MLRadfys

Arrays type float64 after running subfunctions

2

Hi Dominik, I just noticed that both images and segmentations are of type float64 after running any subfunction. That might lead to memory issues during training and the batches take...

2D slicer interface datasplit

1

Hi Dominik, hope you're well! Just one thing I've noticed with the 2D slicer interface. When you take the sample list and feed it to split_validation or cross_validation, the 2D...

img_shape not updateded in sample object

2

Hi Dominik, I just noticed that the img_shape attribute is not updated in a sample object when for example using the resample subfunction. Is that on purposes in order to...

batches.pop(0) pop from empty list

4

Hi, when training a model on multiple GPUs with patch-wise cropping, I get the following error: batches.pop(0) from empty list I train with a patch size of (64,64,64), 4 Gpus...

steps per epoch update when self.prepare_batches

1

Hi again, one more thing I noticed (sorryyyy): When you use patchwise_grid and set the prepare batches flag, I think that the number of steps per epoch is not updated...

Training with patch-wise crop

4

Hi, I just noticed that if you set the 'prepare-batches' flag while training with patch-wise cropping, the network uses the same patches for each epoch instead of creating a new...

Plot Dose distribution on CT scan

4

Hi, Iam wondering if there is an option to plot dose distributions on CT scans? Thanks in advance, cheers, Michael

General question on per sampel augmentation

1

Hi and thanks for sharing this great project! Iam just wondering how batchgenerators applies the augmentation on a sample level? Are multiple augmentations applied at once to a sample (i.ex....

Uwe variables in RedisJson query

1

Hi and thanks for this great Plugin! Iam wondering if it is possible to use Grafana variables inside a Json get query ? Thanks in advance, MikeSv

Finetuning CLIP VIT32 on COCO captions

2

Hi and thank you so much for this awesome repository! Iam trying to finetune the openAI CLIP V32 model on the COCO dataset and observe some major overfitting, though Iam...