Closed OrhanDg closed 3 months ago
Hello, thank you for your interest in DECOLA!
It appears to be that the build has not been successful for the deformable attention modules. Could you follow the Deformable DETR's guide on building it? Should be here. Our installation should automatically compile all third-party modules but I am not sure what happened in your case.
Please try this and ask me if there is any other questions.
Can you please provide a solution or a recommandation for my problem below. I have already checked other respositories of MultiscaleDefomableAttention and I run my code in google colab environment with T4GPU but somehow I couldn't overcome this problem:
! python train_net.py --num-gpus 8 --config-file /content/DECOLA/configs/BoxSup-DeformDETR_Lbase_CLIP_SwinB_4x.yaml