pytorch 代码调试中出现以下报错。
报错:
RuntimeError:
An attempt has been made to start a new process before the
current process has finished its bootstrapping phase.
This probably means that you are not using fork to start your
child processes and you have forgotten to use the proper idiom
in the main module:
if __name__ == '__main__':
freeze_support()
...
The "freeze_support()" line can be omitted if the program
is not going to be frozen to produce an executable. prepare(preparation_data)
原因:多进程设置问题。之前,用一块GPU不会报错,在装有两块GPU的机器上出现该错误。
根据错误提示,似乎少了这句:
if __name__=='__main__':
于是,代码在运行 epoch 之前,加上该句即可。
if __name__=='__main__':
num_epochs = 1000
epoch_list = []
train_loss_list = []
val_loss_list = []
lr_list = []
for epoch in range(1, num_epochs+1):
train_loss = 0
val_loss = 0
# 开启训练模式
net.train()
start = time.time()
亲测,有效!
参考:
https://blog.csdn.net/u014546828/article/details/109235539