- 在pytorch中想自定义求导函数,通过实现torch.autograd.Function并重写forward和backward函数,来定义自己的自动求导运算。参考官网上的demo:传送门
- 直接上代码,定义一个ReLu来实现自动求导
import torch class MyRelu(torch.autograd.Function): @staticmethod def forward(ctx, input): ctx.save_for_backward(input) return input.clamp(min = 0) @staticmethod def backward(ctx, grad_output): input, = ctx.saved_tensors grad_input = grad_output.clone() grad_input[input < 0] = 0 return grad_input
- 进行输入数据并测试
dtype = torch.float device = torch.device('cuda' if torch.cuda.is_available() else 'cpu') generator=torch.Generator(device).manual_seed(42) N, D_in, H, D_out = 64, 1000, 100, 10 x = torch.randn(N, D_in, device=device, dtype=dtype,generator=generator) y = torch.randn(N, D_out, device=device, dtype=dtype, generator=generator) w1 = torch.randn(D_in, H, device=device, dtype=dtype, requires_grad=True, generator=generator) w2 = torch.randn(H, D_out, device=device, dtype=dtype, requires_grad=True, generator=generator) learning_rate = 1e-6 for t in range(500): relu = MyRelu.apply y_pred = relu(x.mm(w1)).mm(w2) loss = (y_pred - y).pow(2).sum() if t % 100 == 99: print(t, loss.item()) loss.backward() with torch.no_grad(): w1 -= learning_rate * w1.grad w2 -= learning_rate * w2.grad w1.grad.zero_() w2.grad.zero_()
- 暂时先做这些测试,如有问题,恳请指正