PyTorch1.0安裝教程（附三個測試示例）
Summary：Python1.0安裝教程
Author：AmusiDate：2018-12-20github：https://github.com/amusi/PyTorch-From-Zero-To-One
知乎：https://www.zhihu.com/people/amusi1994微信公眾號：CVer
本文是在Ubuntu下進行PyTorch1.0正式版的安裝，Windows安裝教程與之類似，也可以參考該教程進行安裝：https://blog.csdn.net/amusi1994/article/details/80077667
PS：考慮出個PyTorch學習教程，一步步踩坑，一步步填坑
環境說明
- OS：Ubuntu16.04
- CUDA：8.0
- cudnn：6.0
- Python（conda）：3.6.4
安裝教程
官網：https://pytorch.org/
檢查Python環境
根據當前系統環境點擊選項
在終端輸入匹配的安裝PyTorch1.0的命令
conda install pytorch torchvision cuda80 -c pytorch
回車進行安裝，此時會有如下提示，當搜索到PyTorch1.0的相關packages時，輸入 y，確定繼續安裝。
註：此時可能會找不到相應的packages，比如Windows環境下。所以你可以添加相關的搜索源，如清華的源。此處可以自行百度解決。
此時需要等待一會兒（具體看網速），因為PyTorch 1.0.0這個packages有437.5 MB大小。
安裝成功後，會提示done。
載入PyTorch並輸出版本號，驗證是否安裝成功。
python
import torch
print(torch.__version__)
測試示例
測試1：檢查CUDA和CUDNN
創建並打開新的腳本文件pytorch_cudn_cudnn_test.py
touch pytorch_cudn_cudnn_test.py
gedit pytorch_cudn_cudnn_test.py
寫入測試代碼
# Summary: 檢測當前Pytorch和設備是否支持CUDA和cudnn
# Author: Amusi
# Date: 2018-12-20
# github: https://github.com/amusi/PyTorch-From-Zero-To-One
import torch
if __name__ == __main__:
print("Support CUDA ?: ", torch.cuda.is_available())
x = torch.Tensor([1.0])
xx = x.cuda()
print(xx)
y = torch.randn(2, 3)
yy = y.cuda()
print(yy)
zz = xx + yy
print(zz)
# CUDNN TEST
from torch.backends import cudnn
print("Support cudnn ?: ",cudnn.is_acceptable(xx))
運行該測試代碼
python pytorch_cudn_cudnn_test.py
輸入結果如下：
測試2：Tensors
創建並打開新的腳本文件pytorch_tensors.py
touch pytorch_tensors.py
gedit pytorch_tensors.py
寫入測試代碼：
# Summary：PyTorch的Tensor基礎知識
# Author: Amusi
# Date: 2018-12-20
# github: https://github.com/amusi/PyTorch-From-Zero-To-One
# Reference: http://pytorch.org/tutorials/beginner/pytorch_with_examples.html#pytorch-tensors
import torch
dtype = torch.FloatTensor
# dtype = torch.cuda.FloatTensor # Uncomment this to run on GPU
# N is batch size; D_in is input dimension;
# H is hidden dimension; D_out is output dimension.
N, D_in, H, D_out = 64, 1000, 100, 10
# Create random input and output data
x = torch.randn(N, D_in).type(dtype)
y = torch.randn(N, D_out).type(dtype)
# Randomly initialize weights
w1 = torch.randn(D_in, H).type(dtype)
w2 = torch.randn(H, D_out).type(dtype)
learning_rate = 1e-6
for t in range(500):
# Forward pass: compute predicted y
h = x.mm(w1)
h_relu = h.clamp(min=0)
y_pred = h_relu.mm(w2)
# Compute and print loss
loss = (y_pred - y).pow(2).sum()
print(t, loss)
# Backprop to compute gradients of w1 and w2 with respect to loss
grad_y_pred = 2.0 * (y_pred - y)
grad_w2 = h_relu.t().mm(grad_y_pred)
grad_h_relu = grad_y_pred.mm(w2.t())
grad_h = grad_h_relu.clone()
grad_h[h < 0] = 0
grad_w1 = x.t().mm(grad_h)
# Update weights using gradient descent
w1 -= learning_rate * grad_w1
w2 -= learning_rate * grad_w2
運行該測試代碼
python pytorch_tensors.py
輸入結果如下：
測試3：MNIST
創建並打開新的腳本文件pytorch_mnist.py
touch pytorch_mnist.py
gedit pytorch_mnist.py
寫入測試代碼：
# Summary: 使用PyTorch玩轉MNIST
# Author: Amusi
# Date: 2018-12-20
# github: https://github.com/amusi/PyTorch-From-Zero-To-One
# Reference: https://blog.csdn.net/victoriaw/article/details/72354307
from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable
# Training settings
parser = argparse.ArgumentParser(description=PyTorch MNIST Example)
parser.add_argument(--batch-size, type=int, default=64, metavar=N,
help=input batch size for training (default: 64))
parser.add_argument(--test-batch-size, type=int, default=1000, metavar=N,
help=input batch size for testing (default: 1000))
parser.add_argument(--epochs, type=int, default=10, metavar=N,
help=number of epochs to train (default: 10))
