blue-oil/blueoil

passing `num_max_boxes` might be possible to remove from train.py

Open

#459 opened on Sep 24, 2019

View on GitHub
 (0 comments) (0 reactions) (0 assignees)Python (250 stars) (85 forks)batch import
good first issue

Description

object detection network receives num_max_boxes parameter, but might be possible to remove.

num_max_boxes is used to create an instance of tf.placeholder. However, it is possible to use None for tf.placeholder if the tensor shape is not fixed. If training performance is not decreased, we can remove this parameter.

Contributor guide

Tech stack
pythontensorflow
Domain
backendmachine learning
Issue type
refactor
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
2
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
under 1 hour
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
fresh
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
mostly clear
Prerequisites
Basic knowledge of TensorFlow placeholder shapes
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
80
Research direction
Examine the file train.py in the repository to identify where num max boxes is used as an input parameter and how it defines a tf.placeholder. Replace the placeholder shape with None (i.e., set shape=[None, ...] accordingly) and ensure the model training still functions correctly. Evaluate if removing the parameter affects training performance; if not, the parameter can be safely removed from the function signature and all calls.