python - 使用 alexnet 和 flow from 目录来训练灰度数据集

Question

这是我的引用: 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 模型从第二个链接修改为 alexnet。我收到 2 条错误消息:

1. ValueError:由于输入形状为:[?,1,1,384]、[3,3,384,384]的“conv2d_83/卷积”(操作:“Conv2D”)从 1 中减去 3 导致的负维度大小。

2. 如果我更改 img_width，img_height = 224,224TypeError: Dense 只能接受 1 个位置参数('units',)，但您传递了以下位置参数:[4096, (224, 224, 1)]

我在 CNN 中是否拥有无与伦比的维度？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")

Answer 1

1. AlexNet旨在与 input_size 一起使用227x227。论文中提到了 224x224，但这是一个拼写错误。这并不是说您不能使用其他尺寸，但是这样架构就没有什么意义了。当输入大小太小时，即您的情况，会出现更明显的问题。 strides=2 的卷积和最大池化操作降低了后续层的维度。您只是用完了尺寸，这由 ValueError: Negative dimension size caused by subtracting 3 from 1 for 'conv2d_83/convolution' 表示。 。对输入图像进行上采样或更改架构。

2. 错误源于 model.add(Dense(4096, input_shape)) 。如果您检查keras Dense 的文档层，您会注意到第二个参数是 activation 。如果有的话，你应该使用 model.add(Dense(4096, input_shape=your_input_shape)) 。