Comments (19)
@prakharchoudhary Ofcourse! Feel free to work on it. I think to ensure efforts are not duplicated, before working on adding the examples, mention the model here so that everyone is aware of it.
from fabrik.
I think we should also try just importing Keras layers with recurrent layers too. That might be easier / more reliable since Keras's support for recurrent layer is much better than caffe.
For instance, you can try importing model definition from here:
https://github.com/fchollet/deep-learning-models/blob/master/music_tagger_crnn.py
https://machinelearningmastery.com/text-generation-lstm-recurrent-neural-networks-python-keras/
https://github.com/mineshmathew/char_rnn_karpathy_keras/blob/master/char_rnn_of_karpathy_keras.ipynb
https://github.com/afgiel/lstm_lm/blob/master/generate.py
https://github.com/philipperemy/keras-attention-mechanism/blob/master/attention_lstm.py
from fabrik.
@dexter1691 Since there are multiple models from several domains that can be added, would it be okay for me to work on this issue as well?
from fabrik.
@dexter1691 I would need to export that keras model to a json file, right?
from fabrik.
@dexter1691 can I take this?
from fabrik.
@Ram81 : Go for it! Thanks!
from fabrik.
@dexter1691 can you point us to some of the models!
from fabrik.
@Ram81 you could look at Captioning models (Show and Tell, Neuraltalk), VQA models, and Text generation models.
from fabrik.
@utsavgarg I am referring this one https://github.com/jeffdonahue/caffe/blob/recurrent-rebase-cleanup/examples/coco_caption/lstm_language_model.prototxt as of now but I would need keras models right?
from fabrik.
@utsavgarg would it be fine if I export this model https://github.com/fchollet/keras/blob/master/examples/lstm_text_generation.py to json then use it as an example?
from fabrik.
@Ram81 you could do it in Caffe or Keras, but choose one out of these two as they are quite similar.
from fabrik.
@utsavgarg I used this model https://github.com/jeffdonahue/caffe/blob/recurrent-rebase-cleanup/examples/coco_caption/lstm_language_model.prototxt & tested it in here's the model
But when I tried to export it to keras it says Can't determine size of HD5Data layer
from fabrik.
Also there are some examples available but I would need to obtain a json file through its implementation if you want I can test them too.
from fabrik.
@Ram81 When you are adding this network, can you also see how to handle the visualization for it better? Also, the error for export to Keras is expected so that is fine.
from fabrik.
@utsavgarg Okay I will take care of the visualization.
from fabrik.
@Ram81 yes
from fabrik.
@utsavgarg I will create a PR for this model & start with adding examples for keras too.
from fabrik.
@dexter1691 , is it ok if I work on it too? Correct me if I'm wrong, but more examples will do no harm.
from fabrik.
Multiple examples added in #125, #134, #140 and #166.
from fabrik.
Related Issues (20)
- Feature Request: Add a new section in Model Zoo for Generation HOT 8
- Create documentation listing currently supported layers for Keras, Caffe and TensorFlow HOT 2
- Unable to export model
- "docker-compose up --build" throws DistributionNotFound error HOT 5
- Fabrik is built with DEBUG settings HOT 1
- Collaboration with GiraffeTools
- Improving security in shared links HOT 1
- networkId in caffe_app/consumers.py undefined when modifying parameters of layers HOT 1
- psycopg2 causes error while installing fabrik on ubuntu 18.04 HOT 4
- Trouble while installing, localhost doesn't show up in available sites while setting up GitHub authentication HOT 1
- Travis CI test for PRs fails by default. HOT 2
- [docs] Documentation headings unclear
- [Wiki] Fabrik Wiki outdated, mentions IDE instead of Fabrik.
- Upgrade from Python2.7 to Python3
- Broken links HOT 1
- Deprecation warning with some dependencies !! HOT 2
- Installation Faliure: No module named skimage.io HOT 4
- Need to add settings/dev.py as in order for migration to work (modified from the provided dev.sample.py)
- django.db.utils.OperationalError: could not translate host name "db" to address: Name or service not known
- Canβt be deployed according to readme
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. πππ
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from fabrik.