Wenqi Li

duplicate of https://github.com/NifTK/NiftyNet/issues/99?

Hi @johnnychhsu an example of transfer learning is presented here -- https://github.com/NifTK/NiftyNet/pull/140. It's still a work in progress, mainly we need a generic user interface (via config file) to handle...

Hi @johnnychhsu The problem in your code is the `layer_op()` call. The following works for me: ```python with tf.Session(config=tf.ConfigProto(allow_soft_placement=True, log_device_placement=False)) as sess: from niftynet.network.dense_vnet import DenseVNet data_dict = sampler.pop_batch_op() net_logits...

Yes @johnnychhsu, there are a few tasks in this direction: 1. the transfer learning interface has been improved by @aleks-djuric https://github.com/NifTK/NiftyNet/pull/258, it would be great to have a step-by-step tutorial...

Thanks for the nice suggestions @agrawal123, actions on this ticket would be: * [ ] improve the documentation -- tensorflow-gpu installation via conda * [ ] build docker images for...

Hi @yuanpeng5 have you looked at this example? https://github.com/NifTK/NiftyNet/issues/254#issuecomment-431793018 which still requires niftynet's IO though.

@yuanpeng5 cool, could you give more details of this inference model deployment? could be a generic feature to have in the upstream. thanks!

@YilinLiu97 sounds like a weight initialisation issue or perhaps you could use a truncated version of the Dice loss (https://github.com/NifTK/NiftyNet/issues/34#issuecomment-360842663)

Thanks for restarting this @dzhoshkun. [The proposed new config](https://cmiclab.cs.ucl.ac.uk/CMIC/NiftyNet/blob/8b3e573e69513c4f414c099010b63ccb2a36dd9c/config/issue-189/yml/niftynet.yml) looks really nice. The next step (to implement the first two stages you mentioned) would be creating a new parser in...

on a side note there's a very brief overview of `niftynet.engine.signal` at https://niftynet.readthedocs.io/en/dev/extending_event_handler.html