Страница телеграм канала Spark in me - Internet, data science, math, deep learning, philosophy
Spark in me - Internet, data science, math, deep learning, philosophy
1332 подписчиков
All this - lost like tears in rain. Internet, data science, math, deep learning, philosophy. No bs. Our website - http://spark-in.me Our chat - https://goo.gl/WRm93d DS courses review - http://goo.gl/5VGU5A - https://goo.gl/YzVUKf
Входит в категории: Технологии
27.05.2019 11:05
2019 DS / ML digest 11
Highlights of the week(s)
- New attention block for CV;
- Reducing the amount of data for CV 10x?;
- Brain-to-CNN interfaces start popping up in the mainstream;
https://spark-in.me/post/2019_ds_ml_digest_11
#digest
#deep_learning
27.05.2019 11:05
Have finished building demo and landing page for my project on mention classification. The idea of this project is to create a model which can assign some labels to objects based on their mentions in context. Right now it works only for people mentions, but if I find interest in this work, I will extend the model to other types like organizations or events. For now, you can check out the online demo of the neural network.
The current implementation can take account of several mentions at a time, so it can distinguish relevant parts of the context, not just averaging prediction.
Its also open sourced, and built with AllenNLP framework from training to serving. Take a look at it.
More technical details of implementation coming later.
24.05.2019 12:05
Really working in the wild audio noise reduction libraries
Spectral gating
https://github.com/timsainb/noisereduce
It works. But you need a sample of your noise.
Will work well out of box for larger files / files with gaps where you can pay attention to each file and a part of file that would act as noise example.
RNNoise: Learning Noise Suppression
Works with any arbitrary noise. Just feed your file.
It works more like adative equalizer.
It filters noise when there is no speech.
But it mostly does not change audio when speech is present.
As authors explain, it improves snr overall and makes sound less "tiring" to listen.
Description / blog posts
- https://people.xiph.org/~jm/demo/rnnoise/
- https://github.com/xiph/rnnoise
Step-by-step instructions in python
- https://github.com/xiph/rnnoise/issues/69
#audio
#deep_learning
20.05.2019 09:05
New in our Open STT dataset
https://github.com/snakers4/open_stt#s
- An mp3 version of the dataset;
- A torrent for mp3 dataset;
- A torrent for the original wav dataset;
- Benchmarks on the public dataset / files with "poor" annotation marked;
#deep_learning
#data_science
#dataset
19.05.2019 19:05
https://pytorch.org/blog/stochastic-weight-averaging-in-pytorch/
14.05.2019 06:05
2019 DS / ML digest 10
Highlights of the week(s)
- New MobileNet;
- New PyTorch release;
- Practical GANs?;
https://spark-in.me/post/2019_ds_ml_digest_10
#digest
#deep_learning
09.05.2019 14:05
Habr.com / TowardsDataScience post for our dataset
In addition to a github release and a medium post, we also made habr.com post:
- https://habr.com/ru/post/450760/
Also our post was accepted to an editors pick part of TDS:
- http://bit.ly/ru_open_stt
Share / give us a star / clap if you have not already!
Original release
https://github.com/snakers4/open_stt/
#deep_learning
#data_science
#dataset
09.05.2019 13:05
The State of ML, eof 2018 in Russian
Quite down-to-earth and clever lecture
Some nice examples for TTS and some interesting forecasts (some of them happened already). #deep_learning
Some nice examples for TTS and some interesting forecasts (some of them happened already). #deep_learning
09.05.2019 13:05
PyTorch DP / DDP / model parallel
Finally they made proper tutorials:
- https://pytorch.org/tutorials/beginner/blitz/data_parallel_tutorial.html
- https://pytorch.org/tutorials/intermediate/model_parallel_tutorial.html
- https://pytorch.org/tutorials/intermediate/ddp_tutorial.html
Model parallel = have parts of the same model on different devices
Data Parallel (DP) = wrapper to use multi-GPU withing a single parent process
Distributed Data Parallel = multiple processes are spawned across cluster / on the same machine
#deep_learning
03.05.2019 11:05
PyTorch
PyTorch 1.1
https://github.com/pytorch/pytorch/releases/tag/v1.1.0
- Tensorboard (beta);
- DistributedDataParallel new functionality and tutorials;
- Multi-headed attention;
- EmbeddingBag enhancements;
- Other cool, but more niche features:
- nn.SyncBatchNorm;
- optim.lr_scheduler.CyclicLR;
#deep_learning