search

zhang-tao-whu / e2ec

E2EC: An End-to-End Contour-based Method for High-Quality High-Speed Instance Segmentation
Other
214 stars 45 forks source link

Train in own dataset #18

Closed aichifandefan closed 2 years ago

aichifandefan commented 2 years ago

How to train ous dataset? when i train in my dataset it get

pos_loss = torch.log(pred) * torch.pow(1 - pred, 2) * pos_inds
RuntimeError: The size of tensor a (80) must match the size of tensor b (2) at non-singleton dimension 1

Is the classes number problem? I can not find the classes config

aichifandefan commented 2 years ago

My dataset have 2 classes, blackground and book.

aichifandefan commented 2 years ago

Yeah I find de classes parameters model.heads['ct_hm'] = 80 when i change it to 2 it can run