blue-oil/blueoil

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

Open

#459 创建于 2019年9月24日

在 GitHub 查看
 (0 评论) (0 反应) (0 负责人)Python (250 star) (85 fork)batch import
good first issue

描述

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.

贡献者指南

技术栈
pythontensorflow
领域
backendmachine learning
议题类型
refactor
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
2
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
under 1 hour
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
fresh
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
Basic knowledge of TensorFlow placeholder shapes
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
80
研究方向
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.