search

hellochick / ICNet-tensorflow

TensorFlow-based implementation of "ICNet for Real-Time Semantic Segmentation on High-Resolution Images".
406 stars 153 forks source link

Code licensing #24

Open jacobdang opened 6 years ago

jacobdang commented 6 years ago

Thanks a lot for this wonderful software. Just wondering what is the license for this code? Can it be used for commercial projects?

hellochick commented 6 years ago

Hey @jacobdang, I think you should contact the original author for details first, I have no idea on such things. But I am glad to know how you can apply this software to commercial projects.

jacobdang commented 6 years ago

Hi, @hellochick Thanks for the reply. We are developing a perception software for an autonomous driving project, i.e. segmentation of road region and lane-marker region. This type of software could be very useful. So Thank you!

Just wondering have you developed the majority portion of software independently by mostly referring to the paper/algorithm rather than original authors' code? If that is the case, then your code is considered as "original work," and I need not original author's permission, as long as you agree. Otherwise, I will ask them.

Thanks very much!

Yours, jacobdang

hellochick commented 6 years ago

Hi @jacobdang , since the paper did not specify the architecture of the network, I need to refer to the author's code which implemented in Caffe, and re-implement the code in tensorflow myself. I think the issue about "original work" is a little ambiguous. At least, I will agree in my part! Hope you can do great job in autonomous driving, I also do research in this field. If you have any good result, please tell me. Thank you !

jacobdang commented 6 years ago

Hi @hellochick, Thanks very much for your kind reply! It is very nice for you to agree on your part to release the code for commercial use. Appreciate that a lot. Will check with the original authors on remaining matters, and let you know the result as well. Will let you know my progress on autonomous driving and hopeful we can have more discussion later. Thanks again!