Mask_RCNN:基於Keras and TensorFlow 的 Mask R-CNN 為 目標檢測和情景分割

Mask R-CNN for Object Detection and Segmentation

這是一個基於 Python 3, Keras, TensorFlow 實現的 Mask R-CNN。這個模型為圖像中的每個對象實例生成邊界框和分割掩碼。它基於 Feature Pyramid Network (FPN) and a ResNet101 backbone.

這個項目包括包括:

在FPN和ResNet101上構建的Mask R-CNN的源代碼。

MS COCO的訓練代碼

MS COCO 預先訓練的權重

Jupyter notebooks 來可視化在每一個步驟的檢測管道

用於多GPU訓練的ParallelModel類

MS COCO指標評估(AP)

訓練您自己的數據集的例子

代碼被記錄和設計為易於擴展。 如果您在研究中使用它,請考慮引用此項目。 如果您從事3D視覺工作,您可能會發現我們最近發布的Matterport3D數據集也很有用。 這個數據集是由我們的客戶拍攝的三維重建空間創建的,這些客戶同意將這些數據公開供學術使用。 你可以在這裡看到更多的例子。

This is an implementation of Mask R-CNN on Python 3, Keras, and TensorFlow. The model generates bounding boxes and segmentation masks for each instance of an object in the image. Its based on Feature Pyramid Network (FPN) and a ResNet101 backbone.

The repository includes:

  • 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

The code is documented and designed to be easy to extend. If you use it in your research, please consider referencing this repository. If you work on 3D vision, you might find our recently released Matterport3D dataset useful as well. This dataset was created from 3D-reconstructed spaces captured by our customers who agreed to make them publicly available for academic use. You can see more examples here.

項目地址:matterport/Mask_RCNN

更多機器學習資源:TensorFlow 安裝,TensorFlow 教程,TensorFlowNews 原創人工智慧,機器學習,深度學習,神經網路,計算機視覺,自然語言處理項目分享。

推薦閱讀:

目標檢測筆記二:Object Detection API 小白實踐指南
【簡評】FaceBoxes
感覺靈感被掏空?你需要這 9 篇論文來補一補 | PaperDaily #05
YOLO2

TAG:TensorFlow | Keras | 目标检测 |