Wenqi Li comments

Results 315 comments of


                                            Wenqi Li

[CICD] TEST ONLY: decrease cpu cores for py tests

![Screenshot 2022-08-15 at 23 07 56](https://user-images.githubusercontent.com/831580/184726652-d5262144-2e85-409a-b602-d2edcc41bddc.png) thanks, the recent runs are pretty fast and stable now, closing this.

Extend/correct behaviour of RandAffined to allow for different input shapes

thanks for the feature request, the root cause is that the current `rotate_range` `translate_range` are defined in terms of the image coordinates, but in this use case, the assumption is...

Adding transforms for signal (ECG, EEG for instance)

/build

Adding transforms for signal (ECG, EEG for instance)

that's from torch 1.12 update, i'm working on a fix https://github.com/Project-MONAI/MONAI/issues/4606

Adding transforms for signal (ECG, EEG for instance)

/black

Adding transforms for signal (ECG, EEG for instance)

/build

add support for UNET++

Hi @baibizhe, thanks for your interest here. There's a basic UNet implementation in MONAI, the goal was to create an easy-to-understand baseline but with some price in flexibility https://github.com/Project-MONAI/MONAI/blob/78509ae55ef98660907544e92713e44897bb7e48/monai/networks/nets/basic_unet.py#L189 as...

add support for UNET++

Hi @yashika-git, I'd recommend avoiding duplicated efforts. There's a UNet with better flexibility and used in many of our examples/tutorials https://github.com/Project-MONAI/MONAI/blob/78509ae55ef98660907544e92713e44897bb7e48/monai/networks/nets/unet.py#L28 It would be great to follow that style, and...

RandAffined does not work for differently sized images

Hi @Spenhouet, Without proper handling of the metadata, it doesn't make sense to compare the different shapes of the raw data arrays because they can be in different coordinate systems....

Rename `Transpose` to `Permute` to Reflect Behaviour

perhaps we make `Permute` an alias of `Transpose`? as for the numpy api: ```py >>> import numpy as np >>> x = np.ones((1, 2)) >>> np.transpose(x, (0, 1)).shape (1, 2)...