Workshop: Object detection with Deep Learning

Hands-on 1: Implementing Faster R-CNN (almost) from scratch

Consists of a Jupyter Notebook that will guide you to complete the implementation of a Faster R-CNN model for object detection.

Instructions

1. Clone the repository.

2. Execute the download_checkpoint.sh script from the base directory in order to download the pre-trained checkpoint:

   cd object-detection-workshop
   ./download_checkpoint.sh
   

3. Install the auxiliary library workshop:

   pip install -e .
   

4. Run Jupyter Notebook from the base directory:

   jupyter notebook
   

5. Open the notebook Implementing Faster R-CNN.ipynb.

6. Read the instructions carefully and complete everything :)

Hands on 2: using Luminoth for real world object detection

Guided demo of Luminoth toolkit, which will teach you the most important functionalities and how to train your own models.

Access the Luminoth tutorial.

Copyright © 2018, Tryolabs.