I’m doing weight clipping, and I’d like to learn an optimal clipping threshold:

```
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.w_max = nn.Parameter(torch.Tensor([0]), requires_grad=True)
self.conv1 = nn.Conv2d(3, 32, kernel_size=5)
self.conv2 = nn.Conv2d(32, 64, kernel_size=5)
self.pool = nn.MaxPool2d(2, 2)
self.relu = nn.ReLU()
self.linear = nn.Linear(64 * 5 * 5, 10)
def forward(self, input):
conv1 = self.conv1(input)
pool1 = self.pool(conv1)
relu1 = self.relu(pool1)
conv2 = self.conv2(relu1)
pool2 = self.pool(conv2)
relu2 = self.relu(pool2)
relu2 = relu2.view(relu2.size(0), -1)
return self.linear(relu2)
model = Net()
torch.nn.init.kaiming_normal_(model.parameters)
nn.init.constant(model.w_max, 0.1)
optimizer = torch.optim.SGD(model.parameters(), lr=0.001)
for epoch in range(100):
for i in range(1000):
output = model(input)
loss = nn.CrossEntropyLoss()(output, label)
optimizer.zero_grad()
loss.backward()
optimizer.step()
model.conv1.weight[model.conv1.weight >= model.w_max] = model.w_max
```

I want the gradient of w_max to be the sum of gradients of all weights above w_max

This works fine for activation clipping thresholds, but for weights I get

TypeError: cannot assign ‘torch.cuda.FloatTensor’ as parameter ‘weight’ (torch.nn.Parameter or None expected)

How do I do this?