Minyue Jiang issues

Repositories
Issues
Comments

Results 2 issues of


                                            Minyue Jiang

why convert the Variable(imgs) to [Variable(imgs)] (it makes more complicated) and without .cuda()?

1) In trainer,the code is: inputs = [Variable(imgs)] outputs = self.model(*inputs) but the simple way is : inputs = Variable(imgs) outputs = self.model(inputs) 2) why not .cuda() of the imgs...

why using num_sample in mean_ap L122. In my opinion, the usage of num_sample is to interpolate gt, but points in each polyline is different between prediction and gt

https://github.com/hustvl/MapTR/blob/main/projects/mmdet3d_plugin/datasets/map_utils/mean_ap.py#L122 This is the detailed code url