yxgeee / FD-GAN

[NeurIPS-2018] FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification.
https://yxgeee.github.io/projects/fdgan.html
281 stars 80 forks source link

OSError: [Errno 24] Too many open files #44

Closed absagargupta closed 4 years ago

absagargupta commented 4 years ago

I was running the command python baseline.py -b 16 -j 4 -d market1501 -a resnet50 --combine-trainval --lr 0.01 --epochs 100 --step-size 40 --eval-step 5

and getting the above said error. Here is the full traceback Extract Features: [968/1206] Time 0.058 (0.058) Data 0.003 (0.004)
Traceback (most recent call last): File "baseline.py", line 200, in File "baseline.py", line 160, in main File "/home/sagar18174/Thesis/person_RE-identification/FD-GAN/reid/evaluators.py", line 193, in evaluate File "/home/sagar18174/Thesis/person_RE-identification/FD-GAN/reid/evaluators.py", line 55, in extract_features File "/home/sagar18174/.local/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 345, in next File "/home/sagar18174/.local/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 841, in _next_data File "/home/sagar18174/.local/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 808, in _get_data File "/home/sagar18174/.local/lib/python2.7/site-packages/torch/utils/data/dataloader.py", line 761, in _try_get_data File "/usr/lib/python2.7/multiprocessing/queues.py", line 135, in get File "/home/sagar18174/.local/lib/python2.7/site-packages/torch/multiprocessing/queue.py", line 22, in recv File "/usr/lib/python2.7/pickle.py", line 1388, in loads File "/usr/lib/python2.7/pickle.py", line 864, in load File "/usr/lib/python2.7/pickle.py", line 1139, in load_reduce File "/home/sagar18174/.local/lib/python2.7/site-packages/torch/multiprocessing/reductions.py", line 287, in rebuild_storage_fd File "/usr/lib/python2.7/multiprocessing/reduction.py", line 155, in rebuild_handle File "/usr/lib/python2.7/multiprocessing/connection.py", line 169, in Client File "/usr/lib/python2.7/multiprocessing/connection.py", line 320, in SocketClient OSError: [Errno 24] Too many open files

Any idea why this might be happening

yxgeee commented 4 years ago

It seems the problem with your CPU I/O. Try to set a smaller value of num_workers for the data loader.