Why the mxnet2caffe.py exit when the layer is "running_mean"?

szad670401 / advanced-mxnet2caffe

Support most of operator which convert mxnet to caffe.

60 stars 18 forks source link

Why the mxnet2caffe.py exit when the layer is "running_mean"? #9

Open ChaoLi977 opened 4 years ago

ChaoLi977 commented 4 years ago

Hi, I have run the json2prototxt.py successfully, but when I run the mxnet2caffe.py, it occurs something wrong. The program exits when it meets the layer "mobilenet0_batchnorm0_running_mean". I don't know why it exits and what should I do to convert the mxnet model normally?

Harryqu123 commented 4 years ago

@ChaoLi977 Can I know have you solved this issue, as I meet the same issue too. Can I know how do you solve it, many thx

Harryqu123 commented 4 years ago

I just realize that there are lines of code exit() in the running_mean and running_var, are they just accidentally put there or are they put there since these two layer still have error?

zheshipinyinMc commented 4 years ago

the name of BNlayer in gluon.nn is "xx_runing_mean", but it is "xx_moving_mean" in mxnet.symbol