Michalis Papakostas's Projects
http://nlp.seas.harvard.edu/2018/04/03/attention.html
Anticipatory Autoregressive Models
Caffe: a fast open framework for deep learning.
Caffe models in TensorFlow
A neural network classifier for urban soundscapes
A deep learning framework for Speech-Music discrimination of continuous audio streams
CogBeacon is a multi-modal dataset designed to target the effects of cognitive fatigue in human performance. The dataset consists of 76 sessions collected from 19 male and female users performing different versions of the Wisconsin Card Sorting Test (WCST); a popular cognitive test in experimental and clinical psychology designed to assess cognitive flexibility, reasoning and specific aspects of cognitive functioning. During each session we record and fully annotate, user's EEG functionality, facial keypoints, real-time self-reports on cognitive fatigue, as well as detailed information of the performance metrics achieved during the cognitive task (success rate, response time, number of errors etc.). Along with the dataset we provide a baseline Machine Learning analysis towards predicting cognitive fatigue and our multi-modal implementation of the WCST, to allow other researches expand or modify the functionalities of the CogBeacon data-collection framework. To our knowledge, this is the first multi-modal dataset specifically designed to assess cognitive fatigue.
An implementation of convolutional lstms in tensorflow. The code is written in the same style as the basiclstmcell function in tensorflow
Markerless pose estimation of user-defined features with deep learning for all animals, including humans
A tool to detect 55 landmark points on a given ear image.
EEG Dataset for the paper: Towards Predicting Task Performance from EEG Signals
:memo: A text file containing 479k English words for all your dictionary/word-based projects e.g: auto-completion / autosuggestion
TensorFlow examples
:fire: 2D and 3D Face alignment library build using pytorch
A simple library for Fréchet Audio Distance (FAD) calculation
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
This is a GUI designed for the specific needs of the https://www.nsf.gov/awardsearch/showAward?AWD_ID=1565328&HistoricalAwards=false project
labelpix is a graphical image labeling interface for drawing bounding boxes
Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax
Lisa Anne's public caffe code.
Implementation of the LLaMA language model based on nanoGPT. Supports flash attention, Int8 and GPTQ 4bit quantization, LoRA and LLaMA-Adapter fine-tuning, pre-training. Apache 2.0-licensed.
Unify Efficient Fine-Tuning of 100+ LLMs
Hugging Face implementation to train a GPT-2 model on LMD logging in WandB
Midi event transformer for music generation