Floras16比keras中的float32慢

Question

我正在测试我的新NVIDIA Titan V,它支持float16操作.我注意到在训练期间,float16比float32(~500 ms /步)慢得多(~800 ms /步).

要执行float16操作,我将keras.json文件更改为:

{
"backend": "tensorflow",
"floatx": "float16",
"image_data_format": "channels_last",
"epsilon": 1e-07
}

为什么float16操作这么慢？我是否需要修改我的代码而不仅仅是keras.json文件？

我在Windows 10上使用CUDA 9.0,cuDNN 7.0,tensorflow 1.7.0和keras 2.1.5.我的python 3.5代码如下:

img_width, img_height = 336, 224

train_data_dir = 'C:\\my_dir\\train'
test_data_dir = 'C:\\my_dir\\test'
batch_size=128

datagen = ImageDataGenerator(rescale=1./255,
    horizontal_flip=True,   # randomly flip the images 
    vertical_flip=True) 

train_generator = datagen.flow_from_directory(
    train_data_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary')

test_generator = datagen.flow_from_directory(
    test_data_dir,
    target_size=(img_height, img_width),
    batch_size=batch_size,
    class_mode='binary')

# Architecture of NN
model = Sequential()
model.add(Conv2D(32,(3, 3), input_shape=(img_height, img_width, 3),padding='same',kernel_initializer='lecun_normal'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

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

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

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

model.add(AveragePooling2D(pool_size=(2,2)))
model.add(Flatten())
model.add(Dense(1))
model.add(Activation('sigmoid'))

my_rmsprop = keras.optimizers.RMSprop(lr=0.0001, rho=0.9, epsilon=1e-04, decay=0.0)
model.compile(loss='binary_crossentropy',
          optimizer=my_rmsprop,
          metrics=['accuracy'])

# Training 
nb_epoch = 32
nb_train_samples = 512
nb_test_samples = 512

model.fit_generator(
    train_generator,
    steps_per_epoch=nb_train_samples/batch_size,
    epochs=nb_epoch,
    verbose=1,
    validation_data=test_generator,
    validation_steps=nb_test_samples/batch_size)

# Evaluating on the testing set
model.evaluate_generator(test_generator, nb_test_samples)

Answer 1

我更新到 CUDA 10.0、cuDNN 7.4.1、tensorflow 1.13.1、keras 2.2.4 和 python 3.7.3。使用与 OP 中相同的代码，float16 的训练时间比 float32 稍微快一些。

我完全期望更复杂的网络架构会在性能上表现出更大的差异，但我没有对此进行测试。