CODEWITHSUNDEEP
tensorflowobject-detectionobject-detection-api
g.smoother
g.smoother

Reputation: 135

Different use of feature extractor with ssd meta-architecture in Tensorflows's Object Detection API

Is it possible to use different feature extractor with SSD meta-architecture in Tensorflow's Object Detection API? I know that .config files for mobilenets and inception are provided but is it possible to use a different architecture like AlexNet or VGG?

Upvotes: 2

Views: 1353

Answers (1)

gdelab
gdelab

Reputation: 6220

It's possible but with a little bit of work, as explained here, you should read this page for detailed explanation and links to examples.

In short, you'll need to create a custom FasterRCNNFeatureExtractor class, corresponding to VGG or AlexNet (it may require a bit of knowledge about these, for instance the amount of subsampling invovled). In this class, you'll code how your data should be preprocessed, how to retrieve the 1st and 2nd stage features in it (typically how is the last convolutional layer called), and how to load it.

Then you'll need to register your feaure extractor (tell the object detection API that it exists) by modifying the file object_detection/builders/model_builder.py.

Finally you should be able to make a config file with your custom feature extractor, et voilà !

Upvotes: 3

Related Questions