Giters

layumi / Person_reID_baseline_pytorch

:bouncing_ball_person: Pytorch ReID: A tiny, friendly, strong pytorch implement of person re-id / vehicle re-id baseline. Tutorial 👉https://github.com/layumi/Person_reID_baseline_pytorch/tree/master/tutorial

Home Page:https://www.zdzheng.xyz

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Intuitive Visualization and Prediction of The Remaining Time

eddiehe99 opened this issue · comments

commented

Is your feature request related to a problem? Please describe.
I learned this tutorial and ran the code on my laptop (i5-7200U + MX150). It took around 30 min for only one epoch during the training processing using ResNet-50. And It took about six hours to finish all processes using ResNet-18 with the basic reference.

Describe the solution you'd like
Maybe it would be better to employ a progress bar like tqdm for intuitive visualization and prediction of the remaining time.

Describe alternatives you've considered
I am quite familiar with tqdm. If possible, I could try to open a pull request for this.

Additional context
I wonder whether it would be a good idea to employ tqdm as I suppose it may be the contributors' pursuit to keep the requirements as limited as possible.

commented

Hi @eddiehe99

  1. MX150 is relatively weak. Yes. It may take about 6 hours.

  2. Thank you. tqdm is good. Please add one.

commented

Hi Dr. Zheng

  1. Thank you for your prompt reply. I have opened a pull request.
  2. Based on your recruitment information, I sent a cover letter and follow-up email to you using my academic email (2021022249@m.scnu.edu.cn). I would highly appreciate your feedback even if my application is not shortlisted.