李鹤年 comments

Results 9 comments of


                                            李鹤年

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"

And when I use "Tracking = true",I get "RuntimeError: indices should be either on cpu or on the same device as the indexed tensor (cpu) "

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"

Dear Sir, I am unable to modify my Pytorch version because I conducted the experiment using my school's server. The CUDA version on it is already fixed. Is there any...

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"

The second one is that I can detect gpu because I am using your track to evaluate MOT17 using gpu

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"

Is there a method for training without using these two parameters? I am setting this parameter to false and training, but the resulting model performance is very poor

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 parameter I am currently using for training. This parameter can be trained normally, but the effect is very poor. Can you give me some suggestions for parameter...

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"

Yes, I have modified the commands used for training. I am currently using "Python train. py" and the set of parameters above

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"

Now I use"python train.py" with args ############ aux_loss = True backbone = 'resnet50' batch_size = 2 bbox_loss_coef = 5.0 clip_max_norm = 0.1 cls_loss_coef = 2.0 coco_and_crowdhuman_prev_frame_rnd_augs = 0.2 coco_min_num_objects =...

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"

> Now I run with "python src/train.py with mot17 deformable output_dir=models/mot17_crowdhuman_deformable_multi_frame " but get"NotImplementedError: No rule for transformer.level_embed with shape torch.Size([4, 256])."

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'm very sorry, but I can't add Tracking because adding it would result in "RuntimeError: indications should be either on CPU or on the same device as the indexed tensor...