Question

几天前，我才刚刚开始学习深度学习。我正在尝试使用包含猫和狗图片的数据集来训练CNN。

但是问题是训练过程在CPU上花费的时间太长，而且我可以看到在训练期间我的CPU使用率没有显着提高。而且培训过程运行非常缓慢。我以为是因为CPU，所以我继续安装CUDA和TensorFlow-gpu，Tensorflow-gpu似乎可以在控制台上显示图形卡。

Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 4620 MB memory) -> physical GPU (device: 0, name: GeForce RTX 2060, pci bus id: 0000:1c:00.0, compute capability: 7.5)

但是在GPU上的训练速度似乎比在CPU上慢。

在训练模型时，它会占用所有GPU内存，但训练时GPU利用率似乎很低。你们能检查我在做什么错吗？以及如何加快速度？

系统规格：

CPU：Ryzen 2700x

GPU：ZOTAC RTX 2060

RAM：DDR4 16GB 3000 MHZ

我正在使用的代码：

import keras as keras
from keras.models import Sequential
from keras.layers import Conv2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense

# Initialising the CNN
classifier = Sequential()

# Step 1 - Convolution
classifier.add(Conv2D(32, (3, 3), input_shape = (64, 64, 3), activation = 'relu'))

# Step 2 - Pooling
classifier.add(MaxPooling2D(pool_size = (2, 2)))

# Adding a second convolutional layer
classifier.add(Conv2D(32, (3, 3), activation = 'relu'))
classifier.add(MaxPooling2D(pool_size = (2, 2)))

# Step 3 - Flattening
classifier.add(Flatten())

# Step 4 - Full connection
classifier.add(Dense(units = 128, activation = 'relu'))
classifier.add(Dense(units = 1, activation = 'sigmoid'))

# Compiling the CNN
classifier.compile(optimizer = 'adadelta', loss = 'binary_crossentropy', metrics = ['accuracy'])

# Part 2 - Fitting the CNN to the images

from keras.preprocessing.image import ImageDataGenerator

train_datagen = ImageDataGenerator(rescale = 1./255,
                                   shear_range = 0.2,
                                   zoom_range = 0.2,
                                   horizontal_flip = True)

test_datagen = ImageDataGenerator(rescale = 1./255)

training_set = train_datagen.flow_from_directory('dataset/training_set',
                                                 target_size = (64, 64),
                                                 batch_size = 32,
                                                 class_mode = 'binary')

test_set = test_datagen.flow_from_directory('dataset/test_set',
                                            target_size = (64, 64),
                                            batch_size = 32,
                                            class_mode = 'binary')

classifier.fit_generator(training_set,
                         steps_per_epoch = 8000,
                         epochs = 35,
                         validation_data = test_set,
                         validation_steps = 20)

print("================== Saving Model ==========================")
classifier.save('./model.h5')
print("=================  Model Saved  ==========================")

速度：

  20/8000 [..............................] - ETA: 10:47 - loss: 0.0269 - acc: 0.9906

Keras在GPU上的训练性能比CPU慢

0 个答案: