666DZY666/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

⭐ 2269 | 🍴 477

marcharper/python-ternary

:small_red_triangle: Ternary plotting library for python with matplotlib

⭐ 778 | 🍴 155

peakji/PJTernarySearchTree

Objective-C implementation of Ternary Search Tree for Mac OS X and iOS. Best for text autocompletion. Store any objects, auto pruning, serializing, unicode support.

⭐ 301 | 🍴 18

jakerdliu/OpenTrit-CHN

• OpenTrit, an open-source cross-framework mixed ternary toolkit, supports one-click conversion of mixed ternary models between PyTorch and TensorFlow. It encapsulates heterogeneous computing power scheduling and quantization optimization, addressing the issues of "framework dependency and poor usability" present in existing ternary tools.

⭐ 266 | 🍴 58