kann
smaz
kann | smaz | |
---|---|---|
5 | 3 | |
656 | 1,131 | |
- | - | |
0.0 | 0.0 | |
over 2 years ago | over 4 years ago | |
C | C | |
GNU General Public License v3.0 or later | BSD 3-clause "New" or "Revised" License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
kann
- Small tensor library in C99
-
C with Deep Learning
TensorFlow has C APIs. I developed KANN from scratch for deep learning. It supports CNN, LSTM and complex topologies. For simple MLPs, you can implement your own as a practice. Use a BLAS library for performance.
-
Implementing Faster R-CNN in C
After some research, I have reached the conclusion that I should use Faster R-CNN. So far, I have completed a classification task with a basic CNN using the C Kann library, as it can create basic layers and has basic functionalities..
-
Using Kann library to classify color images with a CNN
I'm trying to use the kann library to create a model that classifies color images using a CNN, following the mnist cnn example.
-
C Deep
KANN - Two-file ANN library. MIT
smaz
-
Advanced MessagePack capabilities
Choose the data compression algorithm based on the specifics of your data. For example, if you are working with lots of short strings, take a look at [*SMAZ](https://github.com/antirez/smaz).*
-
Improving short string compression.
Take a look at this. Idea behind it seems nice, but it's fixed dictionary ("codebook") was clearly made for English language, and the algorithm itself is really simple. How can we impove on this? Dynamic dictionary won't do, since you have to store it somewhere, nullifying benefits of using such algorithm. Beyond that I have no idea.
-
C Deep
smaz - Efficient string compression library. BSD-3-Clause
What are some alternatives?
Genann - simple neural network library in ANSI C
LZMAT - git mirror of LZMAT (http://www.matcode.com/lzmat.htm)
ZLib - A massively spiffy yet delicately unobtrusive compression library.
Snappy - A fast compressor/decompressor
darknet - Convolutional Neural Networks
doboz
tensorflow - An Open Source Machine Learning Framework for Everyone
zstd - Zstandard - Fast real-time compression algorithm
GLFW - A multi-platform library for OpenGL, OpenGL ES, Vulkan, window and input
Redis - Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs, Bitmaps.
LZHAM - Lossless data compression codec with LZMA-like ratios but 1.5x-8x faster decompression speed, C/C++