Apr-17-2020, 05:50 AM
I use PyTorch for machine learning. I am doing all this in Google Colab.
I use 'cuda' for training, but here is a problem:
(best_val_loss, best_sentence_level_model) = train_eval_loop(sentence_level_model, train_dataset, test_dataset, F.cross_entropy, lr=5e-3, epoch_n=10, batch_size=64, device='cuda', early_stopping_patience=5, max_batches_per_epoch_train=500, max_batches_per_epoch_val=100)
I use 'cuda' for training, but here is a problem:
RuntimeError: cuda runtime error (100) : no CUDA-capable device is detected at /pytorch/aten/src/THC/THCGeneral.cpp:50did somebody meet this issue? how did you solve it?