A senior design project using distributed networking, sensors, and GPS positioning to correlate multiple wearable units' sensors, relative location and heading.

Maker Project Rocket

Caffe Computation Graph Optimization.

Implementation of "Fully Learnable Group Convolution for Acceleration of Deep Neural Networks", CVPR'19

动手学习TVM核心原理教程

volksdep is an open-source toolbox for deploying and accelerating PyTorch, ONNX and TensorFlow models with TensorRT.

Pytorch implementation of our paper accepted by CVPR 2020 (Oral) -- HRank: Filter Pruning using High-Rank Feature Map

pymotiontracker is a Python 3 library to read from an MPU6050 (accelerometer + gyroscope) Bluetooth module

Movement Study in Physic (Education with Python)

Acceleration and Compression of DeepFwFM.

Pytorch implementation of our paper (TNNLS) -- Pruning Networks with Cross-Layer Ranking & k-Reciprocal Nearest Filters

Pytorch implementation of our paper accepted by CVPR 2022 -- IntraQ: Learning Synthetic Images with Intra-Class Heterogeneity for Zero-Shot Network Quantization

Pytorch implementation of our paper accepted by ECCV2022 -- Dynamic Dual Trainable Bounds for Ultra-low Precision Super-Resolution Networks

Pytorch implementation of our paper accepted by ECCV 2022-- Fine-grained Data Distribution Alignment for Post-Training Quantization

Simulation of non-uniform motion on surface

💻 The Experiments of LLMs

[ICLR 2020] Once for All: Train One Network and Specialize it for Efficient Deployment

PyTorch implementation of "Dynamic Structure Pruning for Compressing CNNs" (AAAI 2023 Oral)

CircuitPython I2C driver for MPU9250 9-axis motion tracking device

[NeurIPS 2022, T-PAMI 2023] Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models