-
https://github.com/hassony2/torch_videovision/blob/ae4b32b4dc76f97387ae74c9c652bffb7ba05697/torchvideotransforms/video_transforms.py#L322
Hi @hassony2 , I think there is a bug here where it should …
-
I want to use retinanet to change the two stages in the network, how can I do it based on detectron2？
-
Hi, thanks for sharing the code.
I have gone through the code in Mixup_for_UDA/DM-ADA/trainer_mixed.py, but I can not find the related code about the loss described in the eq. (21).
Can you explai…
Zysty updated
4 years ago
-
Hi im new to this field and i have a minor question about TRZSL setting.
At first, I thought that in TRZSL, only images corresponding to unseen classes could be accessed during training. But after re…
-
`darknet.exe detector test cfg/coco.data cfg/yolov3.cfg yolov3.weights -dont_show -ext_output < data/train.txt > result.txt`
From the code above, I can successfully generate **one single output fil…
-
### HHVM Version
3.18.1
### Standalone code, or other way to reproduce the problem
I expected to ignore only files, the folders would still go through rewrite (note that the ini is "commented…
-
I am going to kick things off by mostly paraphrasing/quoting a discussion with @thiolliere & @shawntabrizi related to FRAME's account management capabilities, specifically the management of [account d…
-
Hi @AlexeyAB,
I'm working on an object detector for autonomous driving (car, truck, pedestrian, bicycle, motor).
I have so far trained Tiny YOLO v3 on BDD100K and Cityscape.
I want to improve per…
-
Dear authors,
Thank you for opensourcing your work. I have quick questions about ORE application that needed clarification:
- Have you used BOTH mavl and RPN pseudolables during training? Or defa…
-
Hi,
Thanks for sharing the code.
I was wondering if you could also share the instruction on how to train on custom datasets. Since I've noticed that you modified the low level code such as `buil…