MNIST_ModelManifoldBoundary 源码

通过模型流形边界简化模型 参考 autograd-hacks 从PyTorch autograd提取有用的数量 每个示例的渐变 autograd_hacks.add_hooks(model) output = model(data) loss_fn(output, targets).backward() autograd_hacks.compute_grad1() # param.grad: gradient averaged over the batch # param.grad1[i]: gradient with respect to example i for param in model.parameters(): assert(torch.allclose(param.grad1.mean(dim=0), param.grad))