search

msracver / Deep-Feature-Flow

Deep Feature Flow for Video Recognition
MIT License
1.3k stars 297 forks source link

run error #57

Open Jessespace opened 6 years ago

Jessespace commented 6 years ago

When I run "python experiments/dff_rfcn/dff_rfcn_end2end_train_test.py --cfg experiments/dff_rfcn/cfgs/resnet_v1_101_flownet_imagenet_vid_rfcn_end2end_ohem.yaml", it generator xxx.log in output/,It was been running for a while, but occurred this problem:

by cudnn, MXNET convolution is applied. Traceback (most recent call last): File "experiments/dff_rfcn/dff_rfcn_end2end_train_test.py", line 19, in <module> train_end2end.main() File "experiments/dff_rfcn/../../dff_rfcn/train_end2end.py", line 171, in main config.TRAIN.begin_epoch, config.TRAIN.end_epoch, config.TRAIN.lr, config.TRAIN.lr_step) File "experiments/dff_rfcn/../../dff_rfcn/train_end2end.py", line 164, in train_net arg_params=arg_params, aux_params=aux_params, begin_epoch=begin_epoch, num_epoch=end_epoch) File "experiments/dff_rfcn/../../dff_rfcn/core/module.py", line 990, in fit [14:22:42] src/operator/nn/convolution.cu:218: This convolution is not supported by cudnn, MXNET convolution is applied. self.set_params(arg_params, aux_params) File "/home/tsn/software/incubator-mxnet/python/mxnet/module/base_module.py", line 679, in set_params allow_extra=allow_extra) TypeError: init_params() got an unexpected keyword argument 'allow_extra'

How to fix this problem? Thanks for your help!

ghost commented 6 years ago

may be this could help https://github.com/apache/incubator-mxnet/issues/8638 @Jessespace

Roshrini commented 6 years ago

@Jessespace Did removing "allow_extra" parameter help to solve the issue? apache/incubator-mxnet#8638

weilanShi commented 6 years ago

When I run "python experiments/dff_rfcn/dff_rfcn_end2end_train_test.py --cfg experiments/dff_rfcn/cfgs/resnet_v1_101_flownet_imagenet_vid_rfcn_end2end_ohem.yaml", it generator xxx.log in output/,It was been running for a while, but occurred this problem:

by cudnn, MXNET convolution is applied. Traceback (most recent call last): File "experiments/dff_rfcn/dff_rfcn_end2end_train_test.py", line 19, in <module> train_end2end.main() File "experiments/dff_rfcn/../../dff_rfcn/train_end2end.py", line 171, in main config.TRAIN.begin_epoch, config.TRAIN.end_epoch, config.TRAIN.lr, config.TRAIN.lr_step) File "experiments/dff_rfcn/../../dff_rfcn/train_end2end.py", line 164, in train_net arg_params=arg_params, aux_params=aux_params, begin_epoch=begin_epoch, num_epoch=end_epoch) File "experiments/dff_rfcn/../../dff_rfcn/core/module.py", line 990, in fit [14:22:42] src/operator/nn/convolution.cu:218: This convolution is not supported by cudnn, MXNET convolution is applied. self.set_params(arg_params, aux_params) File "/home/tsn/software/incubator-mxnet/python/mxnet/module/base_module.py", line 679, in set_params allow_extra=allow_extra) TypeError: init_params() got an unexpected keyword argument 'allow_extra'

How to fix this problem? Thanks for your help!

How did you solve this problem? I also met this problem.

weilanShi commented 6 years ago

You can enter this directory： "/home/tsn/software/incubator-mxnet/python/mxnet/module/base_module.py", see the line 679 : self.init_params(initializer=None, arg_params=arg_params, aux_params=aux_params, allow_missing=allow_missing, force_init=force_init, allow_extra=allow_extra) and delete the ( allow_extra=allow_extra)