cudaCheckError() failed : no kernel image is available for execution on the device

[jkllbn2563]

I use the eval command: python3 main.py --path_opt cfgs/noc_coco_res101.yml --batch_size 4 --cuda True --num_workers 2 --max_epoch 30 --inference_only True --beam_size 3 --start_from save/noc_coco_nbt_1024

get the error: home/jkllbn2563/code/python/pytorch/Neural-Baby-Talk-python3/misc/model.py:174: UserWarning: volatile was removed and now has no effect. Use with torch.no_grad(): instead. conv_feats, fc_feats = self.cnn(Variable(img.data, volatile=True)) cudaCheckError() failed : no kernel image is available for execution on the device

how to deal with this problem my GPU is RTX2060 super thanks!!

[wolfgodAmaterasu]

Hello, I meet the same problem too! How to solve it