JK Jung's repositories
tensorrt_demos
TensorRT MODNet, YOLOv4, YOLOv3, SSD, MTCNN, and GoogLeNet
jetson_nano
This repository is a collection of scripts/programs I use to set up the software development environment on my Jetson Nano, TX2, and Xavier NX.
hand-detection-tutorial
A tutorial on how to train a hand detector with TensorFlow Object Detection API
yolov4_crowdhuman
A tutorial on training a DarkNet YOLOv4 model for the CrowdHuman dataset
tf_trt_models
TensorFlow object detection models accelerated with NVIDIA TensorRT (TF-TRT)
keras-cats-dogs-tutorial
A practical example of image classifier with Keras 2.x and TensorFlow backend, using the Kaggle Cats vs. Dogs dataset. By taking advantage of Keras' image data augmentation capabilities (and also random cropping), we were able to achieve 99% accuracy on the trained model with only 2,000 images in the training set.
keras_imagenet
Code for training Keras ImageNet (ILSVRC2012) image classification models from scratch
dqn-tx1-for-nintendo
My attempt to run DQN on Jetson TX1, which learns how to play Nintendo Famicom Mini games through reinforcement learning directly.
keras-yolo3
A Keras implementation of YOLOv3 (TensorFlow backend), which I used to train an object detector for the Kaggle 2018 "Google AI Open Images - Object Detection Track" competition
jkjung-avt.github.io
My blog posts
DeepMind-Atari-Deep-Q-Learner
DeepMind's DQN code + my tweaks (works on NVIDIA Jetson TX1)
py-faster-rcnn
Faster R-CNN (Python implementation) -- see https://github.com/ShaoqingRen/faster_rcnn for the official MATLAB version
caffe_merge_batchnorm
My repository for testing how to merge/remove BatchNorm and Scale layers in trained caffe models
dataset-tools
A collection of tools/scripts I use to process deep learning datasets
DeepLens_Notifier
An AWS DeepLens agent which sends a LINE notifier to me when it detects an event
Asset-Rx-Edge-Container-Tutorial
Welcome to the Tutorial for making your first Asset-Rx Edge Containers~
deeplearning-cats-dogs-tutorial
A Practical Introduction to Deep Learning with Caffe and Python (works on Jetson TX2)
llama2.c
Inference Llama 2 in one file of pure C
LodeRunner_TotalRecall
Lode Runner - Total Recall (超級**員-全面回憶) : Remake in HTML5
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.