Computing Metrics #196
ojasvijain
started this conversation in
General
Replies: 1 comment
-
The code you're referring to expects target labels (1 for positive, 0 for negative) as the target and a corresponding array of prediction scores from the model as the pred array. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Hi!
I wanted to compute metrics such as precision, recall, ap etc. based on the code provided on https://github.com/tbepler/topaz/blob/master/topaz/metrics.py.
I just wanted to understand what the "target" and "pred" looks like in the average_prediction function. I have 2 files (for each image) which consist of the particle and the corresponding bounding box coordinates (4 points). Is it that what is expected?
Thanks!
Beta Was this translation helpful? Give feedback.
All reactions