Wilfredo Martel's Projects
Bert预训练模型fine-tune计算文本相似度
BERT_Sentense_Similarity
BETO - Spanish version of the BERT model
Chatbot para discord en español programado en python usando Beto
Life-cycle: Internal working of HDFS, SQOOP, HIVE, SPARK, HBASE, KAFKA with code.
Source code for the book "Black Hat Python" by Justin Seitz. The code has been fully converted to Python 3, reformatted to comply with PEP8 standards and refactored to eliminate dependency issues involving the implementation of deprecated libraries.
Public repo for HF Semantic Search Explication
빅데이터 연합동아리 BOAZ 12기 ADV Vision 팀 [Fight Detection] 레포지토리입니다.
Twitter Bootstrap Ajax Typeahead Plugin
"Build Generative AI Apps with LangChain" is a repository that contains a comprehensive framework for building generative AI applications using LangChain, an innovative language modeling platform. This repository includes all the necessary code and documentation to help developers quickly build and deploy generative AI applications
A collection of usage examples for camunda BPM intended to get you started quickly
Chatbot in spanish using differents model: Seq2Seq model with Luong attention and transformer
Implementación de un ChatBot en Epañol/Spanish coon Soft Attention
Lightweight package for interacting with ChatGPT's API by OpenAI. Uses reverse engineered official API.
Powerful rich text editor framework with a modular architecture, modern integrations, and features like collaborative editing.
Official CKEditor 5 Angular 2+ component.
Modificación del componente para pruebas parciales.
Clinical Knowledge Graph (CKG) is a platform with twofold objective: 1) build a graph database with experimental data and data imported from diverse biomedical databases 2) automate knowledge discovery making use of all the information contained in the graph
Experiments with LLM-based code summarization using few-shot learning for use in technical audits.
ColBERT: Contextualized Late Interaction over BERT (code for SIGIR'20 paper)
Exercises and examples of my Computer Vision subject with Deep Learning
Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning
Abstract— Violence detection has been investigated extensively in the literature. Recently, IOT based violence video surveillance is an intelligent component integrated in security system of smart buildings. Violence video detector is a specific kind of detection models that should be highly accurate to increase the model’s sensitivity and reduce the false alarm rate. This paper proposes a novel architecture of ConvLSTM model that can run on low-cost Internet of Things (IOT) device such as raspberry pi board. The paper utilized convolutional neural networks (CNNs) to learn spatial features from video’s frames that were applied to Long Short- Term Memory (LSTM) for video classification into violence/non-violence classes. A complex dataset including two public datasets: RWF-2000 and RLVS-2000 was used for model training and evaluation. The challenging video content includes crowds and chaos, small object at far distance, low resolution, and transient action. Additionally, the videos were captured in various environments such as street, prison, and schools with several human actions such as playing football, basketball, tennis, swimming and eating. The experimental results show high performance of the proposed violence detection model in terms of average metrics having an accuracy of 73.35 %, recall of 76.90 %, precision of 72.53 %, F1 score of 74.01 %, false negative rate of 23.10 %, false positive rate of 30.20 %, and AUC of 82.0 %.
Server core components which are a part of ONLYOFFICE Document Server
Spanish text summarization demo using CoreNLP
Coursera: Data Structures and Algorithms Specialization
Notebook for quick search
Notebook for quick search