about inference speed

[wenhe-jia]

I tried to eval the model with R50 backbone trained on OVIS dataset, but the inference time seems to be meet some problems as below:

[12/23 17:28:26 d2.evaluation.evaluator]: Inference done 1/13. Dataloading: 45.3657 s/iter. Inference: 437.8758 s/iter. Eval: 58.6491 s/iter. Total: 541.8920 s/iter. ETA=1:48:22                                                                                                                             
[12/23 17:40:07 d2.evaluation.evaluator]: Inference done 2/13. Dataloading: 22.7377 s/iter. Inference: 550.4166 s/iter. Eval: 48.6906 s/iter. Total: 621.8460 s/iter. ETA=1:54:00

I inference with 4 RTX 3090 GPUs, and the 3rd iter of inference takes more than 20 minutes, please tell me is this normal?

[babble2]

I tried to eval the model with R50 backbone trained on OVIS dataset, but the inference time seems to be meet some problems as below:

[12/23 17:28:26 d2.evaluation.evaluator]: Inference done 1/13. Dataloading: 45.3657 s/iter. Inference: 437.8758 s/iter. Eval: 58.6491 s/iter. Total: 541.8920 s/iter. ETA=1:48:22                                                                                                                             
[12/23 17:40:07 d2.evaluation.evaluator]: Inference done 2/13. Dataloading: 22.7377 s/iter. Inference: 550.4166 s/iter. Eval: 48.6906 s/iter. Total: 621.8460 s/iter. ETA=1:54:00

I inference with 4 RTX 3090 GPUs, and the 3rd iter of inference takes more than 20 minutes, please tell me is this normal?

I would like to ask how you solved the problem，thx!

• [ ]