Maojianzeng
Master's degree, focusing on deep learning and video understanding.
YANSHAN UniversityChina
Pinned Repositories
100-Days-Of-ML-Code
100 Days of ML Coding
100-Days-Of-ML-Code-1
100-Days-Of-ML-Code中文版
3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)
3DCNN
3D convolutional neural network for video classification
Awesome-Chinese-LLM
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
C3D-tensorflow
C3D is a modified version of BVLC tensorflow to support 3D ConvNets.
CT-Net
[ICLR2022] official implementation of CT-Net
deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
Front-end-articles
分享我的编程经验和学习心得,订阅请点 watch
Some-Attention-codes
注意力机制在计算机视觉领域的应用主要使用于捕捉图像上的respective field,而在自然语言处理领域中的应用主要使用于定位关键的token。这个项目收集了几种代码简洁的注意力机制,调用起来十分方便,可以轻松移植到自己的网络中,提升性能。
Maojianzeng's Repositories
Maojianzeng/Some-Attention-codes
注意力机制在计算机视觉领域的应用主要使用于捕捉图像上的respective field,而在自然语言处理领域中的应用主要使用于定位关键的token。这个项目收集了几种代码简洁的注意力机制,调用起来十分方便,可以轻松移植到自己的网络中,提升性能。
Maojianzeng/100-Days-Of-ML-Code
100 Days of ML Coding
Maojianzeng/100-Days-Of-ML-Code-1
100-Days-Of-ML-Code中文版
Maojianzeng/3D-ResNets-PyTorch
3D ResNets for Action Recognition (CVPR 2018)
Maojianzeng/3DCNN
3D convolutional neural network for video classification
Maojianzeng/Awesome-Chinese-LLM
整理开源的中文大语言模型,以规模较小、可私有化部署、训练成本较低的模型为主,包括底座模型,垂直领域微调及应用,数据集与教程等。
Maojianzeng/C3D-tensorflow
C3D is a modified version of BVLC tensorflow to support 3D ConvNets.
Maojianzeng/CT-Net
[ICLR2022] official implementation of CT-Net
Maojianzeng/deep-learning-for-image-processing
deep learning for image processing including classification and object-detection etc.
Maojianzeng/Front-end-articles
分享我的编程经验和学习心得,订阅请点 watch
Maojianzeng/LateTemporalModeling3DCNN
Maojianzeng/LeetCodeAnimation
Demonstrate all the questions on LeetCode in the form of animation.(用动画的形式呈现解LeetCode题目的思路)
Maojianzeng/grok-1
Grok open release
Maojianzeng/lowcode-llm-demo
低代码与大语言模型的结合实践 demo
Maojianzeng/Medical_image_segmentation
some classic model used to segment the medical images like CT、X-ray and so on
Maojianzeng/Mini-Kinetics-200
Mini-Kinetics-200 data splits used in paper "Rethinking Spatiotemporal Feature Learning For Video Understanding"
Maojianzeng/RubiksNet
Official repo for ECCV 2020 paper - RubiksNet: Learnable 3D-Shift for Efficient Video Action Recognition
Maojianzeng/Something-Something-DataSet-Share
Something-Something DataSet shared on Baidu Netdisk