Open liangjxiong opened 1 year ago
The following error occurred when I used parameter --two_stage during training. What should I do?
enc_outputs_coord_unact = self.decoder.bbox_embed[self.decoder.num_layers](output_memory) + output_proposals
TypeError: 'NoneType' object is not subscriptable
How should I define self.decoder.class_embed and self.decoder.bbox_embed?
I meet the same issue. Did you solve it?
I found the problem. When we set the --two_stage as True, we also need to set --with_box_refine as True. Thx
The following error occurred when I used parameter --two_stage during training. What should I do?
TypeError: 'NoneType' object is not subscriptable
How should I define self.decoder.class_embed and self.decoder.bbox_embed?