Keiichi Kuroyanagi

Object Detection and Segmentation Updates

1

I'm also looking forward to Object Detection and Segmentation updates. As you may already know, the following survey will be helpful. Thank you. [2111.06091] A Survey of Visual Transformers https://arxiv.org/abs/2111.06091

Is the training time recorded as a log?

2

As the title says, does the training time remain in the log?

Add a Dockerfile including DCNv2 GPU compilation

9

Everyone seems to be having trouble with issue about GPU compilation of DCNv2, so I added a Dockerfile that works correctly. I have confirmed the operation in the following environment....

RuntimeError: Expected tensor to have cpu DeviceType, but got tensor with cuda DeviceType

1

When I placed 300W and ran train.py, I got the following error. Do you know the solution? ``` > python train.py 11:45:54 train start! Traceback (most recent call last): File...

Error in multi-person demo even with Docker

1

@caizhongang I created the following Dockerfile. https://github.com/Keiku/docker-mmhuman3d The single person demo below worked fine. ``` python demo/estimate_smpl.py \ configs/hmr/resnet50_hmr_pw3d.py \ data/checkpoints/resnet50_hmr_pw3d-04f40f58_20211201.pth \ --single_person_demo \ --det_config demo/mmdetection_cfg/faster_rcnn_r50_fpn_coco.py \ --det_checkpoint https://download.openmmlab.com/mmdetection/v2.0/faster_rcnn/faster_rcnn_r50_fpn_1x_coco/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth \...