简体繁体 English

如何使用Tensorflow的实例分割预训练的MaskRCNN模型？

[英]How to use Instance segmentation pretrained MaskRCNN model by Tensorflow?

原文 2018-02-18 15:03:14 7 1 python/ tensorflow/ mask

Tensorflow recently seems to have released pretrained model for instance segmentation using MaskRCNN as per below tweet. Tensorflow最近似乎已经发布了使用MaskRCNN进行实例分割的预训练模型，如下文所述。

https://twitter.com/TensorFlow/status/963472849511092225 https://twitter.com/TensorFlow/status/963472849511092225

I downloaded mask_rcnn_resnet101_atrous_coco_2018_01_28.tar.gz from this and was trying to figure out how to use it.I found frozen model (pb) file and loaded the graph in Tensorboard. 我从这里下载了mask_rcnn_resnet101_atrous_coco_2018_01_28.tar.gz并试图弄清楚如何使用它。我找到了冻结的模型（pb）文件并将图形加载到Tensorboard中。

But I cant figure out what should be the input for the model.I couldn't find a node where simply I can input an image , though I was able to locate nodes where we get classes,masks,bounding boxes etc. 但是我不知道应该为模型输入什么。我找不到能够简单输入图像的节点，尽管我能够找到获得类，掩码，边界框等的节点。

Also there seems to be no details online on how to use it (May be because it is new) 网上似乎也没有有关如何使用它的详细信息（可能是因为它是新的）

1 个解决方案

If you follow this tensorflow tutorial it will show you how to run the frozen model on a single/group of images. 如果您遵循此tensorflow教程，它将向您展示如何在单个/一组图像上运行冻结的模型。 To apply this to the model you downloaded, the simplest way would be to first replace the line: 要将其应用于您下载的模型，最简单的方法是首先替换以下行：

PATH_TO_CKPT = MODEL_NAME + '/frozen_inference_graph.pb'

with a path to your downloaded model ie 带有下载模型的路径，即

PATH_TO_CKPT = '/absolute/path/to/frozen_inference_graph.pb'

Then there is no need to run the code under the section Download Model . 然后，无需运行“ Download Model ”部分下的代码。 The rest should work the same. 其余的应该相同。