Lilly Thomas

Hi @ardiya thank you for responding. I believe that I have made the changes you suggested, but I am a bit confused as to what this line (https://github.com/ardiya/siamesenetwork-tensorflow/blob/f81f2bee37a150391e2f895391390f59c4f4f5f2/dataset.py#L37) refers to....

Some current examples of similarity search results generated with 3600~ embeddings from NAIP sized at 256x256 and the `v0.5.3/mae_v0.5.3_epoch-08_val-loss-0.3150.ckpt` checkpoint. These are all from the Bay area of California in...

@yellowcap sounds good! I'll work on swapping the method for getting NAIP chips to use stacchip and request your review on it.

Hi @lauracchen sure thing!

Actually @lauracchen it appears the Worldcover composite we are using is just RGB-Nir (https://esa-worldcover.org/en/data-access). There is a SWIR composite provided as well, which we can stack on the RGB-Nir, but...

Patch-level sim search with the currently-in-place RGB-Nir worldcover model is working, albeit the results are still a bit random: Example 1: Example 2: Working on the adjustments per https://github.com/Clay-foundation/model/pull/231#issuecomment-2079780410

@antymoro I've implemented the concatenation of the RGB-Nir composite with the SWIR and SAR composites (see the new script `run_msi_sar.py`). Feel free to try it on your end.

I've done a few more experiments to rigor-test things. The main changes involved shuffling the samples before partitioning using a seed for consistency across model variants and reproducibility. The prior...

### Controlling the number of epochs (part ii) An experiment where the number of epochs were standardized instead of determined by an early stopping callback. For a set number of...

Same part ii epoch-controlled experiment with two more seeds | Experiment | Variant | Number of epochs | Mean IoU | Seed | | ---------| ---------| ---------| ---------| ---------| |...