flattened_y)