search

chengtaipu / lowrankcnn

Low-rank convolutional neural networks
96 stars 44 forks source link

erro #7

Open fgxfxpfzzfcc opened 7 years ago

fgxfxpfzzfcc commented 7 years ago

Hi,when i run the python2 ./vgg/lowrank_approx.py --model ./vgg/vgg_deploy.prototxt --config ./vgg/config.json --save_model ./vgg/vgg_lowrank_deploy.prototxt --weights ./vgg/models/vgg_finute.caffemodel --save_weights ./vgg/models/vgg_lowrank.caffemodel, i encountered the following error: Traceback (most recent call last): File "./vgg/lowrank_approx.py", line 134, in main(args) File "./vgg/lowrank_approx.py", line 111, in main make_lowrank_model(args.model, conf, args.save_model) File "./vgg/lowrank_approx.py", line 64, in make_lowrank_model v, h = vh_decompose(layer, conf[layer.name]) File "./vgg/lowrank_approx.py", line 41, in vh_decompose v_param.kernel_h, v_param.kernel_w = conv_param.kernel_size, 1 TypeError: <google.protobuf.pyext._message.RepeatedScalarContainer object at 0x7f392a386ca8> has type google.protobuf.pyext._message.RepeatedScalarContainer, but expected one of: int, long

i used the cuda 8.0 , cudnnV5.1 and protobuf 3.2, do you konw how to solver this problom? thanks for your help.

fgxfxpfzzfcc commented 6 years ago

the above problem has been solved, but I encountered the following error, some people know how to solve it? Thank you I1230 23:07:32.525770 11162 net.cpp:312] Memory required for data: 114620912 [libprotobuf WARNING google/protobuf/io/coded_stream.cc:505] Reading dangerously large protocol message. If the message turns out to be larger than 2147483647 bytes, parsing will be halted for security reasons. To increase the limit (or to disable these warnings), see CodedInputStream::SetTotalBytesLimit() in google/protobuf/io/coded_stream.h. [libprotobuf WARNING google/protobuf/io/coded_stream.cc:78] The total number of bytes read was 580013788 Traceback (most recent call last): File "lowrank_approx.py", line 133, in main(args) File "lowrank_approx.py", line 117, in main args.save_weights) File "lowrank_approx.py", line 80, in approx_lowrank_weights [p.data for p in lowrank_net.params[layer_name + '_v']] KeyError: u'conv5_1_v'

ShenghaiRong commented 6 years ago

@fgxfxpfzzfcc hi , I encoutered the same problem as your first problem. Would you tell me how to solve it?Thank you.

ghost commented 6 years ago

@ShenghaiRong refer to issue #10 for resolving your error.

ghost commented 6 years ago

@fgxfxpfzzfcc did your model's prototxt save successfully? Your error would only mean for it to not find a layer by the name of conv5_1_v .