Open daniel-j-h opened 5 years ago
Took a couple more evenings than I hoped it would but now there is
https://github.com/daniel-j-h/efficientnet
Next actions:
The EfficientNets generally use an order of magnitude fewer parameters and floating point operations per second compared to existing models with similar accuracy. If we can make this work for robosat we can expect either much better segmentation results or much smaller models (or both if we e.g. provide a B0 and a B4 backbone for our users).
cc @ocourtin might be interesting to you :)
Updating here. Making progress in https://github.com/daniel-j-h/efficientnet There are some open questions re. the implementation and tricks we can use on top of the paper, you can follow e.g.
This recently came out
https://arxiv.org/abs/1905.11946
with incredible practical implications: we can either get a much better backbone than our current resnet50 for the same computational budget or get a highly computationally efficient backbone and roughly keep the resnet50's prediction performance.
Here's why we should look into this
Check out the paper's table 2 (below) for comparisons; we are currently using a resnet50.
I highlighted