Is it necessary to use caffe-future?

[Richardhongyu]

• Background:

I use face_segment_part.py to get parts of a face. But the result[1] seems wrong when I run this file. I notice the Caffe-future is needed if I run this file. Then I go to the link of Caffe-future in Readmd.md. And I download the "caffe-future.tar.gz".

• Question1:

However in its github home page, I found this, "This was a pre-release Caffe branch for fully convolutional networks (FCNs); however, the needed FCN features are now included in the Caffe master branch. Note however there are differences in the master edition, so refer to the documentation there. ". Is it necessary to use caffe-future now? If the answer is yes, how can I install this version of caffe? I don't find any instructions.

• Qusetion2:

What causes my problem here? Is this related to the version of caffe?

Thanks for your patience!

• [1] The wrong result