我的身材有问题，我该如何解决？我该怎么办？
文件“ run_demo.py”，第116行，位于主目录中 模型= get_crfrnn_model_def（）
get_crfrnn_model_def中的文件“ ./src/crfrnn_model.py”，第70行，
score_fused = Add（）（[score2，score_pool4c]）ValueError：操作数不能与形状（3，34，4）（3，34，3）一起广播
def get_crfrnn_model_def():
channels, height, weight = 3, 500, 500
# Input
input_shape = (height, weight, 3)
img_input = Input(shape=input_shape)
# Add plenty of zero padding
x = ZeroPadding2D(padding=(100, 100))(img_input)
# VGG-16 convolution block 1
x = Conv2D(64, (3, 3), activation='relu', padding='valid', name='conv1_1')(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same', name='conv1_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool1')(x)
# VGG-16 convolution block 2
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_1')(x)
x = Conv2D(128, (3, 3), activation='relu', padding='same', name='conv2_2')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool2', padding='same')(x)
# VGG-16 convolution block 3
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_1')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_2')(x)
x = Conv2D(256, (3, 3), activation='relu', padding='same', name='conv3_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool3', padding='same')(x)
pool3 = x
# VGG-16 convolution block 4
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv4_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool4', padding='same')(x)
pool4 = x
# VGG-16 convolution block 5
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_1')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_2')(x)
x = Conv2D(512, (3, 3), activation='relu', padding='same', name='conv5_3')(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='pool5', padding='same')(x)
# Fully-connected layers converted to convolution layers
x = Conv2D(4096, (7, 7), activation='relu', padding='valid', name='fc6')(x)
x = Dropout(0.5)(x)
x = Conv2D(4096, (1, 1), activation='relu', padding='valid', name='fc7')(x)
x = Dropout(0.5)(x)
x = Conv2D(3, (1, 1), padding='valid', name='score-fr')(x)
print(x)
# Deconvolution
score2 = Conv2DTranspose(3, (4, 4), strides=2, name='score2')(x)
print(score2)
# Skip connections from pool4
score_pool4 = Conv2D(3, (1, 1), name='score-pool4')(pool4)
score_pool4c = Cropping2D((5, 5),name='score-pool4c')(score_pool4)
print('asd')
print(score_pool4c)
score_fused = Add()([score2, score_pool4c])
score4 = Conv2DTranspose(3, (4, 4), strides=2, name='score4', use_bias=False)(score_fused)
# Skip connections from pool3
score_pool3 = Conv2D(3, (1, 1), name='score-pool3')(pool3)
score_pool3c = Cropping2D((9, 9))(score_pool3)
# Fuse things together
score_final = Add()([score4, score_pool3c])
# Final up-sampling and cropping
upsample = Conv2DTranspose(3, (16, 16), strides=8, name='upsample', use_bias=False)(score_final)
upscore = Cropping2D(((31, 37), (31, 37)))(upsample)
output = CrfRnnLayer(image_dims=(height, weight),
num_classes=3,
theta_alpha=160.,
theta_beta=3.,
theta_gamma=3.,
num_iterations=10,
name='crfrnn')([upscore, img_input])
model = Model(img_input, output, name='crfrnn_net')
return model
import numpy as np
import tensorflow as tf
from keras.engine.topology import Layer
import high_dim_filter_loader
custom_module = high_dim_filter_loader.custom_module
def _diagonal_initializer(shape):
return np.eye(shape[0], shape[1], dtype=np.float32)
def _potts_model_initializer(shape):
return -1 * _diagonal_initializer(shape)
class CrfRnnLayer(Layer):
def __init__(self, image_dims, num_classes,
theta_alpha, theta_beta, theta_gamma,
