lvaleriu Goto Github PK

followers: 37.0 following: 101.0 repos: 249.0 gists: 3.0

Name: Valeriu Lacatusu

Type: User

Company: @Meta

Bio: R&D engineer and developer. Expertise in computer vision and visual documents understanding

Location: France

Valeriu Lacatusu's Projects

3d-resnets-pytorch

3D ResNets for Action Recognition (CVPR 2018)

accord-net-extensions

Advanced image processing and computer vision algorithms made as fluent extensions and built for portability

activitynet-2016-cvprw

Tools to participate in the ActivityNet Challenge 2016

aer-cnn-keras

Convolutional Neural Network based implementation of Audio Event Recognition in KERAS

AForge.NET Framework is a C# framework designed for developers and researchers in the fields of Computer Vision and Artificial Intelligence - image processing, neural networks, genetic algorithms, machine learning, robotics, etc.

ai_documentlayoutanalysis

AI_DocumentLayoutAnalysis

asr-study

Implementation of all-neural speech recognition systems using Keras and Tensorflow

attention-is-all-you-need-keras

A Keras+TensorFlow Implementation of the Transformer: Attention Is All You Need

audio-classifier-keras-cnn

Audio Classifier in Keras using Convolutional Neural Network

audio_preprocessor

To create a HDF file with representations for large-scale audio data

awesome-action-recognition

A curated list of action recognition and related area resources

awesome-deep-vision

A curated list of deep learning resources for computer vision

awesome-rnn

Recurrent Neural Network - A curated list of resources dedicated to RNN

bagotricks

Silverlight Bag of tricks (port of Kevin's WPF Bag-o-Tricks)

bert

TensorFlow code and pre-trained models for BERT

bert-as-service

Mapping a variable-length sentence to a fixed-length vector using BERT model

bert-toxic-comments-multilabel

Multilabel classification for Toxic comments challenge using Bert

birdsong-keras

Birdsong classification in noisy environments with Convolutional Neural Networks implemented in Keras Deep Learning library for the BIRDCLEF 2016 competition. Can be fine-tuned to arbitrary audio classification task.