NASA Harvest Field Boundary Detection Challenge
'%3e%3cg id='b'%3e%3cpath id='a' fill='%23E5BE01' d='M116.1 0 35.692 4.699l76.452 25.35L33.26 13.777l67.286 44.273L28.56 21.915l53.534 60.18-60.18-53.534 36.135 71.985L13.777 33.26l16.272 78.884-25.35-76.452L0 116.1-1-1z'/%3e%3cuse xlink:href='%23a' transform='scale(1 -1)'/%3e%3c/g%3e%3cuse xlink:href='%23b' transform='scale(-1 1)'/%3e%3ccircle r='34.3' fill='%23E5BE01' stroke='%2300A1DE' stroke-width='3.4'/%3e%3c/g%3e%3c/svg%3e)
Helping Rwanda
$5 000 USD
Challenge completed over 2 years ago
Classification
Earth Observation
768 joined
185 active
Start
Nov 17, 22
Close
Feb 26, 23
Reveal
Feb 26, 23
Unable to get to the baseline
Notebooks · 17 Jan 2023, 22:49 · 5
Hello,
I have gone through the baseline that is in Tensorflow and converted it to Fast.ai/ PyTorch. I believe I have almost everything the same except I am doing dynamic augmentations. I am only getting 1/2 the result that is output by the baseline.
I was wondering if anyone could take a look at this notebook and let me know where it might be going wrong. https://www.kaggle.com/code/ltspacemonkey/2021-nasa-harvest-rwanda-field-detection-baseline (No guarantees it will run in Kaggle though.)
Thanks,
Steve
Hello Steve,
I got similar results with BCELoss (didn't work even I tried different learning rates). After that I tried DiceLoss, and my results improved.
Hello, Do you use baseline code from this link: radiantearth/Nasa_harvest_field_boundary_competition (github.com)
Thank you.
I used that code as the basis for my notebook in PyTorch, yes. It is done in TensorFlow, which I don't know.
Marcell,
When I use DiceLoss() my validation loss doesn't change at all and training loss bounces around the same number.
I trained for 200 epochs and the numbers didn't change.
Have you used a pretrained model?The model that was used in the baseline notebook is pretrained.