Cannot implement DeepSolo on local environment or on Kaggle or any other cloud

[kunalpurkayastha]

When trying to finetune or pretrain the DeepSolo I'm getting the following error on Kaggle

Traceback (most recent call last): File "tools/train_net.py", line 27, in from detectron2.data import MetadataCatalog, build_detection_train_loader, build_detection_test_loader File "/opt/conda/lib/python3.7/site-packages/detectron2/data/init.py", line 4, in from .build import ( File "/opt/conda/lib/python3.7/site-packages/detectron2/data/build.py", line 14, in from detectron2.structures import BoxMode File "/opt/conda/lib/python3.7/site-packages/detectron2/structures/init.py", line 6, in from .keypoints import Keypoints, heatmaps_to_keypoints File "/opt/conda/lib/python3.7/site-packages/detectron2/structures/keypoints.py", line 6, in from detectron2.layers import interpolate File "/opt/conda/lib/python3.7/site-packages/detectron2/layers/init.py", line 3, in from .deform_conv import DeformConv, ModulatedDeformConv File "/opt/conda/lib/python3.7/site-packages/detectron2/layers/deform_conv.py", line 10, in from detectron2 import _C ImportError: /opt/conda/lib/python3.7/site-packages/detectron2/_C.cpython-37m-x86_64-linux-gnu.so: undefined symbol: _ZN6caffe28TypeMeta21_typeMetaDataInstanceISt7complexIdEEEPKNS_6detail12TypeMetaDataEv

Also how can I use DeepSolo on my Ubuntu 22.04 (My hardware specs are CPU-Ryzen 7 5600H, GPU- 4GB Nvidia RTX 3050, RAM- 16GB)

Either I face the issue of AdelaiDet or some CUDA error all the time in my local machine

[ymy-k]

Maybe detectron2 was not correctly built.

[kunalpurkayastha]

I'm using the below version of detectrol2 detectron2==0.1.3

can you please tell me which version of what is required specifically? as most of the errors I'm facing to implement DeepSolo is due to version mismatch

[ymy-k]

Detectron2 v0.6 & torch 1.9 + cuda11.1 were used.