Python Amazon Web服务P3比使用Keras、TensorFlow和MobileNet的本地GPU慢

我目前正在用keras和tensorflow训练（微调）一个预训练的MobileNet模型。培训使用GTX980在我的本地计算机上完成

为了加快速度，我在AWS上创建了一个p3.2xlarge实例，其中包含一个基于Ubuntu（）的Amazon深度学习AMI

当运行一些测试数据（约300幅图像）时，我注意到我的本地计算机每个历元大约需要10秒，而aws需要26秒。我甚至用p3.16xlarge实例测试了它，但差别不大。当使用

所有内存（每个GPU 16GB）都已填满。我尝试了不同的数据量、keras实现、批量大小和提高GPU速度。列出设备时，GPU显示为已使用。跑得慢会有什么问题？我用的是jupyter笔记本。下面是我的测试代码：

from keras.applications import MobileNet
mobile_model = MobileNet()

for layer in mobile_model.layers[:-4]:
    layer.trainable = False

from keras import models
from keras import layers
from keras import optimizers

# Create the model
model = models.Sequential()

# Add the vgg convolutional base model
model.add(mobile_model)

# Add new layers
#model.add(layers.Flatten(return_sequences=True))
model.add(layers.Dense(1024, activation='relu'))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(2, activation='softmax'))

from keras.preprocessing.image import ImageDataGenerator

train_dir = "./painOrNoPain/train/"
validation_dir = "./painOrNoPain/valid/"
image_size = 224

train_datagen = ImageDataGenerator(
      rescale=1./255,
      rotation_range=20,
      width_shift_range=0.2,
      height_shift_range=0.2,
      horizontal_flip=True,
      fill_mode='nearest')

validation_datagen = ImageDataGenerator(rescale=1./255)

# Change the batchsize according to your system RAM
train_batchsize = 128
val_batchsize = 128

train_generator = train_datagen.flow_from_directory(
        train_dir,
        target_size=(image_size, image_size),
        batch_size=train_batchsize,
        class_mode='categorical')

validation_generator = validation_datagen.flow_from_directory(
        validation_dir,
        target_size=(image_size, image_size),
        batch_size=val_batchsize,
        class_mode='categorical',
        shuffle=False)

try:
    model = multi_gpu_model(model)
except:
    pass

from keras.optimizers import Adam
# Compile the model
model.compile(loss='categorical_crossentropy',
              optimizer=Adam(lr=1e-4),
              metrics=['acc'])
# Train the model
history = model.fit_generator(
      train_generator,
      steps_per_epoch=train_generator.samples/train_generator.batch_size ,
      epochs=3,
      validation_data=validation_generator,
      validation_steps=validation_generator.samples/validation_generator.batch_size,
      verbose=2)

# Save the model
model.save('small_last4.h5')

---

我也有同样的问题。使用Amazon AWS GPU运行甚至比在我自己的笔记本电脑上使用CPU运行还要慢。一个可能的解释是由于CPU和GPU之间的数据传输花费了大量的时间，如

中所述，我也有同样的问题。使用Amazon AWS GPU运行甚至比在我自己的笔记本电脑上使用CPU运行还要慢。一种可能的解释是，如中所述，CPU和GPU之间的数据传输花费了大量时间

from keras.applications import MobileNet
mobile_model = MobileNet()

for layer in mobile_model.layers[:-4]:
    layer.trainable = False

from keras import models
from keras import layers
from keras import optimizers

# Create the model
model = models.Sequential()

# Add the vgg convolutional base model
model.add(mobile_model)

# Add new layers
#model.add(layers.Flatten(return_sequences=True))
model.add(layers.Dense(1024, activation='relu'))
model.add(layers.Dropout(0.5))
model.add(layers.Dense(2, activation='softmax'))

from keras.preprocessing.image import ImageDataGenerator

train_dir = "./painOrNoPain/train/"
validation_dir = "./painOrNoPain/valid/"
image_size = 224

train_datagen = ImageDataGenerator(
      rescale=1./255,
      rotation_range=20,
      width_shift_range=0.2,
      height_shift_range=0.2,
      horizontal_flip=True,
      fill_mode='nearest')

validation_datagen = ImageDataGenerator(rescale=1./255)

# Change the batchsize according to your system RAM
train_batchsize = 128
val_batchsize = 128

train_generator = train_datagen.flow_from_directory(
        train_dir,
        target_size=(image_size, image_size),
        batch_size=train_batchsize,
        class_mode='categorical')

validation_generator = validation_datagen.flow_from_directory(
        validation_dir,
        target_size=(image_size, image_size),
        batch_size=val_batchsize,
        class_mode='categorical',
        shuffle=False)

try:
    model = multi_gpu_model(model)
except:
    pass

from keras.optimizers import Adam
# Compile the model
model.compile(loss='categorical_crossentropy',
              optimizer=Adam(lr=1e-4),
              metrics=['acc'])
# Train the model
history = model.fit_generator(
      train_generator,
      steps_per_epoch=train_generator.samples/train_generator.batch_size ,
      epochs=3,
      validation_data=validation_generator,
      validation_steps=validation_generator.samples/validation_generator.batch_size,
      verbose=2)

# Save the model
model.save('small_last4.h5')