deep learning models
AI
pretrained computer vision models
SHOW HN2016
127points
15comments
#281of 2,264 in 2016
Top 13%of 2016 by points
How HN took it
QuietFewer than 5 comments about the project
0 positive, 3 neutral or asking, 0 mixed, 0 critical, out of 3 comments about the project.
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
Objections
Licensing of the model weights is unclear
From 3 comments
Are you allowed to redistribute the models under the MIT License?
minimaxir on HNDon't take my word for it, but actually as far as I know both in the US and EU data (including model weights) can't be copyrighted.
ma2rten on HNEven if this might be true, including a license of some kind is really a best practice at this point. Something like a Creative Commons license is probably more appropriate than…
cmrx64 on HN
Requests
Clearer licensing information for the weights
From 2 comments
Even if this might be true, including a license of some kind is really a best practice at this point. Something like a Creative Commons license is probably more appropriate than…
cmrx64 on HNThe code is under the MIT license, not the weights. The weights are under their respective licenses. The weights are not included in the git tree and are thus not covered by the…
fchollet on HN
Support for fine-tuning on new image datasets
From 2 comments
Can the classify images example be modified to train on other (new) images. For example, images of screenshots to identify elements that are in the images (such as: word…
Omnipresent on HNYes, you can use these models for fine-tuning (or feature extraction) on a new dataset. This tutorial would be a good place to start (esp. sections 2 and 3):…
fchollet on HN
A registry for loading and sharing models
From 2 comments
Question: Does anyone know of a library for loading models/weights from a registry of some sort?
chris_va on HNWell, this is fairly manual. More like: my_model = registry.get("tensorflow://github.com/asdf/models/imagine/latest") ... my_model.push("...")
chris_va on HN
Questions
Can the models be redistributed under MIT?
From 1 comment
Are you allowed to redistribute the models under the MIT License?
minimaxir on HN
Alternatives named
Caffe Model Zoo
From 1 comment
Caffenet also offers a set of pre-trained models in their "model zoo": https://github.com/BVLC/caffe/wiki/Model-Zoo
terhechte on HN
spaCy Sputnik
From 1 comment
You mean something like this: https://github.com/spacy-io/sputnik ?
elyase on HN