Pinned Repositories
0xDeCA10B
Sharing Updatable Models (SUM) on Blockchain
Consensus-focus-for-object-detection
Dantzig-Algorithm-for-Earth-Mover-s-Distance-Wasserstein-
Dantzig's algorithm for parameters initialization given the Earth Mover's Distance (Wasserstein distance) model
Data-Augmentation-for-YOLOv5
This approach uses Data Augmentation to generate new samples given a training dataset.
ErikValle
jupyter-ros
Jupyter widget helpers for ROS, the Robot Operating System
pylabel
Python library to transform, analyze, and visualize computer vision annotations.
RTLAOI-DD
Relational-based Transfer Learning for Automatic Optical Inspection based on domain discrepancy
Traductor-de-Textos-en-Espanol-al-Sistema-Braille
The Translator of printed Spanish texts into Braille system aims to facilitate the access to information from documents that are not commonly available to people with visual disabilities. The translator is comprised of a mechanical system with linear actuators, which generates the Braille characters for reading, software designed for converting the acquired information from a text to recognizable symbols by this mechanism. It is possible to save, close, and erase acquired data via camera to a text file. For improving the experience between the user and this device, a “text to speech” software is included to read instructions, menu, and documents. An easy interface allows users to navigate quickly throw the main menu to manage files, get information about battery, storage, volume, etc. This device contains more features like translating Portable Document Format (PDF) and Microsoft Word documents into the Braille system.
tsinghua-tencent-100k
Tsinghua-Tencent 100K
ErikValle's Repositories
ErikValle/RTLAOI-DD
Relational-based Transfer Learning for Automatic Optical Inspection based on domain discrepancy
ErikValle/Consensus-focus-for-object-detection
ErikValle/Dantzig-Algorithm-for-Earth-Mover-s-Distance-Wasserstein-
Dantzig's algorithm for parameters initialization given the Earth Mover's Distance (Wasserstein distance) model
ErikValle/ErikValle
ErikValle/Automating-Workflows-with-GitHub-Actions
Automating Workflows with GitHub Actions, published by Packt
ErikValle/Awesome-Skeleton-based-Action-Recognition
A curated paper list of awesome skeleton-based action recognition.
ErikValle/consensus-WBF
ErikValle/DAFormer
Official Implementation of DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation [CVPR22]
ErikValle/DRT
ErikValle/episodic-memory
ErikValle/GitHubGraduation-2022
Join the GitHub Graduation Yearbook and "walk the stage" on June 11.
ErikValle/imbalanced-dataset-sampler
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
ErikValle/MCD_DA
ErikValle/MT-YOLOv7-AOI
ErikValle/opencv-1
Open Source Computer Vision Library
ErikValle/PVEL-AD
ErikValle/qlora
QLoRA: Efficient Finetuning of Quantized LLMs
ErikValle/sapiens
High-resolution models for human tasks.
ErikValle/SB-WBF
Consensus focus for object detection. Case I: Ensembling of multiple models.
ErikValle/SDR
PyTorch implementation of: Michieli U. and Zanuttigh P., "Continual Semantic Segmentation via Repulsion-Attraction of Sparse and Disentangled Latent Representations", CVPR 2021.
ErikValle/SSDA-YOLO
Codes for my paper "SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection"
ErikValle/StyleGAN-nada
Update to TF2
ErikValle/stylegan2-ada
StyleGAN2 with adaptive discriminator augmentation (ADA) - Official TensorFlow implementation
ErikValle/Surface-Defect-Detection
📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.
ErikValle/SurroundDepth
SurroundDepth: Entangling Surrounding Views for Self-Supervised Multi-Camera Depth Estimation
ErikValle/UbH-GCN
ErikValle/Video-K-Net
Code for our CVPR-2022 work: Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
ErikValle/VisionLearningGroup.github.io
ErikValle/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"
ErikValle/Weighted-Boxes-Fusion
Set of methods to ensemble boxes from different object detection models, including implementation of "Weighted boxes fusion (WBF)" method.