我已经研究了很多天的分割问题,在终于找到如何正确读取数据集之后,我遇到了这个问题:
ValueError: Error when checking target: expected activation_1(Softmax) to have 3 dimensions, but got array with shape(32, 416, 608, 3)
I used the functional API, since I took the FCNN architecture from [here](https://github.com/divamgupta/image-segmentation-keras/blob/master/Models/FCN32.py).
根据我的任务(IMAGE_ORDERING = "channels_last"(TensorFlow backend)) 稍作修改和调整。 谁能帮帮我吗? 非常感谢。 下面的架构是针对 FCNN 的,我尝试实现它是为了分割的目的。这是架构(在调用 model.summary() 之后):
1.
2。
具体报错是:
“导入数据集”功能:
“Fit_Generator 方法调用”:
img_input = Input(shape=(input_height,input_width,3)) #Block 1 x = Convolution2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1', data_format=IMAGE_ORDERING)(img_input) x = BatchNormalization()(x) x = Convolution2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool', data_format=IMAGE_ORDERING)(x) f1 = x # Block 2 x = Convolution2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = Convolution2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool', data_format=IMAGE_ORDERING )(x) f2 = x # Block 3 x = Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool', data_format=IMAGE_ORDERING )(x) f3 = x # Block 4 x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2',data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3',data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool', data_format=IMAGE_ORDERING)(x) f4 = x # Block 5 x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2',data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3', data_format=IMAGE_ORDERING)(x) x = BatchNormalization()(x) x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool', data_format=IMAGE_ORDERING)(x) f5 = x x = (Convolution2D(4096,(7,7) , activation='relu' , padding='same', data_format=IMAGE_ORDERING))(x) x = Dropout(0.5)(x) x = (Convolution2D(4096,(1,1) , activation='relu' , padding='same',data_format=IMAGE_ORDERING))(x) x = Dropout(0.5)(x) #First parameter = number of classes+1 (de la background) x = (Convolution2D(20,(1,1) ,kernel_initializer='he_normal' ,data_format=IMAGE_ORDERING))(x) x = Convolution2DTranspose(20,kernel_size=(64,64), strides=(32,32),use_bias=False,data_format=IMAGE_ORDERING)(x) o_shape = Model(img_input,x).output_shape outputHeight = o_shape[1] print('Output Height is:', outputHeight) outputWidth = o_shape[2] print('Output Width is:', outputWidth) #https://keras.io/layers/core/#reshape x = (Reshape((20,outputHeight*outputWidth)))(x) #https://keras.io/layers/core/#permute x = (Permute((2, 1)))(x) print("Output shape before softmax is", o_shape) x = (Activation('softmax'))(x) print("Output shape after softmax is", o_shape) model = Model(inputs = img_input,outputs = x) model.outputWidth = outputWidth model.outputHeight = outputHeight model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics =['accuracy'])
请您参考如下方法:
FCNN 架构示例中的原始代码使用输入维度 (416, 608) .而在您的代码中,输入维度是 (192, 192) (忽略 channel 维度)。现在,如果您仔细观察,这个特定的层
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool', data_format=IMAGE_ORDERING)(x)
生成维度 (6, 6) 的输出(您可以在 model.summary() 中验证)。
下一个卷积层
o = (Convolution2D(4096,(7,7) , activation='relu' , padding='same', data_format=IMAGE_ORDERING))(o)
使用大小为 (7, 7) 的卷积过滤器,但您的输入已经减小到小于该大小(即 (6, 6))。先尝试解决这个问题。
此外,如果您查看 model.summary() 输出,您会注意到它不包含在 block5_pool 层之后定义的层。其中有一个 transposed convolution 层(基本上是对输入进行上采样)。您可能想看看并尝试解决这个问题。
注意:在我的所有维度中,我都忽略了 channel 维度。
编辑下面的详细答案
首先,这是我的 keras.json 文件。它使用 Tensorflow 后端,image_ordering 设置为 channel_last。
{
"floatx": "float32",
"epsilon": 1e-07,
"backend": "tensorflow",
"image_data_format": "channels_last"
}
接下来,我复制粘贴我的确切模型代码。请特别注意以下代码中的内联注释。
