Yxiaoqian

cd torchlight; python setup.py install; cd ..

python eval_rcnn.py --cfg_file cfgs/default.yaml --eval_mode rcnn --test --start_epoch 70 but I get the error: numba.cuda.cudadrv.driver.CudaAPIError: [999] Call to cuDevicePrimaryCtxRetain results in CUDA_ERROR_UNKNOWN

@Gyx-One thank you very much, I have configure the environment correctly, but I get another error when I training: ``` hyperpose/Hyperpose/Model/openpose/train.py:195 one_step * pd_conf,pd_paf,stage_confs,stage_pafs=train_model.forward(image,is_train=True) .virtualenv/tf2-py37/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py:457 __call__ result = self._call(*args, **kwds)...

@Gyx-One It works on my local host, and I have train successfully. But I train it on docker environment, there are some errors like that: ``` ValueError: in converted code:...