search

microsoft / aerial_wildlife_detection

Tools for detecting wildlife in aerial images using active learning
MIT License
230 stars 58 forks source link

argument error of gunicorn #28

Open YangZhangMizzou opened 3 years ago

YangZhangMizzou commented 3 years ago

A very interesting work! However, When I try to launch AIDE with the command './AIDE.sh start ', an error occur as the picture shows. Here is the screenshot: Screenshot from 2021-01-25 19-02-45 I also attach my setting file settings.txt Anyone who has some suggestions on it?

bkellenb commented 3 years ago

Hi!

Thanks for opening the issue. The only explanation I could have is that your environment variable AIDE_CONFIG_PATH points to a different settings file. Are you using Docker? Then you have to modify the docker/settings.ini file, not the config/settings.ini file.

--

To make the system a bit more hiccup-proof, the latest commit now contains a fallback solution to the numWorkers argument if it cannot be found (defaults to 6).

YangZhangMizzou commented 3 years ago

Hi!

Thanks for opening the issue. The only explanation I could have is that your environment variable AIDE_CONFIG_PATH points to a different settings file. Are you using Docker? Then you have to modify the docker/settings.ini file, not the config/settings.ini file.

--

To make the system a bit more hiccup-proof, the latest commit now contains a fallback solution to the numWorkers argument if it cannot be found (defaults to 6). settings.txt terminal_logs.txt my GUI Model settings

Thank you for your reply. The problem is solved! Yes when I use docker I can start the server and log in. I tried to run AIDE on one machine however, when I tried to label the images I uploaded and use built-in model to learn them, I have some questions:

  1. All of my labels cannot be saved. After I finished labeling some images and quit, I cannot find the labels I did anymore. Is it because of some configuration problems in setting.ini file?
  2. How can I apply built-in models automatically? I make some configurations under AI model->setting in GUI but nothing happened. The model does not run when I do the labeling. I tried to find answers in build-in model.md but I am sorry I still feel confused what I should do to make it run. What is the configuration JSON file for and how can I use it? Here are some files I think might help you to understand my questions. Thank you again!
bkellenb commented 3 years ago

Hi!

  1. Your annotations should be saved automatically whenever you click "Next" (or "Previous") or leave the browser page. AIDE tries to maximize the diversity of images annotators get to see; you therefore won't see already checked images again as long as there are unlabeled ones. However, if you are a project administrator you can still take a look at your labels, either by clicking "review annotations" in the bottom right of the main labeling interface screen (below the label class list), or by clicking the tab "Data management" in the configuration page (in your screenshot above)—in there, you can list images and sort them by number of annotations, for example.
  2. A little while ago I started to re-write the automated training procedure, as it was a bit unstable. For the time being, automated model training is disabled for this reason; models can currently only be used (training, prediction, etc.) manually by launching tasks through the Workflow designer. Sorry about that. However, the next major release is coming soon, and in there automated model training will be enabled and configurable again through the "AI model" > "Settings" tab. You can take a sneak peek at this on the respective branch.