Assignment 5 Single-Stage Detector

Assignment 5
In this assignment you will implement two different object detection systems.
The goals of this assignment are:
Learn about the object detection pipeline
Understand how to build an anchor-based single-stage object detectors
Understand how to build a two-stage object detector that combines a region proposal network with a
recognition network
This assignment is due on Monday, November 16th Wednesday, November 18th at 11:59pm EDT.
Q1: Single-Stage Detector (54 points)
The notebook single_stage_detector_yolo.ipynb will walk you through the implementation of a fullyconvolutional single-stage object detector similar to YOLO (Redmon et al, CVPR 2016). You will train and
evaluate your detector on the PASCAL VOC 2007 object detection dataset.
Q2: Two-Stage Detector (46 points)
The notebook two_stage_detector_faster_rcnn.ipynb will walk you through the implementation of a twostage object detector similar to Faster R-CNN (Ren et al, NeurIPS 2015). This will combine a fullyconvolutional Region Proposal Network (RPN) and a second-stage recognition network.
Steps
1. Download the zipped assignment file
Click here to download the starter code
2. Unzip all and open the Colab file from the Drive
Once you unzip the downloaded content, please upload the folder to your Google Drive. Then, open each
*.ipynb notebook file with Google Colab by right-clicking the *.ipynb file. We recommend editing your
*.py file on Google Colab, set the ipython notebook and the code side by side. For more information on
using Colab, please see our Colab tutorial.
3. Work on the assignment
Work through the notebook, executing cells and writing code in *.py, as indicated. You can save your
work, both *.ipynb and *.py, in Google Drive (click “File” -> “Save”) and resume later if you don’t want
to complete it all at once.
While working on the assignment, keep the following in mind:
The notebook and the python file have clearly marked blocks where you are expected to write code.
Do not write or modify any code outside of these blocks.
Do not add or delete cells from the notebook. You may add new cells to perform scratch
computations, but you should delete them before submitting your work.
Run all cells, and do not clear out the outputs, before submitting. You will only get credit for code that
has been run.
4 Evaluate your implementation on Autograder
EECS 498-007 / 598-005
Deep Learning for Computer Vision
Fall 2020
4. Evaluate your implementation on Autograder
Once you want to evaluate your implementation, please submit the *.py , *.ipynb and other required
files to Autograder for grading your implementations in the middle or after implementing everything. You
can partially grade some of the files in the middle, but please make sure that this also reduces the daily
submission quota. Please check our Autograder tutorial for details.
5. Download .zip file
Once you have completed a notebook, download the completed uniqueid_umid_A5.zip file, which is
generated from your last cell of the two_stage_detector_faster_rcnn.ipynb file. Before executing the
last cell in two_stage_detector_faster_rcnn.ipynb , please manually run all the cells of notebook and
save your results so that the zip file includes all updates.
Make sure your downloaded zip file includes your most up-to-date edits; the zip file should include:
single_stage_detector.py
two_stage_detector.py
single_stage_detector_yolo.ipynb
two_stage_detector_faster_rcnn.ipynb
frcnn_detector.pt
yolo_detector.pt
6. Submit your python and ipython notebook files to Autograder
When you are done, please upload your work to Autograder (UMich enrolled students only). Your
*.ipynb files SHOULD include all the outputs. Please check your outputs up to date before submitting
yours to Autograder.
Note: Autograder for A5 will start working on November 5th.
Justin Johnson
justincj@umich.edu
Website for UMich EECS course
EECS 498-007 / 598-005: Deep Learning for Computer Vision