Object Detection by Tensorflow 1.x

The computer vision is one of the top fast growing domain and the deep learning based approach is now widely applied to solve real-world problems such as face recognition, cancer detection, etc.

One of the most effective tool is Tensorflow Object Detection API and use their pre-trained model, replacing the last layer for the particular problem trying to solve and fine tune the model.

Now the API supports Tensorflow 2.x. There are good reasons to use TF2 instead of TF1 — e.g.  eager execution, which was introduced in TF1.5 to make the coding simpler and debugging easier, and new state of the art (SOTA) models such as  CenterNet,  ExtremeNet, and  EfficientDet are available. The latest version as of writing this is Tensorflow 2.3.

The API is backward compatible but still it would make your life easier to use TF1 if your runtime cannot be upgraded.  Here is TF1 version of step-by-step guide.

#ai #machine-learning #object-detection #self-driving-cars #tensorflow