souravraha
souravraha
## What does this PR do? Handles the loading of `.npy` images of integer data-types better. Previously, the ndarrays would be unsafely cast into `'uint8'`. If the original dtype were,...
As things stand, https://github.com/Lightning-AI/lightning-flash/blob/796c9c87b6fcf3ed93bbb15ee15b8150f22378e2/flash/core/data/utils.py#L65 does not have support for downloading files stored on google drives. I suggest replacing this with torchvision's https://github.com/pytorch/vision/blob/5dd95944c609ac399743fa843ddb7b83780512b3/torchvision/datasets/utils.py#L433.
**Describe the bug** The pet pipeline is not intelligently skipping already processed bids entries, unlike the t1 pipeline. This results in the pet pipeline reprocessing all eligible bids entries. **To...
https://github.com/alinlab/M2m/blob/42d08a5399c1b62925044287e7ee8d134260a08a/train.py#L167 @jh-jeong In the line above `p_accept` is supposed to be "per-class" probability distribution. This is according to the definition of `torch.multinomial`. However, the implementation is treating it as a...
#### Description This builds upon #1060. While running the dataset converter for ADNI, it appears that images with unsupported suffixes such as `ADC`, `real`, and `imaginary` are being generated, only...
**What’s the issue?** When projecting (orthographically) the eight cameras into vehicle coordinates (x=forward, y=left, z=up), their optical centers form a convex hull that does *not* contain (0,0). However, the Waymo...
**Describe the bug** When converting ADNI datasets to BIDS format using Clinica (`clinica convert adni-to-bids`), the resulting TSV files fail validation with the [BIDS Validator](https://bids-standard.github.io/legacy-validator). This validation failure occurs because...