tensorflow - 如何确保 Keras 使用带有 tensorflow 后端的 GPU？

Question

我在 Paperspace 云基础架构上创建了虚拟笔记本，后端使用 Tensorflow GPU P5000 虚拟实例。
当我开始训练我的网络时，它比使用纯 CPU 运行时引擎的 MacBook Pro 慢 2 倍。
我如何确保 Keras NN 在训练过程中使用 GPU 而不是 CPU？

请在下面找到我的代码:

from tensorflow.contrib.keras.api.keras.models import Sequential
from tensorflow.contrib.keras.api.keras.layers import Dense
from tensorflow.contrib.keras.api.keras.layers import Dropout
from tensorflow.contrib.keras.api.keras import utils as np_utils
import numpy as np
import pandas as pd

# Read data
pddata= pd.read_csv('data/data.csv', delimiter=';')

# Helper function (prepare & test data)
def split_to_train_test (data):
    trainLenght = len(data) - len(data)//10

    trainData = data.loc[:trainLenght].sample(frac=1).reset_index(drop=True)
    testData = data.loc[trainLenght+1:].sample(frac=1).reset_index(drop=True)

    trainLabels = trainData.loc[:,"Label"].as_matrix()
    testLabels = testData.loc[:,"Label"].as_matrix()

    trainData = trainData.loc[:,"Feature 0":].as_matrix()
    testData  = testData.loc[:,"Feature 0":].as_matrix()

    return (trainData, testData, trainLabels, testLabels)

# prepare train & test data
(X_train, X_test, y_train, y_test) = split_to_train_test (pddata)

# Convert labels to one-hot notation
Y_train = np_utils.to_categorical(y_train, 3)
Y_test  = np_utils.to_categorical(y_test, 3)

# Define model in Keras
def create_model(init):
    model = Sequential()
    model.add(Dense(101, input_shape=(101,), kernel_initializer=init, activation='tanh'))
    model.add(Dense(101, kernel_initializer=init, activation='tanh'))
    model.add(Dense(101, kernel_initializer=init, activation='tanh'))
    model.add(Dense(101, kernel_initializer=init, activation='tanh'))
    model.add(Dense(3, kernel_initializer=init, activation='softmax'))
    return model

# Train the model
uniform_model = create_model("glorot_normal")
uniform_model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
uniform_model.fit(X_train, Y_train, batch_size=1, epochs=300, verbose=1, validation_data=(X_test, Y_test)) 

Answer 1

您需要使用 log_device_placement = True 运行您的网络在 TensorFlow session 中设置(下面示例代码中最后一行之前的行)。有趣的是，如果您在 session 中设置它，当 Keras 进行拟合时它仍然适用。所以下面的这段代码(经过测试)确实输出了每个张量的位置。请注意，由于您的数据不可用，我已将数据读取短路，所以我只是使用随机数据运行网络。这种方式的代码是自包含的，任何人都可以运行。另一个注意事项:如果您从 Jupyter Notebook 运行它，log_device_placement 的输出会去启动 Jupyter Notebook 的终端 ，不是笔记本电池的输出。

from tensorflow.contrib.keras.api.keras.models import Sequential
from tensorflow.contrib.keras.api.keras.layers import Dense
from tensorflow.contrib.keras.api.keras.layers import Dropout
from tensorflow.contrib.keras.api.keras import utils as np_utils
import numpy as np
import pandas as pd
import tensorflow as tf

# Read data
#pddata=pd.read_csv('data/data.csv', delimiter=';')
pddata = "foobar"

# Helper function (prepare & test data)
def split_to_train_test (data):

    return (
        np.random.uniform( size = ( 100, 101 ) ),
        np.random.uniform( size = ( 100, 101 ) ),
        np.random.randint( 0, size = ( 100 ), high = 3 ),
        np.random.randint( 0, size = ( 100 ), high = 3 )
    )

    trainLenght = len(data) - len(data)//10

    trainData = data.loc[:trainLenght].sample(frac=1).reset_index(drop=True)
    testData = data.loc[trainLenght+1:].sample(frac=1).reset_index(drop=True)

    trainLabels = trainData.loc[:,"Label"].as_matrix()
    testLabels = testData.loc[:,"Label"].as_matrix()

    trainData = trainData.loc[:,"Feature 0":].as_matrix()
    testData  = testData.loc[:,"Feature 0":].as_matrix()

    return (trainData, testData, trainLabels, testLabels)

# prepare train & test data
(X_train, X_test, y_train, y_test) = split_to_train_test (pddata)

# Convert labels to one-hot notation
Y_train = np_utils.to_categorical(y_train, 3)
Y_test  = np_utils.to_categorical(y_test, 3)

# Define model in Keras
def create_model(init):
    model = Sequential()
    model.add(Dense(101, input_shape=(101,), kernel_initializer=init, activation='tanh'))
    model.add(Dense(101, kernel_initializer=init, activation='tanh'))
    model.add(Dense(101, kernel_initializer=init, activation='tanh'))
    model.add(Dense(101, kernel_initializer=init, activation='tanh'))
    model.add(Dense(3, kernel_initializer=init, activation='softmax'))
    return model

# Train the model
uniform_model = create_model("glorot_normal")
uniform_model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
with tf.Session( config = tf.ConfigProto( log_device_placement = True ) ):
    uniform_model.fit(X_train, Y_train, batch_size=1, epochs=300, verbose=1, validation_data=(X_test, Y_test)) 

终端输出(部分，太长了):

...
VarIsInitializedOp_13: (VarIsInitializedOp): /job:localhost/replica:0/task:0/device:GPU:0
2018-04-21 21:54:33.485870: I tensorflow/core/common_runtime/placer.cc:884]
VarIsInitializedOp_13: (VarIsInitializedOp)/job:localhost/replica:0/task:0/device:GPU:0
training/SGD/mul_18/ReadVariableOp: (ReadVariableOp): /job:localhost/replica:0/task:0/device:GPU:0
2018-04-21 21:54:33.485895: I tensorflow/core/common_runtime/placer.cc:884]
training/SGD/mul_18/ReadVariableOp: (ReadVariableOp)/job:localhost/replica:0/task:0/device:GPU:0
training/SGD/Variable_9/Read/ReadVariableOp: (ReadVariableOp): /job:localhost/replica:0/task:0/device:GPU:0
2018-04-21 21:54:33.485903: I tensorflow/core/common_runtime/placer.cc:884]
training/SGD/Variable_9/Read/ReadVariableOp: (ReadVariableOp)/job:localhost/replica:0/task:0/device:GPU:0
...

请注意 GPU:0 在许多行的末尾。

Tensorflow 手册的相关页面: Using GPU: Logging Device Placement .