ArneD

Hi, Thanks for the fast response. I cloned the master branch of this repository. And made two changes: **1)** I changed lines 34-35 in bert_document_classification/examples/ml4health_2019_replication/data.py to `if partition == 'train':...

I pushed my code to https://github.com/ArneDefauw/BERT_doc_classification. The only meaningful changes to the master branch of this repository are the ones described above. I also add results (log files) of two...

After some analysis of the code, I may have found the reason for the discrepancy between the results reported in the paper, and the results I found: It seems necessary...

> @ArneDefauw @aeisenbarth tagging you because you opened at some point a issue regarding incremental IO. In this PR incremental IO is implemented, happy to receive feedback in case you...

> Thank you @ArneDefauw for trying the code and for the explanation, I will now look into your PR. > > > In version 0.0.15 of SpatialData, when sdata.add_image(...) was...

Following our discussion, I created a new draft PR that removes much of the complexity introduced in this PR, see https://github.com/scverse/spatialdata/pull/588

> for aggregate points on labels. I've got this walk-around: https://github.com/BioinfoTongLI/Image-ST/blob/main/bin/to_spatialdata.py#L111-L118 it is however not very memory efficient. Hi @BioinfoTongLI , for aggregation of points on labels, I have this...

> Hi, great PR, it looks very interesting! I´m trying to use it for my project, but ran into an error. I´m relatively new to using PRs on github, so...

Hi @LucaMarconato , thanks for having a look! It makes sense to move the code for this PR to spatialdata, and I probably have some time next week to do...

I think this PR is ready for review again, together with related PR https://github.com/scverse/spatialdata/pull/811 Note, we probably need to update this notebook https://spatialdata.scverse.org/en/stable/tutorials/notebooks/notebooks/examples/technology_visium_hd.html after the PR's are merged. I would...