Fernando Pérez-García

Results 82 issues of Fernando Pérez-García

This will avoid e.g. https://github.com/microsoft/InnerEye-DeepLearning/pull/769#issuecomment-1193686392.

From https://github.com/readthedocs/recommonmark: > **Warning:** recommonmark is now deprecated. We recommend using [MyST](https://github.com/executablebooks/MyST-Parser) for a docutils bridge going forward. See [this issue](https://github.com/readthedocs/recommonmark/issues/221) for background and discussion. [AB#5336](https://innereye.visualstudio.com/60ce1777-00d6-4015-82bc-488a0c00202f/_workitems/edit/5336)

documentation
good first issue
not urgent

Assuming #660 has been fixed: ```shell $ make html python preprocess.py Running Sphinx v3.1.1 making output directory... done WARNING: html_static_path entry '_static' does not exist building [mo]: targets for 0...

documentation

The run ID [`refs_pull_633_merge_1642019743_f212b068`](https://ml.azure.com/runs/refs_pull_633_merge_1642019743_f212b068?wsid=/subscriptions/a85ceddd-892e-4637-ae4b-67d15ddf5f2b/resourceGroups/innereye-deeplearning/providers/Microsoft.MachineLearningServices/workspaces/InnerEye-DeepLearning&tid=72f988bf-86f1-41af-91ab-2d7cd011db47) failed. This causes multiple tests to fail, e.g., https://github.com/microsoft/InnerEye-DeepLearning/blob/1600ef3ddfa83328ec35d179533c3a4e95f88a69/Tests/AfterTraining/test_after_training.py#L147-L150 This test is skipped in CI, therefore this is missed: https://github.com/microsoft/InnerEye-DeepLearning/blob/1600ef3ddfa83328ec35d179533c3a4e95f88a69/Tests/AfterTraining/test_after_training.py#L143-L147 If the run ID is replaced...

bug

If the patch size is larger than the image size during inference with TorchIO, an error is raised. This implies that this situation wasn't being covered by the tests. To...

bug

There are some quantitative differences in inference depending on whether RadIO or TorchIO are used: - https://github.com/microsoft/InnerEye-DeepLearning/pull/666#issuecomment-1048104234 I suspect that the little differences might happen because overlapping patches are cropped...

[pytorch-lightning < 1.5.8 is vulnerable to Deserialization of Untrusted Data](https://github.com/advisories/GHSA-2vj5-px25-gjrp). We are using 1.5.5: https://github.com/microsoft/InnerEye-DeepLearning/blob/914a89383d3275cb3304bde9c6cdd6050357f3f7/environment.yml#L57 Should we use a newer version? [AB#4978](https://innereye.visualstudio.com/60ce1777-00d6-4015-82bc-488a0c00202f/_workitems/edit/4978)

Stubs for `tqdm` are now available: https://github.com/tqdm/tqdm/issues/260#issuecomment-1176245901

**🚀 Feature** Add support to transform images in GPU devices. **Motivation** Some transforms would benefit a lot from hardware acceleration. I suspect the two main sources of improvement would be...

enhancement

As in https://github.com/NifTK/NiftyNet/commit/a91644b881192fb68e7faabc2065129f09d5bdd5#diff-5b79901b7b2f56394aca30c562e9e186

enhancement
good first issue