loss fuction:
(1)计算实际输出和目标之间的差距
(2)为我们更新输出提供一定的依据(反向传播)
#nn.loss
inputs = torch.tensor([1,2,3], dtype = torch.float32)
targets = torch.tensor([1,2,5], dtype = torch.float32)
inputs = torch.reshape(inputs, (1,1,1,3))
targets = torch.reshape(targets,(1,1,1,3)))
loss = nn.L1Loss()
result = loss(inputs, targets)
print(result)
# MSELoss
lose_mse = nn.MSELoss()
result_mse = loss_mse(inputs,targets)
print(result_mse)
#CrossEntropyLoss
x = torch.tensor([0.1,0.2,0.3])
y = torch.tensor([1])
x = torch.reshape(x, (1,3))
loss_cross = nn.CrossEntropyLoss()
ressult_cross = loss_cross(x,y)
dataset = torchvision.datasets.CIFAR10("./dataset", train = False, transform = torchvision.transforms.ToTensor(), download=True)
dataloder= DataLoader(dataset, batch_size=1)
class Model_test(nn.Module):
def __init__(self):
super(Model_test, self).__init__()
self.model1 = Sequential(
Conv2d(3, 32,5,padding=2),
MaxPool2d(2),
Conv2d(32, 32,5,padding=2),
MaxPool2d(2),
Flatten(),
Linear(1024, 64),
Linear(64, 10))
def forward(self, x):
x = self.model1(x)
return x
loss = nn.CrossEntropyLoss()
model_test = Model_test()
for data in dataloader:
imgs, targets = data
outputs = model_test(imgs)
result_loss = loss(outputs, targets)
print(result_loss)
result_loss.backward() #反向传播
print("ok")
writer = SummaryWriter("logs_Sequential")
writer.add_graph(model_test, input)
writer.close()
#terminal :tensorboard --logdir=logs_Sequential