Mask_RCNN

开源

Keras和TensorFlow上用于物体探测和实例分解的遮罩 R-CNN

25.6K stars0 点赞0 次浏览

工具介绍

Keras和TensorFlow上用于物体探测和实例分解的遮罩 R-CNN

用于物体探测和分片的遮罩 R-CNN 这是在Python 3,Keras,和TensorFlow上实施Mask R-CNN. 该模型为图像中对象的每个实例生成边框和分块口罩. 它基于地物金字塔网络(FPN)和ResNet101主干. 该寄存器包括: 在FPN和ResNet101上所建的Mask R-CNN的源代码. MS COCO Jupyter笔记本的预培训权重,可视化每个步骤的检测管道平行模式课程多GPU培训 MS COCO 度量衡(AP)评价自行数据集培训实例代码有文件记载,设计上便于扩展. 如果您在研究中使用它,请考虑引用此寄存器(下面为bibtex). 如果你在3D视觉上工作,你可能会发现我们最近发布的Matterport3D数据集也非常有用. 此数据集由三维创建..

核心特点

•Source code of Mask R-CNN built on FPN and ResNet101.
•Training code for MS COCO
•Pre-trained weights for MS COCO
•Jupyter notebooks to visualize the detection pipeline at every step
•ParallelModel class for multi-GPU training
•Evaluation on MS COCO metrics (AP)
•Example of training on your own dataset
•demo.ipynb Is the easiest way to start. It shows an example of using a model pre-trained on MS COCO to segment objects in your own images.
•train_shapes.ipynb shows how to train Mask R-CNN on your own dataset. This notebook introduces a toy dataset (Shapes) to demonstrate training on a new dataset.
•(model.py, utils.py, config.py): These files contain the main Mask RCNN implementation.