- Fix relu inconsistent top name problem
- Add Tanh layer
- Add example convertion file form torch to caffe: convert.lua
Step.1
Change the name inside convert.lua
Step.2
th convert.lua
Caffe: load with Python.
Torch: load with Lua.
Q. How to connect Python & Lua code?
A. We don't need directly interact Python code with Lua code, which is complex.
We use intermediate file exchange, the model parameters are saved to disk layer
by layer as .npy
file, and then loaded to caffe/torch separately.
TODO:
- Caffe split layer -> Torch ConcatTable
- PReLU
- More tests