Name: Marcus Chaffim
Type: User
Company: University of Brasília
Bio: Marcus Chaffim is Assistant Professor of Electronic Engineering and member of the Graduate Program in Biomedical Engineering at University of Brasília, Brasil.
Twitter: chaffim
Location: https://goo.gl/x2TYo0
Blog: https://orcid.org/0000-0001-5876-9910
Marcus Chaffim's Projects
FastAC - Amir Said's Arithmetic and Huffman coding library, example code, and documentation
New generation entropy codecs : Finite State Entropy and Huff0
A graphical user interface (GUI) facilitating fluvial geomorphic covariance structure analysis (GCS).
source code and data sets of <Introduction to Data Compression> 5th edition
Imageinary is a reproducible mechanism which is used to generate large image datasets at various resolutions. The tool supports multiple image types, including JPEGs, PNGs, BMPs, RecordIO, and TFRecord files
Introduction to Image Processing
C++ JPEG compression/fuzzed low-RAM JPEG decompression codec with Public Domain or Apache 2.0 license
File compression library (includes 6 algorithms) with Qt GUI
Python and MATLAB code for linear algebra textbook.
LEARNING-BASED MULTI-FRAME VIDEO QUALITY ENHANCEMENT
Contains all my Matlab toolboxes.
Collection of support scripts to read/write/process light field data
Code that accompanies the book
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
Models and examples built with TensorFlow
NeMo: a toolkit for conversational AI
A collection of tools for neural compression enthusiasts.
Numerical Tours of Signal Processing
Synthesizing and manipulating 2048x1024 images with conditional GANs
A Python Implementation of the tabled Asymmetric Numeral Systems compression method.
Contourlet transform toolbox
Python interface to Curvelab (http://www.curvelet.org)
Python Productivity for ZYNQ
Computer Vision Overlays on Pynq
Collection of support scripts to read/write/process light field data
Pytorch implementation of 2D Discrete Wavelet (DWT) and Dual Tree Complex Wavelet Transforms (DTCWT) and a DTCWT based ScatterNet
Qt sample of compress and extract 7z format files with LZMA SDK.
The QMNIST dataset
Python Implementation of Reinforcement Learning: An Introduction