Rapid object detection suitable for implementation in autonomous vehicles from the Udacity Self-driving Car Engineer Nanodegree.

Unzip frozen_inference_graph.zip within folder <ssd_mobilenet_v1_coco_11_06_2017> to use for inference

In lab this you will:

• Learn about MobileNets and separable depthwise convolutions.

• The SSD (Single Shot Detection) architecture used for object detection

• Use pretrained TensorFlow object detection inference models to detect objects

• Use different architectures and weigh the tradeoffs.

• Apply an object detection pipeline to a video.

Open the notebook and work through it!

Requirements

Install environment with Anaconda:

conda env create -f environment.yml

Change TensorFlow pip installation from tensorflow-gpu to tensorflow if you don't have a GPU available.

The environment should be listed via conda info --envs:

# conda environments:#carnd-advdl-odlab        /usr/local/anaconda3/envs/carnd-advdl-odlab
root                  *  /usr/local/anaconda3

Further documentation on working with Anaconda environments.

Particularly useful sections:

https://conda.io/docs/using/envs.html#change-environments-activate-deactivate https://conda.io/docs/using/envs.html#remove-an-environment

Resources

• TensorFlow object detection model zoo

• Driving video