JumpServer 是全球首款开源的堡垒机,是符合 4A 的专业运维安全审计系统。
-
Updated
Sep 20, 2020 - JavaScript
{{ message }}
JumpServer 是全球首款开源的堡垒机,是符合 4A 的专业运维安全审计系统。
Tensorflow Faster RCNN for Object Detection
Mask RCNN in TensorFlow
Implementation EfficientDet: Scalable and Efficient Object Detection in PyTorch
Visual Question Answering in Pytorch
Helper functions to create COCO datasets
Computer vision based ML training data generation tool
Support PointRend, Fast_SCNN, HRNet, Deeplabv3_plus(xception, resnet, mobilenet), ContextNet, FPENet, DABNet, EdaNet, ENet, Espnetv2, RefineNet, UNet, DANet, HRNet, DFANet, HardNet, LedNet, OCNet, EncNet, DuNet, CGNet, CCNet, BiSeNet, PSPNet, ICNet, FCN, deeplab)
FoveaBox: Beyond Anchor-based Object Detector
Implementation of various human pose estimation models in pytorch on multiple datasets (MPII & COCO) along with pretrained models
The official homepage of the (outdated) COCO-Stuff 10K dataset.
Deformable Convolutional Networks + MST + Soft-NMS
various tools such as label-tools , data-augmentation , etc.
NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection.
Image Captions Generation with Spatial and Channel-wise Attention
Deep Learning Summer School + Tensorflow + OpenCV cascade training + YOLO + COCO + CycleGAN + AWS EC2 Setup + AWS IoT Project + AWS SageMaker + AWS API Gateway + Raspberry Pi3 Ubuntu Core
This is a tensorflow re-implementation of Faster R-CNN: Towards Real-Time ObjectDetection with Region Proposal Networks.
The fastest crypto online
FCOS: Fully Convolutional One-Stage Object Detection.
Training examples and results for ImageNet/CIFAR/COCO/VOC training.Image Classification/Object Detection.
A Clone version from Original SegCaps source code with enhancements on MS COCO dataset.
Add a description, image, and links to the coco topic page so that developers can more easily learn about it.
To associate your repository with the coco topic, visit your repo's landing page and select "manage topics."
I found a new tool makesense who is trying to do the same thing that you're already doing. Probably with some new thoughts in mind. I recently asked the author how that tool is doing differently: SkalskiP/make-sense#23
The author responded that we need multiple clicks while labeling in imglab. Though I didn't understand it well as I can control most of the things with