-
I am trying run VID demo with the following command:
```
# python demo/demo_vid.py configs/vid/dff/dff_faster_rcnn_r101_dc5_1x_imagenetvid.py --checkpoint https://download.openmmlab.com/mmtracking…
-
Hello, I created a custom cocovid dataset to use the RoI align VID model, but I'm stuck with an error.
error log:
```sh
2021-11-05 16:28:18,776 - mmtrack - INFO - Environment info:
-------------…
Chop1 updated
2 years ago
-
Have you any ideas or comments in case I am only having one class? Should it work the same or can I get better detections if I change something in your code if I only have one class?
-
Thanks for your error report and we appreciate it a lot.
**Describe the bug**
When I run SELSA , it reports AttributeError:'NoneType' object has no attribute 'copy'
1. What command or script di…
-
Change "seqs = GOT10k(root_dir, subset='train', return_meta=True)" in the original tool/train code to "seqs = ImageNetVID(root_dir, subset =('train', 'val'))", but "ValueError: num_samples should be a…
-
I use youtubebb and imageVID to train siamrpn_alex_dwxcorr_16gpu。 I crop youtubebb size 255*255 and crop ImagenetVID 511*511。is it ok to crop like this？dose it effect the training process？ From m…
-
I used the provided stmn model to test on VID val dataset, and got the following results:Category AP
airplane 0.814
antelope 0.788
bear 0.900
bicycle 0.772
bird 0.734
bus 0.838
car 0.591
…
-
i tried to use your code to train, failed like below:
-------------------------------------------------------------------------------
python train_mvod_basenet.py --datasets E:\ImageNetVID\ILSVRC201…
-
Hello,Thank you for your answer to my last question.
Let me say it again for clarity:
my python = 3.5 , my pytorch = 0.4.1 , my cuda = 9.0
when I used the imagenetvid datasets to train the ATOM, an…
klyjb updated
5 years ago
-
'ImagenetVID' object has no attribute '_get_class_name_from_id',
when I use imagenet VID 2015.