Keras has an option that can cause the weights of the model to be non negative :
tf.keras.constraints.NonNeg()
What is the equivelent of this in pytorch? lets say my model is the one below, how should i change it to force the weights to be non negative ?
class LogisticRegression(torch.nn.Module):
def __init__(self, input_dim, output_dim):
super(LogisticRegression, self).__init__()
self.linear = torch.nn.Linear(input_dim, output_dim)
def forward(self, x):
outputs = self.linear(x)
return outputs