Pinned Repositories
Anime-Face-Detector
Detect faces and 28 landmarks from anime images
anime-vs-reality-classification
This project simply uses torchvision pretrained model to finetune and classify whether an image is anime or reality
BW-Anime-Arts-Colorization
Using gray image and user's input colors colorize black & white Anime Arts
ctranslate2-triton-backend
Triton backend for https://github.com/OpenNMT/CTranslate2
efficient-bearing-fault-diagnosis
Using Random NAS and QAT Quantizer to optimize model for Bearing Fault Diagnosis
mlabelImg
Modified version of labelImg, fix various errors
object-detection-data-synthesis
Synthesis data in YOLO format given background and object images
Playing-Cards-Detection
Just an simple project to test and using YoloV8
pyblur
Modified blurring routines from pyblur
YOLO-to-TensorRT-NMSBatched
Convert yolo models to ONNX, TensorRT add NMSBatched.
PD-Mera's Repositories
PD-Mera/ctranslate2-triton-backend
Triton backend for https://github.com/OpenNMT/CTranslate2
PD-Mera/efficient-bearing-fault-diagnosis
Using Random NAS and QAT Quantizer to optimize model for Bearing Fault Diagnosis
PD-Mera/Anime-Face-Detector
Detect faces and 28 landmarks from anime images
PD-Mera/pyblur
Modified blurring routines from pyblur
PD-Mera/YOLO-to-TensorRT-NMSBatched
Convert yolo models to ONNX, TensorRT add NMSBatched.
PD-Mera/cart-pole-dqn
Try to reproduce basic example of Deep Q Learning (DQN) with Pytorch
PD-Mera/GFPGAN
GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.
PD-Mera/labeling-tools-tutorial
Simple tutorial about how to run labeling tools
PD-Mera/object-detection-data-synthesis
Synthesis data in YOLO format given background and object images
PD-Mera/video2anything
Convert video to anything you want
PD-Mera/Vietnamese-License-Plate-Generator
Vietnamese License Plate Generator for OCR part
PD-Mera/BasicSR
Open Source Image and Video Restoration Toolbox for Super-resolution, Denoise, Deblurring, etc. Currently, it includes EDSR, RCAN, SRResNet, SRGAN, ESRGAN, EDVR, BasicVSR, SwinIR, ECBSR, etc. Also support StyleGAN2, DFDNet.
PD-Mera/detectron2
Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.
PD-Mera/fvcore
Collection of common code that's shared among different research projects in FAIR computer vision team.
PD-Mera/game-of-nim
Master the Minimax Algorithm and Alpha-Beta Pruning with Game of Nim
PD-Mera/minimalist-classification
A minimalist pipeline to training classification models
PD-Mera/mlabelImg
Modified version of labelImg, fix various errors
PD-Mera/MNIST-Classification
PD-Mera/nvidia-smi2
A tool for enriching the output of nvidia-smi.
PD-Mera/PD-Mera
PD-Mera/PD-Mera.github.io
PD-Mera/tqdm
A Fast, Extensible Progress Bar for Python and CLI
PD-Mera/triton-basic
An easy classification implement to explain how triton work
PD-Mera/understanding-onnx
Understanding about how ONNX store param and process model
PD-Mera/update-readme-image
A GitHub Action that allows you to update README with a random image, from a collection of your own images/logos.
PD-Mera/yolo-data-visualization
Visualize YOLO object detection data to check YOLO label
PD-Mera/YoloV5-DeepSORT
PD-Mera/img_utils
PD-Mera/object-detection-validation
Evaluation for object detection models
PD-Mera/tic-tac-toe
Make an unbeatable Tic-Tac-Toe AI, first step to Game AI