Dickson Neoh's starred repositories
Python-Apple-support
A meta-package for building a version of Python that can be embedded into a macOS, iOS, tvOS or watchOS project.
yolo-ios-app
Ultralytics YOLO iOS App source code for running YOLOv8 in your own iOS apps 🌟
auto-commit-msg
A VS Code extension to generate a smart commit message based on file changes
optimal_confidence_threshold
A FiftyOne Plugin that allows you to find the optimal confidence threshold fast and easy!
zero-shot-prediction-plugin
Run zero-shot prediction models on your data
fiftyone-plugins
A curated list of plugins that you can add to your FiftyOne install!
conda-mobile
A collection of conda recipes for cross compiling python, libraries, and extensions for iOS and Android
imbalanced-dataset-sampler
A (PyTorch) imbalanced dataset sampler for oversampling low frequent classes and undersampling high frequent ones.
sprout_downloader
Download videos from sites based on sproutvideo.com
candle-tutorial
Tutorial for Porting PyTorch Transformer Models to Candle (Rust)
Data-Centric-Machine-Learning-with-Python
Data-Centric Machine Learning with Python, published by Packt
zero_to_gpt
Go from no deep learning knowledge to implementing GPT.
accelerate
🚀 A simple way to launch, train, and use PyTorch models on almost any device and distributed configuration, automatic mixed precision (including fp8), and easy-to-configure FSDP and DeepSpeed support
micronet
micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape
review_object_detection_metrics
Object Detection Metrics. 14 object detection metrics: mean Average Precision (mAP), Average Recall (AR), Spatio-Temporal Tube Average Precision (STT-AP). This project supports different bounding box formats as in COCO, PASCAL, Imagenet, etc.