Pinned Repositories
aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
BRECQ
Pytorch implementation of BRECQ, ICLR 2021
caffe
This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors.
chineseocr_lite
超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
CNN-float-fixed-translation-
CNN中量化算法研究-浮点数定点数转换,包括定点数的运算
cnn-quantization
Quantization of Convolutional Neural networks.
Deformable-DETR
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
EasyQuant
EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.
fcn.berkeleyvision.org
Fully Convolutional Networks for Semantic Segmentation by Jonathan Long*, Evan Shelhamer*, and Trevor Darrell. CVPR 2015 and PAMI 2016.
FPN
Feature Pyramid Networks for Object Detection
cekcoco's Repositories
cekcoco/aimet
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
cekcoco/BRECQ
Pytorch implementation of BRECQ, ICLR 2021
cekcoco/caffe
This fork of BVLC/Caffe is dedicated to improving performance of this deep learning framework when running on CPU, in particular Intel® Xeon processors.
cekcoco/chineseocr_lite
超轻量级中文ocr,支持竖排文字识别, 支持ncnn、mnn、tnn推理 ( dbnet(1.8M) + crnn(2.5M) + anglenet(378KB)) 总模型仅4.7M
cekcoco/cnn-quantization
Quantization of Convolutional Neural networks.
cekcoco/Deformable-DETR
Deformable DETR: Deformable Transformers for End-to-End Object Detection.
cekcoco/EasyQuant
EasyQuant(EQ) is an efficient and simple post-training quantization method via effectively optimizing the scales of weights and activations.
cekcoco/GPTQ-for-LLaMa
4 bits quantization of LLaMA using GPTQ
cekcoco/I-BERT
[ICML'21 Oral] I-BERT: Integer-only BERT Quantization
cekcoco/insightface
State-of-the-art 2D and 3D Face Analysis Project
cekcoco/Learn-Statistical-Learning-Method
Implementation of Statistical Learning Method, Second Edition.《统计学习方法》第二版,算法实现。
cekcoco/leetcode-master
《代码随想录》LeetCode 刷题攻略:200道经典题目刷题顺序,共60w字的详细图解,视频难点剖析,50余张思维导图,支持C++,Java,Python,Go,JavaScript等多语言版本,从此算法学习不再迷茫!🔥🔥 来看看,你会发现相见恨晚!🚀
cekcoco/mlir
"Multi-Level Intermediate Representation" Compiler Infrastructure
cekcoco/mmdeploy
OpenMMLab Model Deployment Framework
cekcoco/MQBench
Model Quantization Benchmark
cekcoco/nanodet
⚡Super fast and lightweight anchor-free object detection model. 🔥Only 980 KB(int8) / 1.8MB (fp16) and run 97FPS on cellphone🔥
cekcoco/NumCpp
C++ implementation of the Python Numpy library
cekcoco/onnx
Open standard for machine learning interoperability
cekcoco/pacnet
Pixel-Adaptive Convolutional Neural Networks (CVPR '19)
cekcoco/ppq
PPL Quantization Tool (PPQ) is a powerful offline neural network quantization tool.
cekcoco/PytorchToCaffe
Pytorch model to caffe model, supported pytorch 0.3, 0.3.1, 0.4, 0.4.1 ,1.0 , 1.0.1 , 1.2 ,1.3 .notice that only pytorch 1.1 have some bugs
cekcoco/smoothquant
[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models
cekcoco/Tengine
Tengine is a lite, high performance, modular inference engine for embedded device
cekcoco/TPAT
TensorRT Plugin Autogen Tool
cekcoco/tpu-mlir
Machine learning compiler based on MLIR for Sophgo TPU.
cekcoco/transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.
cekcoco/triton
Development repository for the Triton language and compiler
cekcoco/tvm
Open deep learning compiler stack for cpu, gpu and specialized accelerators
cekcoco/vision_transformer
cekcoco/wincnn
Winograd minimal convolution algorithm generator for convolutional neural networks.