Segnet网络用keras实现的时候报错ValueError，求大神帮忙看看

Question

报错为：Error when checking target: expected activation_1 to have 3 dimensions, but got array with shape (32, 10)

keras+tensorflow后端

代码如下

# coding=utf-8
import matplotlib
from PIL import Image
matplotlib.use("Agg")
import matplotlib.pyplot as plt
import argparse
import numpy as np
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D, UpSampling2D, BatchNormalization, Reshape, Permute, Activation, Flatten

# from keras.utils.np_utils import to_categorical
# from keras.preprocessing.image import img_to_array
from keras.models import Model
from keras.layers import Input
from keras.callbacks import ModelCheckpoint
# from sklearn.preprocessing import LabelBinarizer
# from sklearn.model_selection import train_test_split
# import pickle
import matplotlib.pyplot as plt

import os
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(
        rescale=1./255,
        shear_range=0.2,
        zoom_range=0.2,
        horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)

path = '/tmp/2'
os.chdir(path)

training_set = train_datagen.flow_from_directory(
    'trainset',
    target_size=(64,64),
    batch_size=32,
    class_mode='categorical',
    shuffle=True)

test_set = test_datagen.flow_from_directory(
    'testset',
    target_size=(64,64),
    batch_size=32,
    class_mode='categorical',
    shuffle=True)


def SegNet():
    model = Sequential()
    # encoder
    model.add(Conv2D(64, (3, 3), strides=(1, 1), input_shape=(64, 64, 3), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(64, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(MaxPooling2D(pool_size=(2, 2)))
    # (128,128)
    model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(MaxPooling2D(pool_size=(2, 2)))
    # (64,64)
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(MaxPooling2D(pool_size=(2, 2)))
    # (32,32)
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(MaxPooling2D(pool_size=(2, 2)))
    # (16,16)
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(MaxPooling2D(pool_size=(2, 2)))
    # (8,8)
    # decoder
    model.add(UpSampling2D(size=(2, 2)))
    # (16,16)
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(UpSampling2D(size=(2, 2)))
    # (32,32)
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(512, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(UpSampling2D(size=(2, 2)))
    # (64,64)
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(256, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(UpSampling2D(size=(2, 2)))
    # (128,128)
    model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(128, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(UpSampling2D(size=(2, 2)))
    # (256,256)
    model.add(Conv2D(64, (3, 3), strides=(1, 1), input_shape=(64, 64, 3), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(64, (3, 3), strides=(1, 1), padding='same', activation='relu'))
    model.add(BatchNormalization())
    model.add(Conv2D(10, (1, 1), strides=(1, 1), padding='valid', activation='relu'))
    model.add(BatchNormalization())
    model.add(Reshape((64*64, 10)))

    # axis=1和axis=2互换位置，等同于np.swapaxes(layer,1,2)
    model.add(Permute((2, 1)))
    #model.add(Flatten())
    model.add(Activation('softmax'))
    model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
    model.summary()
    return model


def main():
    model = SegNet()
    filepath = "/tmp/2/weights.best.hdf5"
    checkpoint = ModelCheckpoint(filepath, monitor='val_acc', verbose=1, save_best_only=True, mode='max')
    callbacks_list = [checkpoint]
    history = model.fit_generator(
        training_set,
        steps_per_epoch=(training_set.samples / 32),
        epochs=20,
        callbacks=callbacks_list,
        validation_data=test_set,
        validation_steps=(test_set.samples / 32))

    # Plotting the Loss and Classification Accuracy
    model.metrics_names
    print(history.history.keys())
    #  "Accuracy"
    plt.plot(history.history['acc'])
    plt.plot(history.history['val_acc'])
    plt.title('Model Accuracy')
    plt.ylabel('Accuracy')
    plt.xlabel('Epoch')
    plt.legend(['train', 'test'], loc='upper left')
    plt.show()

    # "Loss"
    plt.plot(history.history['loss'])
    plt.plot(history.history['val_loss'])
    plt.title('Model loss')
    plt.ylabel('Loss')
    plt.xlabel('Epoch')
    plt.legend(['train', 'test'], loc='upper left')
    plt.show()

if __name__ == '__main__':
    main()

主要是这里，segnet没有全连接层，最后输出的应该是一个和输入图像同等大小的有判别标签的shape吗。。。求教怎么改。
输入图像是64 64的，3通道，总共10类,分别放在testset和trainset两个文件夹里

Answer 1

找到原因了。因为语义分割的网络要求的label是矩阵，就是与原图一样大小的对每个像素点都有标注的。
我这种每张小图片一个label的只能做分类，目标检测之类的工作