search

ethanhe42 / channel-pruning

Channel Pruning for Accelerating Very Deep Neural Networks (ICCV'17)
https://arxiv.org/abs/1707.06168
MIT License
1.07k stars 310 forks source link

Message type "caffe.ImageDataParameter" has no field named "new_dim" #90

Closed zhao1995 closed 5 years ago

zhao1995 commented 6 years ago

All are welcome to create issues, but please google the problem first, and make sure it has not already been reported.

What steps reproduce the bug?

What hardware and operating system/distribution are you running?

Operating system: Ubuntu 14.04 CUDA version: 8.0 CUDNN version: 5.1 openCV version: 2.4.13 BLAS: atlas Python version: 3.4

If the bug is a crash, provide the backtrace.

After compile,i run :

caffe test -model channel_pruning_VGG-16_3C4x/channel_pruning_VGG-16_3C4x.prototxt -weights channel_pruning_VGG-16_3C4x/channel_pruning_VGG-16_3C4x.caffemodel -iterations 5000 -gpu 0

then the result is:

I0316 16:32:38.900554 31805 caffe.cpp:261] Use GPU with device ID 0 I0316 16:32:38.901036 31805 caffe.cpp:265] GPU device name: GeForce GTX 1060 3GB [libprotobuf ERROR google/protobuf/text_format.cc:245] Error parsing text-format caffe.NetParameter: 18:12: Message type "caffe.ImageDataParameter" has no field named "new_dim". F0316 16:32:39.191406 31805 upgrade_proto.cpp:79] Check failed: ReadProtoFromTextFile(param_file, param) Failed to parse NetParameter file: channel_pruning_VGG-16_3C4x/channel_pruning_VGG-16_3C4x.prototxt Check failure stack trace: @ 0x7f994cfeddbd google::LogMessage::Fail() @ 0x7f994cfefc5d google::LogMessage::SendToLog() @ 0x7f994cfed9ac google::LogMessage::Flush() @ 0x7f994cff057e google::LogMessageFatal::~LogMessageFatal() @ 0x7f994d6ac7de (unknown) @ 0x7f994d68b558 (unknown) @ 0x4099e4 (unknown) @ 0x40867c (unknown) @ 0x7f994bad9f45 (unknown) @ 0x408e4d (unknown) Aborted (core dumped)

JinyangGuo commented 6 years ago

I have the same problem. Please tell me the solution if you solve this problem. The strange thing is the first time I can run the caffe test, but when I want to reproduce the result, this problem comes out.

young-fire commented 6 years ago

you should use the author's caffe

ethanhe42 commented 5 years ago

@young-fire is right.