-
Data augmentation is a technique to increase the amount and diversity of data without actually collecting new data. This comes in handy when labelled data are not easy to come by, and can help increas…
-
Hi, thanks for the interesting research / technique. I was trying to reproduce it and ran into a potential issue and was wondering if you could help shed some light on whether this is expected behavio…
-
Here I want to report for the incorrect documentation for tutorial in Random mosaic
The official documentation for Random mosaic is at here https://mmsegmentation.readthedocs.io/en/latest/tutorials…
-
# Describe the feature
Sometimes, you do not want all data augment applied sequentially, because it would totally destroy the image.
Therefore I would like a meta data augmentation that can pick 1 d…
-
### Describe the question.
Hello,
I'm trying to speed up the image augmentations in DINO with DALI. I'm trying to start with a naive solution which is just calling the augmentations from DALI. I…
-
Thanks for your error report and we appreciate it a lot.
**Checklist**
1. I have searched related issues but cannot get the expected help.
2. I have read the [FAQ documentation](https://mmdetec…
-
In pipeline.py / def _augmentation_fn(self, image, boxes):
The function random_image_crop() outputs the cropped image and boxes, then you resize the image without adjust the boxes. I think the r…
-
**Proposed Algorithm:**
Get duration of the background file (bg_file) in seconds.
Sample a random value from the range [0, bg_file_seconds - event_file_seconds).
Read the background f…
-
In the example (text segmentation), operators are used to creating the resizers and further within the augmentation factory.
Do you use the training and validation resizer operators to build a pip…
-
Hi, great work the results look really good. I had few questions regarding training
1. How long did you train the BSRNet?
2. Did you apply the proposed data degradation pipeline on the fly as a data…