I'm Engineer & an AI Enthusiast with interest in applied AI and software development. I love working with and contributing to open source projects. Professional Computer Vision & ML/DL Expert with years of experience in researching and implementing optimized deployment solutions for various target platforms. Proven experience in deploying solutions to NVIDIA TensorRT, Intel Openvino, Android NDK's.
class Xiang(Minimalist):
def __init__(self):
self.professional_status = {
"role" : "Sr. Digital Engineer",
"company" : "Conneqt Digital",
}
self.degree_status = {
"level" : "BE",
"subject" : "Computer Science",
"institution" : "SGB University",
}
self.languages = ["python", "java", "C/C++"]
self.py_datasci_stack = ["opencv", "numpy", "scikit-learn", "keras", "pytorch"]
self.tools = ["dvc", "git", "android-studio", "vs-code"]
def main(self):
if not self:
self = self.__init__()
⚡ Some of my notable open source contributions:
-
Tensorrtx(4.6k Stars) - Integrated new Yolov5-v6.2 classification model support to infer using TensorRT IE (PR). SuperPoint Pytorch implementation using TensorRT IE (PR)
-
Tencent/Ncnn(15.5k Stars) - Added sample android based application which infers Yolov7 PyTorch model. (PR), the android sample is hosted at xiang-wuu/ncnn-android-yolov7
-
Yolov5 (30k Stars) - Added Gardio integration with hugging face spaces to offecial Yolov5 implementation.(PR)
-
Yolov6 (4k Stars) - Added DVC integration support to track data/model artifacts & support for MLOps integration. (PR)
-
Yolov7 (5.5k Stars) - Added TensorRT inference support to offecial Yolov7 implementation. (PR), also added some very basic functionality (PR)
-
xiang-wuu/TensorRT-PTQ🔒 - Post Training Quantization inference using TensorRT for different CNN Architectures.
-
xiang-wuu/opencv-projects🔒 - Collection of many usefull computer vision based projects for study and academic purposes.
-
xiang-wuu/activity-monitor-cpp🔒 - This is CPP implementation of User activity monitoring utility based on facial recogntion, this is primarily used to keep track of AFK/AFD user activity.
⚡:1st_place_medal: Deployment Releases
- AI developement evolution & AI/NN End-to-end Pipeline. ✔️🥇
- Resposnible for design & implementation of ML workflow pipeline using DVC+Git. ✔️🥇
- S.O.T.A TensorRT Release for full-body Gender Classification UseCase - (08/12/2022). ✔️🥇
- TensorRT Release for full-body Gender Classification based on ResNet-IBN-18-a Architecture - (21/11/2022). ✔️🥇
- TensorRT Release for Person ReID UseCase based on ResNet-IBN-18-a Architecture - (21/03/2022). ✔️🥇
⚡:1st_place_medal: Research Releases
- Multi Attribute Recognition Release based on DeepM.A.R & Weakly Supervised Implementation - (07/07/2021). ✔️🥇
- Multi Attribute Recognition Release based on IBN-Net architecture for Person & Vehicle UseCase - (07/12/2021). ✔️🥇
- Traffic Light Classification & Blinking State Detection Release - (25/12/2021). ✔️🥇
- Person Re-ID Release based on Resnet-IBN-Net-18-a architecture for Person UseCase - (01/03/2022). ✔️🥇
- Gender Classification Release based on GenNet architecture for Person UseCase - (28/05/2022). ✔️🥇
- Concurrent Gender Classification & Person ReID Release based on IBN-Net Architecture - (05/9/2022). ✔️🥇