Training a model to detect text from the ground up could be a very hard and frustrating task. Conventional way is to use R-CNN with Feature Pyramid Network or using algorithms like YOLO.

训练模型以从头开始检测文本可能是一项非常艰巨而令人沮丧的任务。 常规方法是将R-CNN与功能金字塔网络配合使用，或使用类似YOLO的算法。

Either of them is very hard to implement if you are not aware of the mathematics and logic behind these.

如果您不了解它们背​​后的数学和逻辑，则很难实现它们中的任何一个。

Detectron 2 which is developed by Facebook AI research team is a state-of-the-art object detection model which is based on mask-r-CNN benchmark. It is powered by non-other than Pytorch deep learning framework. Key feature includes

Facebook AI研究团队开发的Detectron 2是基于mask-r-CNN基准的最新对象检测模型。 它由Pytorch深度学习框架以外的其他组织提供支持。 主要功能包括

1. Panoptic Segmentation: Another product of FAIR, is a type of segmentation That unifies the typically distinct tasks of semantic segmentation (assign a class label to each pixel) and instance segmentation (detect and segment each object instance).

   全景分割 ：FAIR的另一种产品是一种分割类型，它将语义分割(将类标签分配给每个像素)和实例分割(检测并分割每个对象实例)的典型任务统一起来。

2. Dense pose: Used to map all human pixels of an RGB image to the 3D surface of the human body. This is powered by caffe2.

2. 密集姿势 ：用于将RGB图像的所有人类像素映射到人体的3D表面。 这是由caffe2驱动的。

“This model is meant to advance object detection by offering speedy training and addressing the issues companies face when making the step from research to production”

“此模型旨在通过提供快速培训并解决公司从研究到生产的过程中面临的问题来提高对象检测的效率”

让我们开始吧！ (Let’s get started!)

Detectron 2 can be implemented for object detection using Google Colab Notebook. We are choosing Google Colab over local system to take advantage of GPU for faster training.

可以使用Google Colab Notebook将Detectron 2实施为对象检测。 我们选择Google Colab而非本地系统，以利用GPU进行更快的培训。

步骤1：安装和导入Detectron 2 (Step 1: Installing and Importing Detectron 2)

We will be writing this code on google colab or you get the entire notebook here.

我们将在google colab上编写此代码，或者您可以在此处获取整个笔记本。

To get started we will be installing some dependencies such as COCO API,CUDA (To get info on GPU),Tourch Visison

首先，我们将安装一些依赖项，例如COCO API，CUDA(有关GPU的信息)，Tourch Visison

Importing utilities and common libraries

导入实用程序和通用库

步骤2：运行预训练的detectron2模型 (Step 2 : Run a pre-trained detectron2 model)

We will be using images from COCO dataset asnd will be running a pre trained model, If you want to run this model on a custome dataset see here.

我们将使用来自COCO数据集的图像，然后将运行预先训练的模型。如果要在自定义数据集上运行此模型，请参见此处 。

Code for running model on image from COCO :

在COCO的图像上运行模型的代码：

…and you have successfuuly implemented your first project using detectron.

…您已经成功地使用Detectron实施了您的第一个项目。

结果：可视化前后 (Results : Before and after visualization)

资源： (Resources :)

1. Facebook AI research page for detectron

   Facebook针对AI的研究页面

2. Paper explaining panoptic segmentation

   解释全景分割的论文