Spark in me - Internet, data science, math, deep learning, philo

snakers4 @ telegram, 1812 members, 1759 posts since 2016

All this - lost like tears in rain.

Data science, ML, a bit of philosophy and math. No bs.

Our website
- http://spark-in.me
Our chat
- https://t.me/joinchat/Bv9tjkH9JHbxiV5hr91a0w
DS courses review
- http://goo.gl/5VGU5A
- https://goo.gl/YzVUKf

Posts by tag «computer_vision»:

snakers4 (Alexander), October 22, 2018

Amazing articles about image hashing

Also a python library

- Library github.com/JohannesBuchner/imagehash

- Articles:

fullstackml.com/wavelet-image-hash-in-python-3504fdd282b5www.hackerfactor.com/blog/index.php?/archives/529-Kind-of-Like-That.html

www.hackerfactor.com/blog/index.php?/archives/432-Looks-Like-It.html

www.hackerfactor.com/blog/index.php?/archives/529-Kind-of-Like-That.html

#data_science

#computer_vision

JohannesBuchner/imagehash

A Python Perceptual Image Hashing Module. Contribute to JohannesBuchner/imagehash development by creating an account on GitHub.


Text iterators in PyTorch

Looks like PyTorch has some handy data-processing / loading tools for text models - torchtext.readthedocs.io.

It is explained here - bastings.github.io/annotated_encoder_decoder/ - how to use them with pack_padded_sequence and pad_packed_sequence to boost PyTorch NLP models substantially.

#nlp

#deep_learning

snakers4 (Alexander), April 10, 2018

Yolov3 - best paper.

But not in terms of scientific contribution, but rebuttal of DS community BS.

Very funny read.

- pjreddie.com/media/files/papers/YOLOv3.pdf

If you want a proper comparison of object detection algorithms - use this paper arxiv.org/abs/1611.10012

Looks like SSD and YOLO are reasonably good and fast, and RCNN can be properly tuned to be 3-5x slower (not 100x) and more accurate.

#data_science

#computer_vision

Download YOLOv3.pdf 2.14 MB

snakers4 (Alexander), January 09, 2018

When I started doing CV - this page was quite scarce.

Now it's full and amazing!

I recommend this page as your go-to reference for already implemented non CNN based (classic) CV. It is just amazing. Simple and illustrative examples with code.

This totally eliminates the need in open-cv abomination =)

scikit-image.org/docs/dev/auto_examples/index.html

Best libraries for images I have seen so far

- pillow (pillow simd)

- skimage

- imageio

- scikit video

- moviepy

#data_science

#computer_vision

snakers4 (Alexander), January 02, 2018

Interesting dataset with room layouts (a lot of them)

- lsun.cs.princeton.edu/2015.html

- lsun.cs.princeton.edu/2016/

#datasets

Pillow-SIMD is a Pillow fork, that claims 3-6x faster performance on CPU using same resources

- github.com/uploadcare/pillow-simd

- habrahabr.ru/post/301576/

It claims to be this easy

$ pip uninstall pillow
$ CC="cc -mavx2" pip install -U --force-reinstall pillow-simd

#computer_vision

uploadcare/pillow-simd

The friendly PIL fork. Contribute to uploadcare/pillow-simd development by creating an account on GitHub.


habrahabr.ru/post/301576/

Pillow-SIMD

Ускорение операций в 2.5 раза по сравнению с Pillow и в 10 по сравнению с ImageMagick Pillow-SIMD — это «форк-последователь» библиотеки работы с изображениями...


snakers4 (Alexander), October 29, 2017

Судя по прошлому опросу просили полнотекстовую статью.

В прошлый раз по итогу конкурса сил хватило только на пост на канале. В этот раз я разродился чутка причесать код, выложить тетрадки и написать целый длинный блог пост. По сути было весело:

- новый домен - видео - и сгенерирована тонна копипасты для работы с ним в тетрадках;

- новые sota модели для изучения;

- изучен и весьма распробован новый фреймворк - pytorch;

Статья

- spark-in.me/post/fish-object-detection-ssd-yolo

Комментируйте, репостите, шлите друзьям, критикуйте.

И как всегда можно:

- Поставить оценку каналу тут - telegram.me/tchannelsbot?start=snakers4 (1000+ подписчиков и только 50+ оценок - 5% как бы норм, но почему не больше?)

- Задонатить на новые статьи и развитие канала (вести канал несложно, статьи и соревнования занимают очень много времени) тут:

-- На чай - goo.gl/zveIOr

-- Договор ТКС 5011673505

#data_science

#deep_learning

#computer_vision

Identify fish challenge - playing with object detection

My path to learning SSD and YOLO and my experience in participating in a video object search competition with 300+GB of data Статьи автора - http://spark-in.me/author/snakers41 Блог - http://spark-in.me


older first