Hardik Kamboj comments

Results 3 comments of


                                            Hardik Kamboj

Ch2 Conceptual Questions - Ex 7(d)'s answer is wrong?

Hello Chenyulue, First of all, I really appreciate you writing about the mistake. And yes, the value of k should be small for it to fit a highly non linear...

I try to train with MOT17,when I use "multi_frame_attention = True",I get " RuntimeError: stack expects each tensor to be equal size, but got [2, 2, 21, 27, 43] at entry 0 and [2, 2, 21, 27, 42] at entry 1"

I am getting same error "RuntimeError: stack expects each tensor to be equal size, but got [2, 2, 160, 160, 43] at entry 0 and [2, 2, 160, 160, 42]...

I try to train with MOT17,when I use "multi_frame_attention = True",I get " RuntimeError: stack expects each tensor to be equal size, but got [2, 2, 21, 27, 43] at entry 0 and [2, 2, 21, 27, 42] at entry 1"

This is the whole log - "Traceback (most recent call last): File "/home/hardikkamboj/TrackRTMO/src/train.py", line 370, in train(args) File "/home/hardikkamboj/TrackRTMO/src/train.py", line 296, in train train_one_epoch( File "/home/hardikkamboj/TrackRTMO/src/trackformer/engine.py", line 135, in train_one_epoch...