ValueError：检查目标时出错：预期激活具有形状 (1,) 但得到形状为 (2,) 的数组

Question

我正在尝试使用 python 中的 keras 创建一个深度神经网络，但出现以下错误：

ValueError：检查目标时出错：预期激活具有形状 (1,) 但得到形状为 (2,) 的数组

我的代码如下：

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Convolution2D
from tensorflow.keras.layers import MaxPooling2D
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Dense, Activation, Dropout
from sklearn.model_selection import train_test_split
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.utils import to_categorical
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
import cv2
import random

df = pd.read_csv(r'UTKFace\data.csv', low_memory=False, header=None)
df = df.values

labels = [];
data = [];
random.seed(42)
random.shuffle(df);

for i in range(0,df.shape[0]):
    # load the image, pre-process it, and store it in the data list
    image = cv2.imread("UTKFace/" + df[i][0])
    image = img_to_array(image)
    data.append(image)

    # extract the class label from the image path and update the
    # labels list
    labels.append(df[i][1])

data = np.array(data, dtype="float") / 255.0
labels = np.array(labels)

(trainX, testX, trainY, testY) = train_test_split(data, labels, test_size=0.3, random_state=42)

trainY = to_categorical(trainY, 2)
testY = to_categorical(testY, 2)

print(trainX.shape)
print(trainY.shape)

print('done')

model = Sequential()
model.add(Convolution2D(32, (3,3), input_shape = (100,100,3), activation = 'relu'))
model.add(MaxPooling2D(pool_size = (2,2), strides=(2,2)))
model.add(Convolution2D(64, (1,1), activation = 'relu'))
model.add(MaxPooling2D(pool_size = (2,2), strides=(2,2)))
model.add(Convolution2D(128, (1,1), activation = 'relu'))
model.add(MaxPooling2D(pool_size = (2,2), strides=(2,2)))
model.add(Convolution2D(256, (1,1), activation = 'relu'))
model.add(MaxPooling2D(pool_size = (2,2), strides=(2,2)))
model.add(Flatten())
model.add(Dense(256, activation = 'relu'))
model.add(Dense(256, activation = 'relu'))
model.add(Dropout(0.5));
model.add(Dense(1, activation = 'relu'))
model.add(Activation('softmax'))
model.summary()
model.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])

#train the network
print("[INFO] training network...")
hist = model.fit(trainX, trainY, batch_size=256, epochs=10, validation_split=0.3)

谁能告诉我我做错了什么？ 我的模型架构如下：

> Layer (type)                 Output Shape              Param #
=================================================================
conv2d (Conv2D)              (None, 98, 98, 32)        896
_________________________________________________________________
max_pooling2d (MaxPooling2D) (None, 49, 49, 32)        0
_________________________________________________________________
conv2d_1 (Conv2D)            (None, 49, 49, 64)        2112
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 24, 24, 64)        0
_________________________________________________________________
conv2d_2 (Conv2D)            (None, 24, 24, 128)       8320
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 12, 12, 128)       0
_________________________________________________________________
conv2d_3 (Conv2D)            (None, 12, 12, 256)       33024
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 6, 6, 256)         0
_________________________________________________________________
flatten (Flatten)            (None, 9216)              0
_________________________________________________________________
dense (Dense)                (None, 256)               2359552
_________________________________________________________________
dense_1 (Dense)              (None, 256)               65792
_________________________________________________________________
dropout (Dropout)            (None, 256)               0
_________________________________________________________________
dense_2 (Dense)              (None, 1)                 257
_________________________________________________________________
activation (Activation)      (None, 1)                 0
=================================================================
Total params: 2,469,953
Trainable params: 2,469,953
Non-trainable params: 0
_________________________________________________________________

Answer 1

更改输出层中的激活函数和神经元数：

model.add(Dense(2, activation = 'sigmoid'))

并删除它，因为它现在是多余的：

model.add(Activation('softmax'))

如果这不起作用，请将您的损失更改为categorical_crossentropy ，我不确定binary_crossentropy需要 1D 或 2D 输出。