Hyperparameter Optimization for predict_tile #472
Closed
mtaniguchiking
started this conversation in
General
Replies: 1 comment
-
Closing, since was responded by email. #471 opened issue. |
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
-
Hello! I'm evaluating DeepForest's predict_tile as a CV tree detection method for OFO and would appreciate insight/feedback on my current approach:
As a starting point for the evaluation, I'm optimizing
![image](https://private-user-images.githubusercontent.com/112134530/262139016-58b73d8c-f1ff-4f81-97e5-9da810290341.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTk2MjkxNTEsIm5iZiI6MTcxOTYyODg1MSwicGF0aCI6Ii8xMTIxMzQ1MzAvMjYyMTM5MDE2LTU4YjczZDhjLWYxZmYtNGY4MS05N2U1LTlkYTgxMDI5MDM0MS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNjI5JTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDYyOVQwMjQwNTFaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT0xNzFkNWYwMWNjOTE0ZjE2Yzg1ZDUzOGRhZjc4ZmNjYzk2NDc2YTkyZTc4ZmQyNmU1NDVkMjg5YWMyOTM5MzBhJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.0NHeSLqzJ4nZ2T1xgI8jjT9yGHKYTQyOJnOZW9-Tklw)
predict_tile
's hyperparameters on a forest orthomosaic to gauge the effectiveness ofpredict_tile
and to get a sense for how the performance (i.e. f-score) of predict_tile changes depending on its hyperparameters. Before considering multiple parameters, I began by exploring the influence of individual parameters - as an example, here is a preliminary result from a range of patch_size values:My current approach for hyperparameter fine-tuning involves running
predict_tile
on an orthomosaic with different hyperparameter combinations before comparing the DeepForest tree detections against a ground-measured reference tree map.My plan involves performing the following searches for hyperparameter fine-tuning:
Random Search with NMS (
use_soft_nms = False
):I’m curious about the role of
thresh
whenuse_soft_nms = False
. Documentation indicatesthresh
only filters bboxes after soft NMS is performed (therefore, it is not relevant whenuse_soft_nms = False
), but I would like to confirm this. I’m also more generally interested in other considerations (specific to DeepForest) I should take into account as I optimize these parameters.Beta Was this translation helpful? Give feedback.
All reactions