mynetwork: Exception occurred during handler processing. Backtrace from offending handler [get_topology] servicing event [EventSwitchEnter] follows.
Traceback (most recent call last):
File "/usr/local/lib/python3.6/dist-packages/ryu/base/app_manager.py", line 290, in event_loop
handler(ev)
File "/home/ming1/ryu/ryu/app/my_no_loop_get_topology_with_DDPG.py", line 215, in get_topology
action_dim=len(links.keys()))
File "/home/ming1/ryu/ryu/app/memory.py", line 149, in init
self.actor = Actor(state_dim, action_dim)
File "/home/ming1/ryu/ryu/app/memory.py", line 99, in init
self.l1 = nn.Linear(state_dim, 400)
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/linear.py", line 84, in init
self.reset_parameters()
File "/usr/local/lib/python3.6/dist-packages/torch/nn/modules/linear.py", line 87, in reset_parameters
init.kaiming_uniform(self.weight, a=math.sqrt(5))
File "/usr/local/lib/python3.6/dist-packages/torch/nn/init.py", line 376, in kaiming_uniform_
std = gain / math.sqrt(fan)
ZeroDivisionError: float division by zero
在运行代码的时候出现了这个错误，意思是我的linear神经网络在创建生成参数的时候底层有一个方法除零了，有大佬知道怎么解决吗？系统是ubuntu 18.04 torch是1.8.1+cpu python版本是3.6.9