BiaPy

BiaPy copied to clipboard

Speed up prediction by chunks

18

We need to rethink how the final prediction is reconstructed using inference by chunks, as right now we are using so much disk (and time) with the mask that needs...

danifranco

Feature request: Qualily control results of test dataset after training a instance segmentation model

4

I'm having hard time locating the quality control results of the test dataset after training an instance segmentation model. The results are nicely visualized, but the quality control metrics, such...

jpylvanainen

It could be nice to create a CSV file with the calculated metrics for each test sample. Also, at this point I think we need to unify the names of...

danifranco

Now the detection masks are not created by chunks as it is done in the instance segmentation workflow. The whole image is loaded in memory and then dumped into the...

danifranco

Now the dataset is replicated for each worker that is spawned. We should split the dataset as it is done in "by chunks" inference in order to save memory when...

danifranco

On-the-fly conversion of instances to semantic masks/affinities

1

Hi Dani, For an extremely large dataset, the converting all instance labels to masks can be tedious and lead to data redundancy. It would be easier with a method (as...

Mohinta2892

I'm trying to load some images from a directory using this code: ```python # load data X_test, *_ = load_data_from_dir(cfg.DATA.TEST.PATH, is_3d=True) Y_test, *_ = load_data_from_dir(cfg.DATA.TEST.GT_PATH, is_3d=True) ``` And I get...

iarganda

Useful for finetunning just a part of the model.

danifranco