深度学习环境搭建极简教程(win10+cuda_9.0)
开始入深度学习的坑了,记录一次环境搭建记录
看着别的博客安装贼复杂,我这个算是贼简单。
- 首先安装好vs2017 勾选C++
- 然后再下面的操作
1.Python环境
直接安装Python 3.6.8 64位,不需要安装臃肿的Anaconda。
2.CUDA 9.0
cuda_9.0.176_win10
如果安装不上,完全卸载显卡驱动,推荐使用工具Display Driver Uninstaller (DDU) V17.0.8.5 Released在安全模式下卸载显卡驱动后再正常安装
3.CuDNN
cudnn-9.0-windows10-x64-v7.4.2.24
下载完成后,解压复制到Toolkit目录下即可
4.安装Keras和Tensorflow-GPU
pip install Keras
pip install Tensorflow-GPU
5.Hello World
from keras import models
from keras import layers
from keras.datasets import mnist
from keras.utils import to_categorical
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()
network = models.Sequential()
network.add(layers.Dense(512, activation='relu', input_shape=(28 * 28,)))
network.add(layers.Dense(10, activation='softmax'))
network.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
train_images = train_images.reshape((60000, 28 * 28))
train_images = train_images.astype('float32') / 255
test_images = test_images.reshape((10000, 28 * 28))
test_images = test_images.astype('float32') / 255
train_labels = to_categorical(train_labels)
test_labels = to_categorical(test_labels)
network.fit(train_images, train_labels, epochs=5, batch_size=128)
test_loss, test_acc = network.evaluate(test_images, test_labels)
print('test_acc:', test_acc)