-
Notifications
You must be signed in to change notification settings - Fork 42
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
About the test results #26
Comments
@Bigtuo. The first 6 numbers are ADE (not exactly implemented the metric as the website/paper description, considering the numerical stability problem), and the last number is the sum of the first 6 numbers. During training, one can use these numbers to roughly get some sense about the performance of the model, they are not the correct errors. Please submit your results to the website to get the final error. Thanks. |
ok,thankyou
…---Original---
From: ***@***.***>
Date: Mon, Jul 12, 2021 18:07 PM
To: ***@***.***>;
Cc: ***@***.******@***.***>;
Subject: Re: [xincoder/GRIP] About the test results (#26)
@Bigtuo. The first 6 numbers are ADE (not exactly implemented the metric as the website/paper description, considering the numerical stability problem), and the last number is the sum of the first 6 numbers. During training, one can use these numbers to roughly get some sense about the performance of the model, they are not the correct errors. Please submit your results to the website to get the final error. Thanks.
—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub, or unsubscribe.
|
Is this 6 number means predicted horizon? for example 1 second , 2 second .... 6 second ? Thank you. |
The first 6 are what you said, WS is the sum of the weighted values of car, bike, and person (WSADE = Dv · ADEv + Dp · ADEp + Db · ADEb). This value is mentioned in the paper |
Thank you. [Test_Epoch20] All_All: 0.275 0.498 0.739 1.011 1.289 1.584 5.397 |
Hi @han1222, thank you for your interest in our work. Those values mean nothing but the performance of the model tested on my own split validation set (80% for training, and 20% for testing, split in xin_feeder_baidu.py [line33-34]). Next, you may want to generate predicted results on the testing set (main.py [line358-360]), and then submit the results to the Apolloscape website to get the final testing results (these numbers are results reported in papers). |
I really appreciate your kind answer. Thank you. |
Hello, I would like to inquire about the specific meaning of the 7 numbers in the testing results. Do the first six numbers represent the ADE values for the next three seconds, with two frames per second? |
I'm sorry to bother you again.
As follows,
What do the seven columns represent in these result data?
Is ADE and FDE displayed?
The evaluation results of an Epoch are as follows,
#######################################Test
|2021-07-09 17:58:51.802929|[car] All_All: 0.449 0.773 1.140 1.520 1.927 2.356 8.165
|2021-07-09 17:58:51.802929|[human] All_All: 0.145 0.267 0.403 0.554 0.715 0.891 2.977
|2021-07-09 17:58:51.802929|[bike] All_All: 0.432 0.826 1.207 1.615 2.009 2.440 8.528
|2021-07-09 17:58:51.802929|[WS] All_All: 0.269 0.491 0.727 0.981 1.242 1.525 5.236
|2021-07-09 17:58:51.818551|[Test_Epoch20] All_All: 0.275 0.498 0.739 1.011 1.289 1.584 5.397
The text was updated successfully, but these errors were encountered: