yoyomimi / AS-Net

Code for one-stage adaptive set-based HOI detector AS-Net.
MIT License
48 stars 1 forks source link

Get Some Error #16

Closed SherlockHolmes221 closed 3 years ago

SherlockHolmes221 commented 3 years ago

running the test code on HICO-DET python3 tools/eval.py --cfg configs/hico.yaml 088935aaa1b5648f58d7b80a537bba1

SherlockHolmes221 commented 3 years ago

More question: Could you provide the training log files? How many GPUs and the batch sizes did you use to get the final results in paper? Thanks

yoyomimi commented 3 years ago

Please check the closed issue to see if it works for you: issues_7. Sorry we currently don't have the training logs. We train with 32 GPUs and 2 sample for each GPU. You can decrease the GPU amounts according to your devices, and then modify the learning rate correspondingly, e.g.: 32 GPU 2 img/per GPU(batchsize 64) & lr -> 8 GPU 2 img/per GPU(batchsize 16) & 0.25lr.

SherlockHolmes221 commented 3 years ago

Thanks