ishang3 Goto Github PK

actionai

custom human activity recognition modules by pose estimation and cascaded inference using sklearn API

aws-create-thing-boto3

Create AWS IoT Thing using python and boto3

confusion-matrix

This goes through the ground truth and all the predictions made by the model and calculates False positives, true positives, False negatives - then based off a threshold value it calculates the precision and recall

create-thing

Create a thing Pragmatically

dataset-analysis

Takes dataset in kittiformat; returns histogram of annotation sizes; avg annotations per image, and cropping of each annotation in a separate folder

datataset-analysis

deepstream-demo

detectnet-4-models

distance-assistant

Pedestrian monitor that provides visual feedback to help ensure proper social distancing guidelines are being observed

junebaseline

kinesis-put-media

Python Script for pushing frames to kinesis video stream

mobilenetv1-ssd-tensorrt

Got 100fps on TX2. Got 1000fps on GeForce GTX 1660 Ti. Implement mobilenetv1-ssd-tensorrt layer by layer using TensorRT API. If the project is useful to you, please Star it.

rectlabel-support

RectLabel - An image annotation tool to label images for bounding box object detection and segmentation.

s3class

traffic-light-detection-with-yolov3-bosch-traffic-light-dataset

A tutorial for training YOLOv3 to detect traffic lights using BOSCH small traffic light dataset.

trt_pose

Real-time pose estimation accelerated with NVIDIA TensorRT

yolov4-tiny-tensorrt

Got 100fps on TX2. Got 500fps on GeForce GTX 1660 Ti. Implement yolov4-tiny-tensorrt layer by layer using TensorRT API. If the project is useful to you, please Star it.