pytorch 张量处理

张量处理

张量基本信息

tensor = torch.randn(3,4,5)
print(tensor.type())  # 数据类型
print(tensor.size())  # 张量大小
print(tensor.dim())   # 维度的数量

张量命名

NCHW = [‘N’, ‘C’, ‘H’, ‘W’] 
images = torch.randn(32, 3, 56, 56, names=NCHW) 
images.sum('C') 
images.select('C', index=0)

torch.Tensor与np.ndarray转换

ndarray = tensor.cpu().numpy() 
tensor = torch.from_numpy(ndarray).float() 

Torch.tensor与PIL.Image转换

# torch.Tensor -> PIL.Image 
image = torchvision.transforms.functional.to_pil_image(tensor) 
# PIL.Image -> torch.Tensor 
path = r'./figure.jpg' 
tensor =torchvision.transforms.functional.to_tensor(PIL.Image.open(path))

np.ndarray与PIL.Image的转换

image = PIL.Image.fromarray(ndarray.astype(np.uint8))
ndarray = np.asarray(PIL.Image.open(path))

张量拼接

torch.cat()：沿着给定的维度拼接

torch.stack()：新增一个维度

tensor = torch.cat(list_of_tensors, dim=0) 
tensor = torch.stack(list_of_tensors, dim=0)

将整数标签转为one-hot编码

# 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())

矩阵乘法

# 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

模型定义

两层卷积网络的示例

class ConvNet(nn.Module): 
    def __init__(self, num_classes=10): 
        super(ConvNet, self).__init__() 
        self.layer1 = nn.Sequential(
                      nn.Conv2d(1, 16, kernel_size=5, stride=1, padding=2), 
    		              nn.BatchNorm2d(16), 
    		              nn.ReLU(), 
    		              nn.MaxPool2d(kernel_size=2, stride=