Giters

lkeab / gsnet

Official code of ECCV 2020 paper "GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision". GSNet performs joint vehicle pose estimation and vehicle shape reconstruction with single RGB image as input.

Home Page:https://arxiv.org/abs/2007.13124

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Abrut kill happening when trying to run the demo.py

rohithagaram opened this issue · comments

commented

Hello,

Firstly, thanks for the codes of your impressive research.

when i tired to the below command to to execute the demo.py ( i don't see the datasets folder )
CUDA_VISIBLE_DEVICES=0 python3 demo/demo.py --config-file configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x_apollo.yaml
--input 'datasets/coco/val_apollo/'
--output 'medium_result_val/'
--opts MODEL.WEIGHTS ./output/model_final.pth

by reading the parser arguments i learnt --input should be list of input images with this i changed the command as follows

command : CUDA_VISIBLE_DEVICES=0 python3 demo/demo.py --config-file configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x_apollo.yaml --input 'datasets/apollo/annotations/test/images/171206_034559609_Camera_5.jpg' --output 'medium_result_val/' --opts MODEL.WEIGHTS ./output/model_final.pth

Output
name: coco_2014_train
name: coco_2014_val
name: coco_2014_minival
name: coco_2014_minival_100
name: coco_2014_valminusminival
name: coco_2017_train
name: coco_2017_val
name: coco_2017_occ
name: coco_2017_test
name: coco_2017_test-dev
name: coco_2017_val_100
name: apollo_train
name: apollo_val
name: keypoints_coco_2014_train
name: keypoints_coco_2014_val
name: keypoints_coco_2014_minival
name: keypoints_coco_2014_valminusminival
name: keypoints_coco_2014_minival_100
name: keypoints_coco_2017_train
name: keypoints_coco_2017_val
name: keypoints_coco_2017_val_100
[10/13 00:22:46 detectron2]: Arguments: Namespace(config_file='configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x_apollo.yaml', webcam=False, video_input=None, input=['datasets/apollo/annotations/test/images/171206_034559609_Camera_5.jpg'], output='medium_result_val/', confidence_threshold=0.5, opts=['MODEL.WEIGHTS', './output/model_final.pth'])

Killed

can you please help me where I'm going wrong

commented

Hi, could you report more detailed error message for program being killed? '--input ' should be a folder containing input images.

commented

Hi , thanks for the reply .
tried to change the '--input' arg pointing to image directory but still the issue exist
complete output as follows :
(pytorch) ragaram@gnode39:~/gsnet/reference_code/GSNet-release$ CUDA_VISIBLE_DEVICES=0 python3 demo/demo.py --config-file configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x_apollo.yaml --input '/home2/ragaram/gsnet/reference_code/GSNet-release/input_images' --output 'medium_result_val/' --opts MODEL.WEIGHTS ./output/model_final.pth
name: coco_2014_train
name: coco_2014_val
name: coco_2014_minival
name: coco_2014_minival_100
name: coco_2014_valminusminival
name: coco_2017_train
name: coco_2017_val
name: coco_2017_occ
name: coco_2017_test
name: coco_2017_test-dev
name: coco_2017_val_100
name: apollo_train
name: apollo_val
name: keypoints_coco_2014_train
name: keypoints_coco_2014_val
name: keypoints_coco_2014_minival
name: keypoints_coco_2014_valminusminival
name: keypoints_coco_2014_minival_100
name: keypoints_coco_2017_train
name: keypoints_coco_2017_val
name: keypoints_coco_2017_val_100
[10/13 20:56:44 detectron2]: Arguments: Namespace(config_file='configs/COCO-Keypoints/keypoint_rcnn_R_101_FPN_3x_apollo.yaml', webcam=False, video_input=None, input=['/home2/ragaram/gsnet/reference_code/GSNet-release/input_images'], output='medium_result_val/', confidence_threshold=0.5, opts=['MODEL.WEIGHTS', './output/model_final.pth'])
done cfg
Killed

commented

I think it may be the problem of wrong pytorch or cuda versions. Make sure detectron2, pytorch and cuda are matched and installed correctly. The reported error log does not contain enough information for me.