can it convert the undefine format model?

[eeric]

sush as following:
layer{
name: "slice_fc1"
type:"Slice"
slice_param {
slice_dim: 1
}
bottom: "fc1"
top: "slice_fc1_1"
top: "slice_fc1_2"
}
layer{
name: "etlwise_fc1"
type: "Eltwise"
bottom: "slice_fc1_1"
bottom: "slice_fc1_2"
top: "eltwise_fc1"
eltwise_param {
operation: MAX
}
}
it was from that the light cnn C model: https://github.com/AlfredXiangWu/face_verification_experiment

[latifisalar]

Unfortunately not, implementation of the custom layers needs to be added for the support.

[akbarxie]

Tecent yesterday release their ncnn,contain the layers you need ,but they only runs on the cpu,and not fast enough,but it may meets your needs.

[latifisalar]

That's great, thanks for the update and your help, we'll have a look to their implementation.

[eeric]

@latifisalar, it was to be for the support to slice and etlwise, was it?