Re: Request for invitation to the slack channel

2019-01-10 Thread Steffen Rochel
Send invitation to ASF, welcome to the team. Steffen On Wed, Jan 9, 2019 at 11:28 PM aashu dwivedi wrote: > Hi, > > Can you please add me to the MXNet slack for the channels #mxnet and > #mxnet-scala. > > -Ashutosh >

Re: Tensorflow contrib loss functions ported to mxnet

2019-01-10 Thread István Fehérvári
Thanks for the feedback, I was planning to add an example as well for each loss, possibly an extension to the current embedding learning gluon example. The forgotten PR is https://github.com/apache/incubator-mxnet/pull/13632 On Thu, Jan 10, 2019 at 12:40 AM Hagay Lupesko wrote: > Istavan, > > T

legacy model gallery

2019-01-10 Thread István Fehérvári
Hello, Does anyone know how these models were trained? https://github.com/dmlc/mxnet-model-gallery/blob/master/imagenet-1k-inception-bn.md I am trying to use the inception-bn model but it seems the inputs were not normalized to [0..1] (I get better results without), no idea about mean and std tho

Re: [Announcement] New Committer - Roshani Nagmote

2019-01-10 Thread Hagay Lupesko
Congrats and so much well deserved :) On Tue, Jan 8, 2019 at 9:20 AM Steffen Rochel wrote: > Congratulation Roshani! > > On Tue, Jan 8, 2019 at 8:53 AM Qing Lan wrote: > > > Congrats Roshani! Great to have you here! > > > > -Qing > > > > > > > > > > > Congrats Roshani. Well deserved. > > > > >

Re: Tensorflow contrib loss functions ported to mxnet

2019-01-10 Thread Hagay Lupesko
Istavan, This sounds useful to me, and would encourage you to contribute it. It's always helpful if you describe one or two use cases for the contribution (e.g. models/problems where these loss functions are useful) - this stimulates interest. Can you share the link to the PR that got zero attent