Bruno Sánchez-Andrade Nuño
Bruno Sánchez-Andrade Nuño
Cold install errors with: `The POM for com.conveyal:traffic-engine:jar:0.3 is missing, no dependency information available`
[The documentation](https://stackstac.readthedocs.io/en/stable/examples/cluster.html#Set-a-coarser-resolution-to-speed-up-the-computation) implies that setting `resolution` uses overview, but as far as I can see, that it doesn't. It seems that `stackstac.stack` doesn't use or can read COG overviews. This...
This PR expands the instructions, and integrates the example creating a fresh stack with AWS CloudFormation. cc @zugaldia.
It doesn't load the satellite layer.
nbdev
Hi @tgherzog 👋 Love this. Just wanted to encourage you to check [nbdev](https://nbdev.fast.ai/) to package the code. It's insanely practical. You basically play around on a jupyter notebook, and it...
174 Sentinel-2 scenes captured between 2015-2022, with approximately 1.5M pixel-level annotations (_cl), confidence levels (_conf) and reports (_rep). These derive from 3 field-expert annotators. https://marine-pollution.github.io/ License is open: Creative Commons...
- [ ] Basic documentation to train/inference - [ ] Model card - [ ] Data card. - [ ] GH release commit. - [ ] Deploy buttons working (the...
We need to generate embeddings, like on v0.1, on all the training set. Since we are currently doing random cropping on the training set on loading, we also need to...
From @yellowcap, we will be able to input image sizes smaller than the chips we have (i.e. we crop the chip before feeding it into the model). This also means...
A MAE with a Unet like ours is actually a dual learning strategy. 1) creating accurate embeddings at patch level to reconstruct the input image, and 2) masking out to...