本文是PyTorch常用代码段合集,涵盖基本配置、张量处理、模型定义与操作、数据处理、模型训练与测试等5个方面,还给出了多个值得注意的Tips,内容非常全面。
PyTorch最好的资料是官方文档。本文是PyTorch常用代码段,在参考资料[1](张皓:PyTorch Cookbook)的基础上做了一些修补,方便使用时查阅
import torch
import torch.nn as nn
import torchvision
print(torch.__version__)
print(torch.version.cuda)
print(torch.backends.cudnn.version())
print(torch.cuda.get_device_name(0))
在硬件设备(CPU、GPU)不同时,完全的可复现性无法保证,即使随机种子相同。但是,在同一个设备上,应该保证可复现性。具体做法是,在程序开始的时候固定torch的随机种子
,同时也把numpy的随机种子固定。
np.random.seed(0)
torch.manual_seed(0)
torch.cuda.manual_seed_all(0)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
一张显卡
# Device configuration
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
多张显卡
,比如0,1号显卡。import os
os.environ['CUDA_VISIBLE_DEVICES'] = '0,1'
CUDA_VISIBLE_DEVICES=0,1 python train.py
torch.cuda.empty_cache()
nvidia-smi --gpu-reset -i [gpu_id]
tensor = torch.randn(3,4,5)
print(tensor.type()) # 数据类型
print(tensor.size()) # 张量的shape,是个元组
print(tensor.dim()) # 维度的数量
张量命名是一个非常有用的方法,这样可以方便地使用维度的名字来做索引或其他操作,大大提高了可读性、易用性,防止出错。
# 在PyTorch 1.3之前,需要使用注释
# Tensor[N, C, H, W]
images = torch.randn(32, 3, 56, 56)
images.sum(dim=1)
images.select(dim=1, index=0)
# PyTorch 1.3之后
NCHW = [‘N’, ‘C’, ‘H’, ‘W’]
images = torch.randn(32, 3, 56, 56, names=NCHW)
images.sum('C')
images.select('C', index=0)
# 也可以这么设置
tensor = torch.rand(3,4,1,2,names=('C', 'N', 'H', 'W'))
# 使用align_to可以对维度方便地排序
tensor = tensor.align_to('N', 'C', 'H', 'W')
# 设置默认类型,pytorch中的FloatTensor远远快于DoubleTensor
torch.set_default_tensor_type(torch.FloatTensor)
# 类型转换
tensor = tensor.cuda()
tensor = tensor.cpu()
tensor = tensor.float()
tensor = tensor.long()
除了CharTensor,其他所有CPU上的张量都支持转换为numpy格式然后再转换回来。
ndarray = tensor.cpu().numpy()
tensor = torch.from_numpy(ndarray).float()
tensor = torch.from_numpy(ndarray.copy()).float() # If ndarray has negative stride.
# pytorch中的张量默认采用[N, C, H, W]的顺序,并且数据范围在[0,1],需要进行转置和规范化
# torch.Tensor -> PIL.Image
image = PIL.Image.fromarray(torch.clamp(tensor*255, min=0, max=255).byte().permute(1,2,0).cpu().numpy())
image = torchvision.transforms.functional.to_pil_image(tensor) # Equivalently way
# PIL.Image -> torch.Tensor
path = r'./figure.jpg'
tensor = torch.from_numpy(np.asarray(PIL.Image.open(path))).permute(2,0,1).float() / 255
tensor = torchvision.transforms.functional.to_tensor(PIL.Image.open(path)) # Equivalently way
image = PIL.Image.fromarray(ndarray.astype(np.uint8))
ndarray = np.asarray(PIL.Image.open(path))
value = torch.rand(1).item()
# 在将卷积层输入全连接层的情况下通常需要对张量做形变处理,
# 相比torch.view,torch.reshape可以自动处理输入张量不连续的情况
tensor = torch.rand(2,3,4)
shape = (6, 4)
tensor = torch.reshape(tensor, shape)
tensor = tensor[torch.randperm(tensor.size(0))] # 打乱第一个维度
# pytorch不支持tensor[::-1]这样的负步长操作,水平翻转可以通过张量索引实现
# 假设张量的维度为[N, D, H, W].
tensor = tensor[:,:,:,torch.arange(tensor.size(3) - 1, -1, -1).long()]
# Operation
| New/Shared memory | Still in computation graph |tensor.clone()
# | New | Yes |tensor.detach() # | Shared | No |tensor.detach.clone()() # | New | No |
'''
注意torch.cat和torch.stack的区别在于torch.cat沿着给定的维度拼接,
而torch.stack会新增一维。例如当参数是3个10x5的张量,torch.cat的结果是30x5的张量,
而torch.stack的结果是3x10x5的张量。
'''
tensor = torch.cat(list_of_tensors, dim=0)
tensor = torch.stack(list_of_tensors, dim=0)
# pytorch的标记默认从0开始
tensor = torch.tensor([0, 2, 1, 3])
N = tensor.size(0)
num_classes = 4
one_hot = torch.zeros(N, num_classes).long()
one_hot.scatter_(dim=1, index=torch.unsqueeze(tensor, dim=1), src=torch.ones(N, num_classes).long())
torch.nonzero(tensor) # index of non-zero elements
torch.nonzero(tensor==0) # index of zero elements
torch.nonzero(tensor).size(0) # number of non-zero elements
torch.nonzero(tensor == 0).size(0) # number of zero elements
torch.allclose(tensor1, tensor2) # float tensor
torch.equal(tensor1, tensor2) # int tensor
# Expand tensor of shape 64*512 to shape 64*512*7*7.
tensor = torch.rand(64,512)
torch.reshape(tensor, (64, 512, 1, 1)).expand(64, 512, 7, 7)
# Matrix multiplcation: (m*n) * (n*p) * -> (m*p).
result = torch.mm(tensor1, tensor2)
# Batch matrix multiplication: (b*m*n) * (b*n*p) -> (b*m*p)
result = torch.bmm(tensor1, tensor2)
# Element-wise multiplication.
result = tensor1 * tensor2
利用广播机制
dist = torch.sqrt(torch.sum((X1[:,None,:] - X2) ** 2, dim=2))