Pytorch
跳到导航
跳到搜索
网络初始化
- Xavier and Kaiming initialization [4]
数据准备
import torch import torch.utils.data as Data torch.manual_seed(1) # reproducible BATCH_SIZE = 5 # 批训练的数据个数 x = torch.linspace(1, 10, 10) # x data (torch tensor) y = np.arange(1, 10) y = torch.from_numpy(y) #numpy ndarray to torch tensor torch_dataset = Data.TensorDataset(x, y) # 换成 torch 能识别的 Dataset # 把 dataset 放入 DataLoader loader = Data.DataLoader( dataset=torch_dataset, # torch TensorDataset format batch_size=BATCH_SIZE, # mini batch size shuffle=True, # 要不要打乱数据 (打乱比较好) num_workers=2, # 多线程来读数据 )
nan问题
- 第一个是判断条件,第二个是符合条件的设置值,第三个是不符合条件的设置值。
a = torch.Tensor([[1, 2, np.nan], [2, np.nan, 4], [3, 4, 5]]) a = torch.where(torch.isnan(a), torch.full_like(a, 0), a)
函数
- torch.clamp(input, min=None, max=None, *, out=None) → Tensor
- Clamps all elements in input into the range [ min, max ]. Letting min_value and max_value be min and max, respectively
- torch.eye(n, m=None, out=None)
- 返回一个2维张量,对角线位置全1,其它位置全0
- torch.view()
- 相当于numpy的reshape,某个维度上等于-1,就是让计算机自己算一下这一维度上应该有多少
- torch.cat & torch.stack
- orch.stack()沿着一个新维度对输入张量序列进行连接。 序列中所有的张量都应该为相同形状。
- torch.cat()是为了把函数torch.stack()得到tensor进行拼接而存在的 (不增加新的维度)
- gather
- In PyTorch you can perform the same operation using the gather() method. If s is a PyTorch Tensor of shape (N, C) and y is a PyTorch Tensor of shape (N,) containing longs in the range 0 <= y[i] < C, then s.gather(1, y.view(-1, 1)).squeeze() will be a PyTorch Tensor of shape (N,) containing one entry from each row of s, selected according to the indices in y.
- squeeze()
- 删除一个张量中所有维数为1的维度
Tensor
- cpu() numpy() detach() item() [5]
- 注意cuda上面的变量类型只能是tensor,不能是其他
torchvision
- PyTorch框架中有一个非常重要且好用的包:torchvision,该包主要由3个子包组成,分别是:torchvision.datasets、torchvision.models、torchvision.transforms [6]
- __all__ = ["Compose", "ToTensor", "ToPILImage", "Normalize", "Resize",
"Scale", "CenterCrop", "Pad", "Lambda", "RandomCrop", "RandomHorizontalFlip", "RandomVerticalFlip", "RandomResizedCrop", "RandomSizedCrop", "FiveCrop", "TenCrop","LinearTransformation", "ColorJitter", "RandomRotation", "Grayscale", "RandomGrayscale"]
第三方库
- thop
- THOP 是 PyTorch 非常实用的一个第三方库,可以统计模型的 FLOPs 和参数量。
from thop import clever_format from thop import profile class YourModule(nn.Module): # your definition input = torch.randn(10, 128, 128) flops, params = profile(model, inputs=(input, )) flops, params = clever_format([flops, params], "%.3f")