Hello Sir,
Using your data-set, (ade20k), I trained and tested.
Then I tried to train using my own-datasets.
But I met some CUDA error.
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_INITIALIZED
terminate called after throwing an instance of 'c10::CUDAError'
what(): CUDA error: device-side assert triggered
CUDA kernel errors might be asynchronously reported at some other API call,so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Exception raised from create_event_internal at /pytorch/c10/cuda/CUDACachingAllocator.cpp:1055 (most recent call first):
frame #0: c10::Error::Error(c10::SourceLocation, std::string) + 0x42 (0x7fe0fbd04a22 in /home/itsme/anaconda3/lib/python3.7/site-packages/torch/lib/libc10.so)
frame #1: <unknown function> + 0x10aa3 (0x7fe0fbf65aa3 in /home/itsme/anaconda3/lib/python3.7/site-packages/torch/lib/libc10_cuda.so)
frame #2: c10::cuda::CUDACachingAllocator::raw_delete(void*) + 0x1a7 (0x7fe0fbf67147 in /home/itsme/anaconda3/lib/python3.7/site-packages/torch/lib/libc10_cuda.so)
frame #3: c10::TensorImpl::release_resources() + 0x54 (0x7fe0fbcee5a4 in /home/itsme/anaconda3/lib/python3.7/site-packages/torch/lib/libc10.so)
frame #4: <unknown function> + 0xa2f382 (0x7fe1a0b13382 in /home/itsme/anaconda3/lib/python3.7/site-packages/torch/lib/libtorch_python.so)
frame #5: <unknown function> + 0xa2f421 (0x7fe1a0b13421 in /home/itsme/anaconda3/lib/python3.7/site-packages/torch/lib/libtorch_python.so)
<omitting python frames>
frame #21: __libc_start_main + 0xe7 (0x7fe1a387eb97 in /lib/x86_64-linux-gnu/libc.so.6)
What should I do for this problem??
Hello Sir,
Using your data-set, (ade20k), I trained and tested.
Then I tried to train using my own-datasets.
But I met some CUDA error.
What should I do for this problem??