This is your work, valued

Kuala Lumpur, Malaysia

Dickson Neoh

Elite
@dnth

Full stack AI engineer specializing in deploying computer vision models on edge devices for real-time inference.

DEIMKit. DEIMKit is a Python package that provides a wrapper for DEIM: DETR with Improved Matching for Fast Convergence. Check out the original repo for more details.

121

yolov5-deepsparse-blogpost. By the end of this post, you will learn how to: Train a SOTA YOLOv5 model on your own data. Sparsify the model using SparseML quantization aware training, sparse transfer learning, and one-shot quantization. Export the sparsified model and run it using the DeepSparse engine at insane speeds. P/S: The end result - YOLOv5 on CPU at 180+ FPS using on

56

timm-flutter-pytorch-lite-blogpost. PyTorch at the Edge: Deploying Over 964 TIMM Models on Android with TorchScript and Flutter.

45

supercharge-your-pytorch-image-models-blogpost. Supercharge Your PyTorch Image Models: Bag of Tricks to 8x Faster Inference with ONNX Runtime & Optimizations

24

behavior-dataset. Dataset for behavior recognition on NAO

8

yolov5-torchscript-flutter-blogpost. YOLOv5 real time inference on Android with Torchscript and Flutter

6

huggingface-timm-mobile-blogpost. Bringing High-Quality Image Models to Mobile: Hugging Face TIMM Meets Android & iOS

6

mafat-fastdup-blogpost. Data insights from the MAFAT Satellite Vision challenge.

3

deployment-frameworks. Python

3

fastdup-manage-clean-curate-blogpost. Find duplicate and anomalies in your dataset. Identify wrong/confusing labels in your dataset. Uncover data leak in your dataset.

3

cvat-gradio. Load CVAT datasets into Gradio

2

clean-up-digital-life-fastdup-blogpost. Eliminate duplicates, blurry, dark, bright and broken images with fastdup and Python.

2

YOLOX-teras-plate-det-rec. YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/

1

design-patterns-in-python. My practice to implement design patterns in Python

1

zenml-optuna. Jupyter Notebook

1

flutter-login-template. Dart

1

microalgae-cell-counter-blogpost. Accompanying repo for the blogpost Modelling a Microalgae Cell Counter with Deep Learning on dicksonneoh.com

1

ram-onnx-inference. Jupyter Notebook

1

satellite-image-deep-learning-course. Jupyter Notebook

1

dl-android-hf-blogpost. Dart

1

dnth.

1

mmdetection. OpenMMLab Detection Toolbox and Benchmark

1

webdemo-microalgae-detection. Jupyter Notebook

1

webdemo-fridge-detection. Jupyter Notebook

1

soc_data. Jupyter Notebook

1

deepwork-pomodoro. My personal pomodoro timer for deep work

1

PhD. Jupyter Notebook

1

yolox-body-head-hand-face. Jupyter Notebook

1