the problem in trainning

[FUTUREEEEE]

Traceback (most recent call last):
File "/home/chen/anaconda3/envs/siammask/lib/python3.6/multiprocessing/resource_sharer.py", line 142, in _serve
with self._listener.accept() as conn:
File "/home/chen/anaconda3/envs/siammask/lib/python3.6/multiprocessing/connection.py", line 455, in accept
deliver_challenge(c, self._authkey)
File "/home/chen/anaconda3/envs/siammask/lib/python3.6/multiprocessing/connection.py", line 722, in deliver_challenge
response = connection.recv_bytes(256) # reject large message
File "/home/chen/anaconda3/envs/siammask/lib/python3.6/multiprocessing/connection.py", line 216, in recv_bytes
buf = self._recv_bytes(maxlength)
File "/home/chen/anaconda3/envs/siammask/lib/python3.6/multiprocessing/connection.py", line 407, in _recv_bytes
buf = self._recv(4)
File "/home/chen/anaconda3/envs/siammask/lib/python3.6/multiprocessing/connection.py", line 383, in _recv
raise EOFError
EOFError

[FUTUREEEEE]

This problem appeared after 1% training，the trainning data is coco