neukaren

neukaren's Stars

• open-mmlab/mmdetection

  OpenMMLab Detection Toolbox and Benchmark

  Language:Python30k3728.4k9.5k

• google-research/vision_transformer

  Language:Jupyter Notebook10.8k1062071.3k

• facebookresearch/SlowFast

  PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

  Language:Python6.7k986941.2k

• dvgodoy/dl-visuals

  Over 200 figures and diagrams of the most popular deep learning architectures and layers FREE TO USE in your blog posts, slides, presentations, or papers.

  1.4k322122

• LeapLabTHU/DAT

  Repository of Vision Transformer with Deformable Attention (CVPR2022) and DAT++: Spatially Dynamic Vision Transformerwith Deformable Attention

  Language:Python815133674

• kennethleungty/Neural-Network-Architecture-Diagrams

  Diagrams for visualizing neural network architecture (Created with diagrams.net)

  78741475

• bubbliiiing/ssd-pytorch

  这是一个ssd-pytorch的源码，可以用于训练自己的模型。

  Language:Python6968101176

• facebookresearch/LeViT

  LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

  Language:Python606112873

• ChenhongyiYang/QueryDet-PyTorch

  [CVPR 2022 Oral] QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection

  Language:Python444610448

• Icecream-blue-sky/Past-and-present-small-object-detection

  Latest paper about small object detection

  42911153

• yatengLG/SSD-Pytorch

  SSD目标检测算法(Single Shot MultiBox Detector)(简单,明了,易用,全中文注释,单机多卡训练,视频检测)( If you train the model on a single computer and mutil GPU, this program will be your best choice , easier to use and easier to understand )

  Language:Python3981116187

• hyz-xmaster/VarifocalNet

  VarifocalNet: An IoU-aware Dense Object Detector

  Language:Python35193552

• wkentaro/imgviz

  Image Visualization Tools (object detection, semantic and instance segmentation)

  Language:Python247111530

• cvondrick/ihog

  Visualizing Object Detection Features. ICCV 2013

  Language:C++223338127

• hustvl/TinyDet

  Language:Python875316

• haohaobaozhi/soft

  本仓库所提供的所有软件均来自于互联网，个人存放在此作为备用，以备将来不时之需，同时作为大家的分享和学习成果，仅供个人研究和学习使用，请勿用于商业用途，下载后请于24小时内删除，请支持正版！ 附: 二○○二年一月一日《计算机软件保护条例》第十七条规定：为了学习和研究软件内含的设计**和原理，通过安装、显示、传输或者存储软件等方式使用软件的，可以不经软件著作权人许可，不向其支付报酬!

  773071

• damo-cv/GiraffeDet

  Language:Python73596

• coeusguo/ceit

  Language:Python592111

• yuchenZhangTG/SSD_resnet_pytorch

  Language:Python474513

• renmengye/oc-fewshot-public

  Code associated with paper "Wandering Within a World: Online Contextualized Few-Shot Learning"

  Language:Python24826

• cjf8899/SSD_ResNet_Pytorch

  :boat:ResNet based SSD, Implementation in Pytorch

  Language:Jupyter Notebook23407

• icedle/CBPH-Net

  Language:Python9131

• laochen330/HR-FPN

  Language:Python8112

• Liudadadabao/YOLOv3_Visualizer

  This is a CNN visualizer designed for YOLOv3 object detection algorithm.

  Language:Python4103

• arojsubedi/SIoU

  SIoU implementation for the YOLOv8

  Language:Python211

• mahdilamb/yolo-visualization

  Alternative ways of visualizing yolo outputs

  Language:Python1100

• MohamedRamadan-prog/-RASPBERRY-PI---YOLO-implementation-

  5.3.2 RUNNING YOLO ALGORITHM ON LIVE CAMERA FEED (REALTIME) - When trying to implement the code in real-time, we were shocked by the results as we discovered that the raspberry-pi resources can’t handle real-time processing. - After running few optimizations on the code and increasing the swap memory of the raspberry -pi to the maximum, we were able to run the module and get results, but it can be considered as bad results as explained below: - The code worked but its processing was too slow as it took a huge time just to build the network and load the weights of our model. Furthermore, even after all that time the real time processing of the raspberry is slow, and the visualized frame is lagging a lot from the real captured frame. -The code was working with a rate less than 1 FPS, which is not acceptable nor logical to work with, but we managed to make it work and detect persons and vehicles accurately but with a cost which is speed. - so for just a prototype, we can consider it as a successful trial.

  Language:Python120

• neukaren/ceit-transformers

  Language:Python1000

• neukaren/LeViT-transformers

  LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference

  Language:Python1000

• zjjszj/kaggle_ps_dm_faster-rcnn.pytorch-pytorch-1.0

  Language:Python10