Using SqueezeNet to classify video frames coming from a webcam or a smartphone camera

Address the crowd counting problem on the Mall dataset (sparse) by exploring regression-based (Xception) and density-based (CSRNet) approaches.

Pre-training of Deep Bidirectional Transformers for Language Understanding

Een beschrijving van het schakelprogramma Ad FDND -> Ba CMD. NB: private tot de examencommissie goedkeuring geeft!

Source codes and datasets for paper "Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives" (AAAI 2024)

PyTorch code for Finding in NAACL 2022 paper "Probing the Role of Positional Information in Vision-Language Models".

This repository is about how to pretrain language models on a custom corpus.

Comprehensive Project on training and fine-tuning transformer models using PyTorch and the Hugging Face Transformers library. Aimed at enthusiasts and researchers, it offers an accessible yet deep dive into the practical aspects of working with transformers for NLP tasks.

This is a simple modified Pytorch implementation of swap noise Denoising AutoEncoder for deep models on tabular data (Jahrer 2018).

My solution of BirdCLEF 2023.

Master Thesis for M.Sc. Business Education - Pre-Trained Denoising Autoencoders Long Short-Term Memory Networks as probabilistic Models for Estimation of Distribution Genetic Programming

Methodology to pre-train and evaluate a LLM to the Portuguese language

Pre-training a Transformer from scratch.

[Paper][Preprint 2024] Multi-domain Knowledge Graph Collaborative Pre-training and Prompt Tuning for Diverse Downstream Tasks

Large-Scale and Comprehensive Data Hub for Reinforcement Learning

The official GitHub page for the survey paper "Self-Supervised learning for Videos: A survey"

Pre-Training and Fine-Tuning transformer models using PyTorch and the Hugging Face Transformers library. Whether you're delving into pre-training with custom datasets or fine-tuning for specific classification tasks, these notebooks offer explanations and code for implementation.

Source codes and datasets for paper "Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives" (AAAI2024)

This project is dataset and model checkpoints for the paper "Query of CC: Unearthing Large Scale Domain-Specific Knowledge from Public Corpora".