num_iterations, **kwargs):
self.image_dims = image_dims
self.num_classes = num_classes
self.theta_alpha = theta_alpha
self.theta_beta = theta_beta
self.theta_gamma = theta_gamma
self.num_iterations = num_iterations
self.spatial_ker_weights = None
self.bilateral_ker_weights = None
self.compatibility_matrix = None
super(CrfRnnLayer, self).__init__(**kwargs)
def build(self, input_shape):
# Weights of the spatial kernel
self.spatial_ker_weights = self.add_weight(name='spatial_ker_weights',
shape=(self.num_classes, self.num_classes),
initializer=_diagonal_initializer,
trainable=True)
# Weights of the bilateral kernel
self.bilateral_ker_weights = self.add_weight(name='bilateral_ker_weights',
shape=(self.num_classes, self.num_classes),
initializer=_diagonal_initializer,
trainable=True)
# Compatibility matrix
self.compatibility_matrix = self.add_weight(name='compatibility_matrix',
shape=(self.num_classes, self.num_classes),
initializer=_potts_model_initializer,
trainable=True)
super(CrfRnnLayer, self).build(input_shape)
def call(self, inputs):
unaries = tf.transpose(inputs[0][0, :, :, :], perm=(2, 0, 1))
rgb = tf.transpose(inputs[1][0, :, :, :], perm=(2, 0, 1))
c, h, w = self.num_classes, self.image_dims[0], self.image_dims[1]
all_ones = np.ones((c, h, w), dtype=np.float32)
# Prepare filter normalization coefficients
spatial_norm_vals = custom_module.high_dim_filter(all_ones, rgb, bilateral=False,
theta_gamma=self.theta_gamma)
bilateral_norm_vals = custom_module.high_dim_filter(all_ones, rgb, bilateral=True,
theta_alpha=self.theta_alpha,
theta_beta=self.theta_beta)
q_values = unaries
for i in range(self.num_iterations):
softmax_out = tf.nn.softmax(q_values, 0)
# Spatial filtering
spatial_out = custom_module.high_dim_filter(softmax_out, rgb, bilateral=False,
theta_gamma=self.theta_gamma)
spatial_out = spatial_out / spatial_norm_vals
# Bilateral filtering
bilateral_out = custom_module.high_dim_filter(softmax_out, rgb, bilateral=True,
theta_alpha=self.theta_alpha,
theta_beta=self.theta_beta)
bilateral_out = bilateral_out / bilateral_norm_vals
# Weighting filter outputs
message_passing = (tf.matmul(self.spatial_ker_weights,
tf.reshape(spatial_out, (c, -1))) +
tf.matmul(self.bilateral_ker_weights,
tf.reshape(bilateral_out, (c, -1))))
# Compatibility transform
pairwise = tf.matmul(self.compatibility_matrix, message_passing)
# Adding unary potentials
pairwise = tf.reshape(pairwise, (c, h, w))
q_values = unaries - pairwise
return tf.transpose(tf.reshape(q_values, (1, c, h, w)), perm=(0, 2, 3, 1))
def compute_output_shape(self, input_shape):
return input_shape
答案 0 :(得分：0)
好的，我想我找到了问题。
data_format：字符串，
"channels_last"或"channels_first"中的一个。输入中尺寸的顺序。"channels_last"对应于形状为(batch, height, width, channels)的输入，而"channels_first"对应于形状为(batch, channels, height, width)的输入。默认为在image_data_format的Keras配置文件中找到的~/.keras/keras.json值。如果您从未设置，那么它将是“ channels_last”。
但是，那是一个肮脏的谎言。实际上，可以从backend配置image_data_format。而您的run_demo.py中的两行正是这样：
from keras import backend as K
K.set_image_dim_ordering('th')
最好的部分？这似乎是一些旧式API。当我搜索该函数时，只能在Keras 1.2.2 documentation中找到它（当前版本为2.2.4）。
请考虑您是否真的需要这两行。实际上，无论如何都要删除第二行。如果确实需要，可以添加K.set_image_data_format('channels_first')，可能还需要更改输入形状以匹配：
# input_shape = (height, weight, channels)
input_shape = (channels, height, weight)
答案 1 :(得分：0)
我认为您可以尝试使用keras的image_data_format函数：
from keras import backend as K
img_width, img_height = 500, 500
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_height)
else:
input_shape = (img_width, img_height, 3)