python - 使用alexnet和目录流来训练灰度数据集

这是我的参考：
flow from directory example
alexnet architecture

我尝试使用alexnet架构训练3个类别。数据集是灰度图像。我将第一个链接修改为分类类模式，然后将CNN模型修改为第二个链接的alexnet。
我收到2条错误消息：


ValueError：负尺寸大小是由于输入形状为[？，1,1,384]，[3,3,384,384]的'conv2d_83 / convolution'（op：'Conv2D'）的值从1中减去3引起的。
如果我更改img_width，img_height = 224,224
TypeError：Dense只能接受1个位置参数（'units'，），但是您传递了以下位置参数：[4096，（224，224，1）]


CNN中的尺寸是否无法比拟？
谢谢

这是代码：

import json
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
#from tensorflow.keras.optimizers import RMSprop


# dimensions of our images.
img_width, img_height = 150,150

train_data_dir = 'data/train'
validation_data_dir = 'data/validation'
nb_train_samples = 200*3
nb_validation_samples = 50*3
epochs = 1
batch_size = 5

if K.image_data_format() == 'channels_first':
    input_shape = (1, img_width, img_height)
else:
    input_shape = (img_width, img_height, 1)
print(input_shape)
model = Sequential()
model.add(Conv2D(filters=96, input_shape=input_shape,data_format='channels_last', kernel_size=(11,11), strides=(4,4), padding='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='valid'))

model.add(Conv2D(filters=256, kernel_size=(11,11), strides=(1,1), padding='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='valid'))

model.add(Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), padding='valid'))
model.add(Activation('relu'))
#model.add(MaxPooling2D(pool_size=(2, 2)))

# 4th Convolutional Layer
model.add(Conv2D(filters=384, kernel_size=(3,3), strides=(1,1), padding='valid'))
model.add(Activation('relu'))

# 5th Convolutional Layer
model.add(Conv2D(filters=256, kernel_size=(3,3), strides=(1,1), padding='valid'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2,2), strides=(2,2), padding='valid'))

model.add(Flatten())
model.add(Dense(4096, input_shape))
model.add(Activation('relu'))
model.add(Dropout(0.4))

model.add(Dense(4096))
model.add(Activation('relu'))
model.add(Dropout(0.4))

model.add(Dense(1000))
model.add(Activation('relu'))
model.add(Dropout(0.4))

# Output Layer
model.add(Dense(3))
model.add(Activation('softmax'))

model.summary()

# Compile the model
model.compile(loss=keras.losses.categorical_crossentropy, optimizer='adam', metrics=['accuracy'])

#model.compile(loss='categorical_crossentropy',optimizer=RMSprop(lr=0.001),metrics=['accuracy'])

# this is the augmentation configuration we will use for training
train_datagen = ImageDataGenerator(
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

# this is the augmentation configuration we will use for testing:
# only rescaling
test_datagen = ImageDataGenerator(rescale=1. / 255)

train_generator = train_datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_width, img_height),
    color_mode='grayscale',
    batch_size=batch_size,
    class_mode='categorical')

validation_generator = test_datagen.flow_from_directory(
    validation_data_dir,
    target_size=(img_width, img_height),
    color_mode='grayscale',
    batch_size=batch_size,
    class_mode='categorical')

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=nb_validation_samples // batch_size)

model_json = model.to_json()
with open("model_in_json.json", "w") as json_file:
    json.dump(model_json, json_file)

model.save_weights("model_weights.h5")

最佳答案

AlexNet适用于227x227的input_size。本文提到224x224，但这是一个错字。并不是说您不能使用其他大小，但是架构将变得没有意义。当输入大小过小时（即您的情况），出现了更多的发音问题。步幅= 2的卷积和最大池化操作降低了后续层的维数。您只用完了尺寸，用ValueError: Negative dimension size caused by subtracting 3 from 1 for 'conv2d_83/convolution'表示。上采样输入图像或更改体系结构。
该错误源于model.add(Dense(4096, input_shape))。如果检查Dense层的keras文档，您会注意到第二个参数是activation。如果有的话，您应该使用model.add(Dense(4096, input_shape=your_input_shape))。