BrokenPipeError: [Errno 32] Broken pipe

reinforcement-learning
1

BrokenPipeError: [Errno 32] Broken pipe
threads issue, unable to set threads
data loader problem
RuntimeError: CUDA out of memory. Tried to allocate 128.00 MiB (GPU 0; 11.00 GiB total capacity; 8.25 GiB already allocated; 70.74 MiB free; 8.31 GiB reserved in total by PyTorch)

2

You are running out of memory on your GPU.
Try to decrease the batch size or alternatively try to trade compute for memory via torch.utils.checkpoint.

3

Capture1
Capture1787×338 16 KB

when i define No. of workers 2 it gives me an error [broken pipe error]
iam using intel 9920x
RTX 2080 TI 11GB
windows 10 pro
i have also uploaded the screenshot

6

Have a look at the Windows FAQ for multiprocessing. Maybe you are missing the if-clause protection.