You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
It seems that the script is used to fuse the results of different model. How can I generate the submitted file using only one model, such as "02_ek100_avt_tsn_test_testonly.txt"? ''python launch.py -c expts/02_ek100_avt_tsn.txt -l -t'' can only evaluate the model in the validation set?
Hi, apologies for the delay. You can always pass in a single file with weights = 1 and it will generate outputs for that single file.
Also since the test set is not public, the code itself can only do evaluation on the val set. For test results you need to submit to the evaluation server.
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
We can only see the accuracy of validation set, when we run
python launch.py -c expts/02_ek100_avt_tsn.txt -l -t
.Can you tell us how to generate the submitted file for the challenge ek100?
The text was updated successfully, but these errors were encountered: