search

ijkguo / mx-rcnn

Parallel Faster R-CNN implementation with MXNet.
Other
671 stars 290 forks source link

training error when saving checkpoint #82

Closed wuyi1983 closed 6 years ago

wuyi1983 commented 6 years ago

Hi, after finishing the first epoch, I got the following error. How to fix it? Thanks

INFO:root:Epoch[0] Batch [10020] Speed: 4.99 samples/sec Train-RPNAcc=0.990064, RPNLogLoss=0.034670, RPNL1Loss=0.447456, RCNNAcc=0.849728, RCNNLogLoss=0.468532, RCNNL1Loss=1.930149,
INFO:root:Epoch[0] Train-RPNAcc=0.990062 INFO:root:Epoch[0] Train-RPNLogLoss=0.034672 INFO:root:Epoch[0] Train-RPNL1Loss=0.447425 INFO:root:Epoch[0] Train-RCNNAcc=0.849727 INFO:root:Epoch[0] Train-RCNNLogLoss=0.468535 INFO:root:Epoch[0] Train-RCNNL1Loss=1.930103 INFO:root:Epoch[0] Time cost=2069.632 Traceback (most recent call last): File "train_end2end.py", line 178, in main() File "train_end2end.py", line 175, in main lr=args.lr, lr_step=args.lr_step) File "train_end2end.py", line 137, in train_net arg_params=arg_params, aux_params=aux_params, begin_epoch=begin_epoch, num_epoch=end_epoch) File "/home/wuyi/anaconda2/lib/python2.7/site-packages/mxnet/module/base_module.py", line 517, in fit self.set_params(arg_params, aux_params) File "/home/wuyi/anaconda2/lib/python2.7/site-packages/mxnet/module/base_module.py", line 652, in set_params allow_extra=allow_extra) TypeError: init_params() got an unexpected keyword argument 'allow_extra'

yaoliUoA commented 6 years ago

I met the same problem, just remove the 'allow_extra' on line 652 in /mxnet/module/base_module.py, and it worked fine for me.

ijkguo commented 6 years ago

Module API changed. Should have been fixed now.