datumaro
DA-RetinaNet
| datumaro | DA-RetinaNet | |
|---|---|---|
| 2 | 2 | |
| 486 | 59 | |
| 2.5% | - | |
| 9.4 | 6.1 | |
| 2 days ago | 5 months ago | |
| Python | Python | |
| MIT License | MIT License |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
datumaro
-
Does anyone use CVAT for image annotation?
1) CVAT has internal inference for models. If you upload model there in the correct format, then it will be able to generate the detection box itself - https://onepanel.medium.com/train-an-object-detection-model-from-scratch-and-run-inference-on-it-in-10-minutes-16147ef656aa 2) Yes you can upload your prediction. But last time i did it - there were some problems and it took me several hours. It seems to me that you just need to load the markup in one of the formats that it supported by CVAT. If your format is not supported, then you will need to convert. For example like this - https://github.com/openvinotoolkit/datumaro
- Can I know what kind of dataset annotation for object detection is this?
DA-RetinaNet
- Detectron2 Da-RetinaNet, Unsupervised Domain Adaptation for object detection
-
Detectron2 DA-RetinaNet
Link to the repo DA-RetinaNet: https://github.com/fpv-iplab/DA-RetinaNet
What are some alternatives?
cocojson - Utility scripts for COCO json annotation format
layout-parser - A Unified Toolkit for Deep Learning Based Document Image Analysis
sahi - Framework agnostic sliced/tiled inference + interactive ui + error analysis plots
Unsupervised-Semantic-Segmentation - Unsupervised Semantic Segmentation by Contrasting Object Mask Proposals. [ICCV 2021]
datasets - 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
DA-Faster-RCNN - Detectron2 implementation of DA-Faster R-CNN, Domain Adaptive Faster R-CNN for Object Detection in the Wild
label-studio - Label Studio is a multi-type data labeling and annotation tool with standardized output format
globox - A package to read and convert object detection datasets (COCO, YOLO, PascalVOC, LabelMe, CVAT, OpenImage, ...) and evaluate them with COCO and PascalVOC metrics.
UCF-SST-CitySim1-Dataset - Official github page of UCF SST CitySim Dataset
mmdetection - OpenMMLab Detection Toolbox and Benchmark
synthetic-computer-vision - A list of synthetic dataset and tools for computer vision
BCNet - Deep Occlusion-Aware Instance Segmentation with Overlapping BiLayers [CVPR 2021]