tensorflow - CNN 在 keras 中具有多个 conv3d

Question

我正在尝试在 Keras 中使用多个 conv3d 创建一个 CNN 模型以处理 cifar10 数据集。但面临以下问题:

ValueError: ('The specified size contains a dimension with value <= 0', (-8000, 256))

下面是我尝试执行的代码。

from __future__ import print_function
import keras
from keras.datasets import cifar10
from keras.preprocessing.image import ImageDataGenerator
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Conv3D, MaxPooling3D
from keras.optimizers import SGD
import os
from keras import backend as K

batch_size = 128
num_classes = 10
epochs = 20
learning_rate = 0.01

(x_train, y_train), (x_test, y_test) = cifar10.load_data()
print('x_train shape:', x_train.shape)
print(x_train.shape[0], 'train samples')
print(x_test.shape[0], 'test samples')
img_rows = x_train.shape[1]
img_cols = x_train.shape[2]
colors = x_train.shape[3]


if K.image_data_format() == 'channels_first':
    x_train = x_train.reshape(x_train.shape[0], 1,colors, img_rows, img_cols)
    x_test = x_test.reshape(x_test.shape[0], 1,colors, img_rows, img_cols)
    input_shape = (1, colors, img_rows, img_cols)
else:
    x_train = x_train.reshape(x_train.shape[0], img_rows, img_cols, colors, 1)
    x_test = x_test.reshape(x_test.shape[0], img_rows, img_cols, colors, 1)
    input_shape = (img_rows, img_cols, colors, 1)


# Convert class vectors to binary class matrices.
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)

model = Sequential()
model.add(Conv3D(32, kernel_size=(3, 3, 3),activation='relu',input_shape=input_shape))
model.add(Conv3D(32, kernel_size=(3, 3, 3),activation='relu'))
model.add(MaxPooling3D(pool_size=(2, 2, 1)))
model.add(Dropout(0.25))
model.add(Conv3D(64, kernel_size=(3, 3, 3),activation='relu'))
model.add(Conv3D(64, kernel_size=(3, 3, 3),activation='relu'))
model.add(MaxPooling3D(pool_size=(2, 2, 1)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))

sgd=SGD(lr=learning_rate)


model.compile(loss=keras.losses.categorical_crossentropy,
              optimizer=sgd,
              metrics=['accuracy'])

history = model.fit(x_train, y_train,
          batch_size=batch_size,
          epochs=epochs,
          verbose=1,
          validation_data=(x_test, y_test))

score = model.evaluate(x_test, y_test, verbose=0)
print('Test loss:', score[0])
print('Test accuracy:', score[1])

我尝试过使用单个 conv3d，它有效但准确度很低。代码片段如下:

model = Sequential()
model.add(Conv3D(32, kernel_size=(3, 3, 3),activation='relu',input_shape=input_shape))
model.add(MaxPooling3D(pool_size=(2, 2, 1)))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))

Answer 1

问题

问题出在颜色 channel 上:它最初等于 3，您正在应用大小为 3 和 padding='valid' 的卷积。在第一个 Conv3D 之后，输出张量为:

(None, 30, 30, 1, 32)

... 并且不能对那个维度应用更多的卷积。您提供的简单示例之所以有效，是因为只有一个卷积层。

解决方案

您的一个选择是设置 padding='same'，以便保留张量形状:

(None, 32, 32, 3, 32)

但是，对我来说，颜色卷积并没有增加很多值(value)，所以我会选择这个模型:

model = Sequential()
model.add(Conv3D(32, kernel_size=(3, 3, 1), activation='relu', input_shape=input_shape))
model.add(Conv3D(32, kernel_size=(3, 3, 1), activation='relu'))
model.add(MaxPooling3D(pool_size=(2, 2, 1)))

model.add(Dropout(0.25))
model.add(Conv3D(64, kernel_size=(3, 3, 1), activation='relu'))
model.add(Conv3D(64, kernel_size=(3, 3, 1), activation='relu'))
model.add(MaxPooling3D(pool_size=(2, 2, 1)))
model.add(Dropout(0.25))
model.add(Flatten())
model.add(Dense(256, activation='relu'))
model.add(Dense(10, activation='softmax'))