Is there any parameter that I can pass to md.get_learner to specify the last layer activation ?
You can just copy the MixedInputModel from column_data.py and costumize like you want. But if it is a multilabel classification the last activation will be sigmoid by default.
Here is the code for the forward() method of the MixedInputModel:
def forward(self, x_cat, x_cont):
if self.n_emb != 0:
x = [e(x_cat[:,i]) for i,e in enumerate(self.embs)]
x = torch.cat(x, 1)
x = self.emb_drop(x)
if self.n_cont != 0:
x2 = self.bn(x_cont)
x = torch.cat([x, x2], 1) if self.n_emb != 0 else x2
for l,d,b in zip(self.lins, self.drops, self.bns):
x = F.relu(l(x))
if self.use_bn: x = b(x)
x = d(x)
x = self.outp(x)
if not self.is_reg:
if self.is_multi:
x = F.sigmoid(x)
else:
x = F.log_softmax(x)
elif self.y_range:
x = F.sigmoid(x)
x = x*(self.y_range[1] - self.y_range[0])
x = x+self.y_range[0]
return x