Jeff Waller

Following up, I wrote a little exploratory stuff and here are the layer types of GoogleNet. InnerProducts are supported, and I guess Convolutions. What about the rest? Looks like in...

Yea I'm reading the docs now looks like there's a translation possible, I'm looking at them one by one. So far looks like all of the convolution layers have 2...

that's fine, the caffe file does have 2 blobs. Bias blob? Does that correspond to bottom? ``` make_blob(backend, ... ``` Should this have a default value of whatever the current...

So how are the parameter blobs connected to a Convolution layer. I see the only candidates are bottom and top. If not those then what else is there?

The part I'm having trouble with is the mapping. Here's the [ProtoBuf description](https://gist.github.com/waTeim/944e097e01b07c724295). There is a blobs field in the layers section. When read this field is populated with 2...

x is a parsed trained caffe net, so looks like option 3. Is this simply a matter of creating a new Initializer type?

Took a while, but I'm back on it. This look about right? ``` immutable CopyInitializer

I'm pretty sure that by the time it gets into to caffe.BlobProto it's an array that exists independent of the file, normal GC applies. Re using copy, yea asy change....

Last layer type, it's the data layer type and comes with a Transformation Parameter: ``` type TransformationParameter scale::Float32 mirror::Bool crop_size::UInt32 mean_file::AbstractString mean_value::Array{Float32,1} force_color::Bool force_gray::Bool TransformationParameter() = (o=new(); fillunset(o); o) end...

Limited success. 1. To keep things simple I used [cifar10_nin.caffemodel from Model Zoo](https://github.com/BVLC/caffe/wiki/Model-Zoo) 2. The output can be seen [here](https://gist.github.com/waTeim/45370cfe33db3fee7902). 3. I just arbitrarily picked input blob dimensions of 10x10x1x1...