parser.add_argument(--lr, type=float, default=0.01, metavar=LR,
help=learning rate (default: 0.01))
parser.add_argument(--momentum, type=float, default=0.5, metavar=M,
help=SGD momentum (default: 0.5))
parser.add_argument(--no-cuda, action=store_true, default=False,
help=disables CUDA training)
parser.add_argument(--seed, type=int, default=1, metavar=S,
help=random seed (default: 1))
parser.add_argument(--log-interval, type=int, default=10, metavar=N,
help=how many batches to wait before logging training status)
args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed) #為CPU設置種子用於生成隨機數，以使得結果是確定的
if args.cuda:
torch.cuda.manual_seed(args.seed)#為當前GPU設置隨機種子；如果使用多個GPU，應該使用torch.cuda.manual_seed_all()為所有的GPU設置種子。
kwargs = {num_workers: 1, pin_memory: True} if args.cuda else {}
"""載入數據。組合數據集和採樣器，提供數據上的單或多進程迭代器
參數：
dataset：Dataset類型，從其中載入數據
batch_size：int，可選。每個batch載入多少樣本
shuffle：bool，可選。為True時表示每個epoch都對數據進行洗牌
sampler：Sampler，可選。從數據集中採樣樣本的方法。
num_workers：int，可選。載入數據時使用多少子進程。默認值為0，表示在主進程中載入數據。
collate_fn：callable，可選。
pin_memory：bool，可選
drop_last：bool，可選。True表示如果最後剩下不完全的batch,丟棄。False表示不丟棄。
"""
train_loader = torch.utils.data.DataLoader(
datasets.MNIST(../data, train=True, download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST(../data, train=False, transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.conv1 = nn.Conv2d(1, 10, kernel_size=5)#輸入和輸出通道數分別為1和10
self.conv2 = nn.Conv2d(10, 20, kernel_size=5)#輸入和輸出通道數分別為10和20
self.conv2_drop = nn.Dropout2d()#隨機選擇輸入的信道，將其設為0
self.fc1 = nn.Linear(320, 50)#輸入的向量大小和輸出的大小分別為320和50
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = F.relu(F.max_pool2d(self.conv1(x), 2))#conv->max_pool->relu
x = F.relu(F.max_pool2d(self.conv2_drop(self.conv2(x)), 2))#conv->dropout->max_pool->relu
x = x.view(-1, 320)
x = F.relu(self.fc1(x))#fc->relu
x = F.dropout(x, training=self.training)#dropout
x = self.fc2(x)
return F.log_softmax(x)
model = Net()
if args.cuda:
model.cuda()#將所有的模型參數移動到GPU上
optimizer = optim.SGD(model.parameters(), lr=args.lr, momentum=args.momentum)
def train(epoch):
model.train()#把module設成training模式，對Dropout和BatchNorm有影響
for batch_idx, (data, target) in enumerate(train_loader):
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data), Variable(target)#Variable類對Tensor對象進行封裝，會保存該張量對應的梯度，以及對生成該張量的函數grad_fn的一個引用。如果該張量是用戶創建的，grad_fn是None，稱這樣的Variable為葉子Variable。
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)#負log似然損失
loss.backward()
optimizer.step()
if batch_idx % args.log_interval == 0:
print(Train Epoch: {} [{}/{} ({:.0f}%)] Loss: {:.6f}.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
def test(epoch):
model.eval()#把module設置為評估模式，只對Dropout和BatchNorm模塊有影響
test_loss = 0
correct = 0
for data, target in test_loader:
if args.cuda:
data, target = data.cuda(), target.cuda()
data, target = Variable(data, volatile=True), Variable(target)
output = model(data)
test_loss += F.nll_loss(output, target).item()#Variable.data
pred = output.data.max(1)[1] # get the index of the max log-probability
correct += pred.eq(target.data).cpu().sum()
test_loss = test_loss
test_loss /= len(test_loader) # loss function already averages over batch size
print(
Test set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)
.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
if __name__ == __main__:
for epoch in range(1, args.epochs + 1):
train(epoch)
test(epoch)
運行該測試代碼
python pytorch_mnist.py
輸入結果如下：
參考
- https://pytorch.org/
- https://github.com/amusi/PyTorch-From-Zero-To-One
- https://blog.csdn.net/amusi1994/article/details/80077667
推薦閱讀：