from keras.models import *
from keras.layers import *
IMAGE_ORDERING = 'channels_last' # In consistency with the json file
def getFCN32(nb_classes = 20, input_height = 416, input_width = 608):
img_input = Input(shape=(input_height,input_width, 3)) # Expected input will have channel in the last dimension
#Block 1
x = Convolution2D(64, (3, 3), activation='relu', padding='same', name='block1_conv1', data_format=IMAGE_ORDERING)(img_input)
x = BatchNormalization()(x)
x = Convolution2D(64, (3, 3), activation='relu', padding='same', name='block1_conv2', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block1_pool', data_format=IMAGE_ORDERING)(x)
f1 = x
# Block 2
x = Convolution2D(128, (3, 3), activation='relu', padding='same', name='block2_conv1', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = Convolution2D(128, (3, 3), activation='relu', padding='same', name='block2_conv2', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block2_pool', data_format=IMAGE_ORDERING )(x)
f2 = x
# Block 3
x = Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv1', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv2', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = Convolution2D(256, (3, 3), activation='relu', padding='same', name='block3_conv3', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block3_pool', data_format=IMAGE_ORDERING )(x)
f3 = x
# Block 4
x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv1', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv2',data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block4_conv3',data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block4_pool', data_format=IMAGE_ORDERING)(x)
f4 = x
# Block 5
x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv1', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv2',data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = Convolution2D(512, (3, 3), activation='relu', padding='same', name='block5_conv3', data_format=IMAGE_ORDERING)(x)
x = BatchNormalization()(x)
x = MaxPooling2D((2, 2), strides=(2, 2), name='block5_pool', data_format=IMAGE_ORDERING)(x)
f5 = x
x = (Convolution2D(4096,(7,7) , activation='relu' , padding='same', data_format=IMAGE_ORDERING))(x)
x = Dropout(0.5)(x)
x = (Convolution2D(4096,(1,1) , activation='relu' , padding='same',data_format=IMAGE_ORDERING))(x)
x = Dropout(0.5)(x)
x = (Convolution2D(20,(1,1) ,kernel_initializer='he_normal' ,data_format=IMAGE_ORDERING))(x)
x = Convolution2DTranspose(20,kernel_size=(64,64), strides=(32,32),use_bias=False,data_format=IMAGE_ORDERING)(x)
o_shape = Model(img_input, x).output_shape
# NOTE: Since this is channel last dimension ordering, the height and width dimensions are along [1] and [2], not [2] and [3]
outputHeight = o_shape[1]
outputWidth = o_shape[2]
x = (Reshape((outputHeight*outputWidth, 20)))(x) # Channel should be along the last dimenion of reshape
# No need of permute layer anymore
print("Output shape before softmax is", o_shape)
x = (Activation('softmax'))(x)
print("Output shape after softmax is", o_shape)
model = Model(inputs = img_input,outputs = x)
model.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics =['accuracy'])
return model
model = getFCN32(20)
print(model.summary())
接下来,我将提供有关我的 model.summary() 外观的片段。如果你看一下最后几层,它是这样的:
所以这意味着,conv2d_transpose 层产生维度为 (448, 640, 20) 的输出,并在应用 flatten 之前将其输出em>softmax 就可以了。所以输出的维度是(286720, 20)。同样,您的 target_generator(在您的情况下为 mask_generator)也应该生成相似维度的目标。同样,您的 input_generator 也应该生成大小为 [batch size, input_height,input_width, 3] 的输入批处理,如 img_input 中所述你的功能。
希望这能帮助您找到问题的根源并找出合适的解决方案。请查看代码中的细微变化(以及内联注释)以及如何创建您的输入 和目标 批处理。
