Published March 29, 2023
| Version v1
Dataset
Open
Model weights and predictions for reproducible benchmarking experiments in MedMNIST v2
Description
This data repository is associated with our GitHub code
weights_*.zip
:- PyTorch, AutoKeras and Google AutoML Vision are provided for MedMNIST2D.
- PyTorch and AutoKeras are provided for MedMNIST3D.
- If you are using PyTorch model weights, please note that the ResNet18_224 / ResNet50_224 models are trained with images resized to 224 x 224 by
PIL.Image.NEAREST
. - Snapshots for
auto-sklearn
are not uploaded due to the embarrassingly large model sizes (lots of model ensemble).
predictions.zip
: We also provide all standard prediction files by PyTorch, auto-sklearn, AutoKeras and Google AutoML Vision, which works withmedmnist.Evaluator
. Each file is named as{flag}_{split}_[AUC]{auc:.3f}_[ACC]{acc:.3f}@{run}.csv
, e.g.,bloodmnist_test_[AUC]0.997_[ACC]0.957@autokeras_3.csv
.
Files
predictions.zip
Files
(28.4 GB)
Name | Size | Download all |
---|---|---|
md5:1a2563e89d3d36d0f29d7ca31e8a41c2
|
2.0 GB | Preview Download |
md5:c5dabcf205815bf65d665dae0857c201
|
2.1 GB | Preview Download |
md5:e49ce8a3502481309eb21f193d8c2f77
|
1.5 GB | Preview Download |
md5:f3e91872a00cf0ce94186e17ee805156
|
1.1 GB | Preview Download |
md5:b1a3f28cc7d83c8750bbab2acb20734e
|
1.3 GB | Preview Download |
md5:2f9a3f0ef3f52a6dfe169b9baaf048e2
|
1.0 GB | Preview Download |
md5:e5ad198c4e8fe7117c877fe03a1a4f9f
|
1.8 GB | Preview Download |
md5:3b7af4b86f695967f7e22e6476d470f2
|
1.9 GB | Preview Download |
md5:7dbd82265c224ce112ab4f973ac86f32
|
1.6 GB | Preview Download |
md5:10360f6f3803fc8409bf9a331227bc79
|
920.9 MB | Preview Download |
md5:4f8027d14e60093f66f572aa21b6dfed
|
1.5 GB | Preview Download |
md5:1fffc36ee4c3ff768a0bdb70dd5d1fa9
|
1.8 GB | Preview Download |
md5:f5a9550814b494ccf8a43bb626ebdc68
|
1.5 GB | Preview Download |
md5:90b4fb5cc399a4caaba8401c438d43c5
|
1.5 GB | Preview Download |
md5:01ee733fc0e3263e0b809e2b0182594d
|
853.4 MB | Preview Download |
md5:a6aa2d4985ba8e032381017ec848971d
|
953.8 MB | Preview Download |
md5:af65b8273773701c0a347c0197cbf8a5
|
2.1 GB | Preview Download |
md5:777a28b064659bcb64971ab340caa16f
|
1.2 GB | Preview Download |
md5:7574e43f7ea77fd906744f46ad933588
|
1.8 GB | Preview Download |