Keras：卷积神经网络多分类器。

Question

在使用Keras官方的二元分类例子（参见此处）之后，我正在使用Tensorflow作为后端实现多类分类器。在这个例子中，有两个类别（狗/猫），而我现在有50个类别，并且数据以相同的方式存储在文件夹中。

训练时，损失值不会下降，准确率也不会提高。我已将最后一层从使用sigmoid函数改为使用softmax函数，将binary_crossentropy更改为categorical_crossentropy，将class_mode更改为categorical。

以下是我的代码：

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
import keras.optimizers



optimizer = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)

# dimensions of our images.
img_width, img_height = 224, 224

train_data_dir = 'images/train'
validation_data_dir = 'images/val'
nb_train_samples = 209222
nb_validation_samples = 40000
epochs = 50
batch_size = 16

if K.image_data_format() == 'channels_first':
    input_shape = (3, img_width, img_height)
else:
    input_shape = (img_width, img_height, 3)

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(50))
model.add(Activation('softmax'))



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


train_datagen = ImageDataGenerator()

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

validation_generator = train_datagen.flow_from_directory(
    directory=validation_data_dir,
    target_size=(img_width, img_height),
    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.save_weights('weights.h5')

您有什么想法，我可能做错了什么吗？ 非常感谢您的任何意见！

编辑： 根据 @RobertValencia 的要求，以下是最新培训日志的开头：

Using TensorFlow backend.
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcublas.so.7.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcudnn.so.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcufft.so.7.5 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcuda.so.1 locally
I tensorflow/stream_executor/dso_loader.cc:135] successfully opened CUDA library libcurand.so.7.5 locally
Found 3517 images belonging to 50 classes.
<keras.preprocessing.image.DirectoryIterator object at 0x7fd1d4515c10>
Found 2451 images belonging to 50 classes.
Epoch 1/50
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE3 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
I tensorflow/stream_executor/cuda/cuda_gpu_executor.cc:910] successful NUMA node read from SysFS had negative value (-1), but there must be at least one NUMA node, so returning NUMA node zero
I tensorflow/core/common_runtime/gpu/gpu_device.cc:885] Found device 0 with properties: 
name: GRID K520
major: 3 minor: 0 memoryClockRate (GHz) 0.797
pciBusID 0000:00:03.0
Total memory: 3.94GiB
Free memory: 3.91GiB
I tensorflow/core/common_runtime/gpu/gpu_device.cc:906] DMA: 0 
I tensorflow/core/common_runtime/gpu/gpu_device.cc:916] 0:   Y 
I tensorflow/core/common_runtime/gpu/gpu_device.cc:975] Creating TensorFlow device (/gpu:0) -> (device: 0, name: GRID K520, pci bus id: 0000:00:03.0)
 8098/13076 [=================>............] - ETA: 564s - loss: 15.6869 - categorical_accuracy: 0.0267   

- Graham Slick

---

你的优化器设置怎么了？为什么动量那么小，还为什么禁用nesterov momentum？ - nemo

@nemo 谢谢，我复制了错误的优化器代码。已经进行了修改。但是我遇到了这个问题：optimizer = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)（如帖子所述）。 - Graham Slick

你能否尝试使用categorical_accuracy替代accuracy作为你的度量指标？ - Robert Valencia

@GrahamSlick，你能给我们展示一下你的训练日志吗？ - Robert Valencia

@RobertValencia 刚刚将其添加到问题中。 - Graham Slick

Answer 1

考虑到您需要区分的类别数量，也许增加模型的复杂性，并使用不同的优化器，可以获得更好的结果。尝试使用这个模型，它部分基于VGG-16 CNN架构，但不是那么复杂：

model = Sequential()
model.add(Convolution2D(32, 3, 3, activation='relu'))
model.add(Convolution2D(32, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(Convolution2D(64, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(Convolution2D(128, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(Convolution2D(256, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(Convolution2D(512, 3, 3, activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(Flatten())
model.add(Dense(1024, activation='relu'))
model.add(Dense(1024, activation='relu'))
model.add(Dense(50, activation='softmax'))

optimizer = Nadam(lr=0.002,
                  beta_1=0.9,
                  beta_2=0.999,
                  epsilon=1e-08,
                  schedule_decay=0.004)

model.compile(loss='categorical_crossentropy',
              optimizer=optimizer,
              metrics=['categorical_accuracy'])

如果你想要更好的结果，我建议你看一下VGG-16模型：

1. https://github.com/fchollet/keras/blob/master/keras/applications/vgg16.py 或者
2. https://gist.github.com/baraldilorenzo/07d7802847aaad0a35d3（包括零填充和dropout层）

- Robert Valencia

---

谢谢，我会尝试一下。但是这似乎只能将模型的准确率从80%提高到95%，而不能将其从3%提高到95%。不过我会在几个小时后尝试并告诉你结果。 - Graham Slick

好的。如果你得到了更好的结果，请告诉我们。我也很想知道它的结局。 - Robert Valencia