error in pspnet.prototxt

[jeansely]

Hello, when run weight-converter this error occur:

"caffe.LayerParameter" has no field named "bn_param".

                      i replace it with "batch_norm_param"

again occur below error: "caffe.BatchNormParameter" has no field named "slope_filler".

[Vladkryvoruchko]

Hello @jeansely . There is modified prototxt in /utils/model

[jeansely]

now in /utils/model the prototxt is ; bn_param { slope_filler { type: "constant" value: 1 } bias_filler { type: "constant" value: 0 } frozen: true momentum: 0.95

what are replace these lines ?

[jefequien]

It is from here. https://github.com/hszhao/PSPNet/blob/master/evaluation/prototxt/pspnet50_ADE20K_473.prototxt

[jeansely]

when run weigth -converter occur error in prototxt "line 109"

has no field named "bn_param". and "caffe.BatchNormParameter" has no field named "slope_filler".

[CuriousCat-7]

I hold the same problem

[tangsanli5201]

I hold the same problem too.

[Vladkryvoruchko]

@CuriousCat-7 @tangsanli5201 Please use already converted h5, json weights. Links that can be found in README.md I just cannot remember what was done with this converter, so if I find out i will leave a comment in this thread

[tangsanli5201]

@Vladkryvoruchko Yeah. I tried to use the already converted json weights, but it raised an error: 'bad marshal data...'., which I thought it is caused by the different version of Keras( mine is 2.1.2). And it's solved now: I generated the json file through Keras 2.1.2 and replaced the old one. It's working. Thanks!

[RahavLussato]

@tangsanli5201 how did you manage to generate the json ? i have the same bad marshal data... issue