This repository has been archived by the owner on Nov 21, 2023. It is now read-only.
-
Notifications
You must be signed in to change notification settings - Fork 5.5k
No results on test dataset #620
Comments
Looks like a duplicate of #293. (#588 could be relevant too) |
Yes, I changed name of test dataset and everything is ok! thanks! |
your AP is very high ,my AP is low, how to improve it? |
This AP is evaluating with the train dataset |
xzhewei
pushed a commit
to xzhewei/Detectron
that referenced
this issue
Jan 10, 2019
Summary: Fix for facebookresearch#620 & facebookresearch#293. Pull Request resolved: facebookresearch#624 Reviewed By: ir413 Differential Revision: D9574052 Pulled By: rbgirshick fbshipit-source-id: f44cea71e5cf6e613d319322db62a60ecb814a75
I change voc_2007_val to voc_2007_test but it didn't work as well |
The folder can't contain "test" |
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
python --version
output: 2.7.12I trained a Faster R-CNN with ResNet50 model on my custom train dataset, and everything seems ok. But when I test it on my custom test dataset (test of train_net.py), I get this results:
But If I run infer_simple.py with the test images, I can see that model is relatively good:
If I test it on my train dataset (I know that this isn't correct), I get this:
I don't know why if model can detect object on test dataset, I don't get summary metrics... and only I get -1.0000 in all metrics.
My original dataset's labels was in xml, and I convert it to json with this file, but the generated json to test and train are slightly differents, because this script assign a id number to a name in order in which script find it in dataset. I testes withouth changes, change the json with find+replace to leave category_id same in both json and finally, I changed script, I replaced line 22, and I assign category_item_id to harcoded name:
But in all cases, I always get same results if I test on my test dataset.
The text was updated successfully, but these errors were encountered: