具有不同尺寸图像的张量流卷积神经网络

如果我们确保它final与DeConnv1(和其他)具有相同的尺寸,它将使y我们想要的形状正确:[-1, N * M * P, 3].

将它们结合在一起

您的网络非常庞大,但所有解卷积基本上都遵循相同的模式,因此我将概念验证代码简化为一个解卷积.目标只是展示哪种网络能够处理任意大小的图像.最后再说一句:图像尺寸可变化之间的批次,但一个批次内,他们必须是相同的.

完整代码:

sess = tf.InteractiveSession()

def conv3d_dilation(tempX, tempFilter):
  return tf.layers.conv3d(tempX, filters=tempFilter, kernel_size=[3, 3, 1], strides=1, padding='SAME', dilation_rate=2)

def conv3d(tempX, tempW):
  return tf.nn.conv3d(tempX, tempW, strides=[1, 2, 2, 2, 1], padding='SAME')

def conv3d_s1(tempX, tempW):
  return tf.nn.conv3d(tempX, tempW, strides=[1, 1, 1, 1, 1], padding='SAME')

def weight_variable(shape):
  initial = tf.truncated_normal(shape, stddev=0.1)
  return tf.Variable(initial)

def bias_variable(shape):
  initial = tf.constant(0.1, shape=shape)
  return tf.Variable(initial)

def max_pool_3x3(x):
  return tf.nn.max_pool3d(x, ksize=[1, 3, 3, 3, 1], strides=[1, 2, 2, 2, 1], padding='SAME')

x_image = tf.placeholder(tf.float32, shape=[None, None, None, None, 1])
label = tf.placeholder(tf.float32, shape=[None, None, 3])

W_conv1 = weight_variable([3, 3, 1, 1, 32])
h_conv1 = conv3d(x_image, W_conv1)
# second convolution
W_conv2 = weight_variable([3, 3, 4, 32, 64])
h_conv2 = conv3d_s1(h_conv1, W_conv2)
# third convolution path 1
W_conv3_A = weight_variable([1, 1, 1, 64, 64])
h_conv3_A = conv3d_s1(h_conv2, W_conv3_A)
# third convolution path 2
W_conv3_B = weight_variable([1, 1, 1, 64, 64])
h_conv3_B = conv3d_s1(h_conv2, W_conv3_B)
# fourth convolution path 1
W_conv4_A = weight_variable([3, 3, 1, 64, 96])
h_conv4_A = conv3d_s1(h_conv3_A, W_conv4_A)
# fourth convolution path 2
W_conv4_B = weight_variable([1, 7, 1, 64, 64])
h_conv4_B = conv3d_s1(h_conv3_B, W_conv4_B)
# fifth convolution path 2
W_conv5_B = weight_variable([1, 7, 1, 64, 64])
h_conv5_B = conv3d_s1(h_conv4_B, W_conv5_B)
# sixth convolution path 2
W_conv6_B = weight_variable([3, 3, 1, 64, 96])
h_conv6_B = conv3d_s1(h_conv5_B, W_conv6_B)
# concatenation
layer1 = tf.concat([h_conv4_A, h_conv6_B], 4)
w = tf.Variable(tf.constant(1., shape=[2, 2, 4, 1, 192]))
DeConnv1 = tf.nn.conv3d_transpose(layer1, filter=w, output_shape=tf.shape(x_image), strides=[1, 2, 2, 2, 1], padding='SAME')

final = DeConnv1
final_cOnv= conv3d_s1(final, weight_variable([1, 1, 1, 1, 3]))
y = tf.reshape(final_conv, [-1, 3])
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(labels=label, logits=y))

print('x_image:', x_image)
print('DeConnv1:', DeConnv1)
print('final_conv:', final_conv)

def try_image(N, M, P, B=1):
  batch_x = np.random.normal(size=[B, N, M, P, 1])
  batch_y = np.ones([B, N * M * P, 3]) / 3.0

  deconv_val, final_conv_val, loss = sess.run([DeConnv1, final_conv, cross_entropy],
                                              feed_dict={x_image: batch_x, label: batch_y})
  print(deconv_val.shape)
  print(final_conv.shape)
  print(loss)
  print()

tf.global_variables_initializer().run()
try_image(32, 32, 7)
try_image(16, 16, 3)
try_image(16, 16, 3, 2)