robertklee/coco-human-pose

Train a stacked hourglass deep neural network for human pose estimation on the COCO 2017 dataset.

Welcome to my GitHub!

👋 I am an award-winning and ambitious B.Eng. in electrical/computer engineering passionate about:

• machine learning (specifically computer vision problems)
• software engineering
• firmware engineering and embedded systems

💼 Workplace: Microsoft Software Engineer II.

I currently work on vector search within Azure Search team.

👨‍💻 I'm currently working on:

• building and hosting my own personal website (check it out here!)
• creating a computer vision project for 3D bounding box for autonomous vehicle applications

✅ Some of my most exciting projects include:

• Human Pose Estimation on COCO 2017 Dataset: I led a team to design and train a deep neural network for human pose estimation (labelling various joint locations). Using a modified stacked hourglass network and a newly implemented data ingestion and preprocessing pipeline, we achieved results comparable with state-of-the-art from late 2017, in less than three months of work.

• Road Segmentation Machine Learning Project on KITTI ROAD dataset: A convolutional neural network (CNN) for semantic segmentation of road surfaces within a driving context.

• Embedded C Optimization Project with Discrete Cosine Transform algorithm: Implementation of DCT algorithm in C and optimizing performance using more efficient software algorithms, software-level optimizations, and hypothetical firmware- and hardware-based optimizations.

• Computer Vision Project on Monocular Depth Estimation: A CNN for depth estimation on DrivingStereo dataset using Keras & Python.

📝 Reach out to me on LinkedIn if you want to collaborate or connect!

coco-human-pose's Issues

mutli person keypoint detection

Dear Author,

Great work. I have borrowed your code to parse the coco json annotations using pandas data frame. Thank you for that.
I have some queries regarding your implementation. I see you have cropped the person and give it to training, the model only learns to detect single person in the image?

Cannot open human pose estimation project

Hi, I was actually looking for a way to deploy image segmentation project and mainly I wanted to see if I can use spaces to take raw video feed from my webcam as input and use various models to check the segmentation live on the web. Is it possible to do such live testing using spaces??

Missing from streamlit gallery

Hello!
It is more of a query rather than an issue, but I cannot find the deployed demo app which was earlier present in gallery on Streamlit's official site.

Is there any particular reason behind it? If yes, when would it be back up?

Thanks.