-
I'm trying to use validation_set=0.1 with the below tflearn image augmentation pipeline, but I get the following error which makes it seem like tflearn is trying to run the metric on the original imag…
-
Can someone give me some insight about the heuristic value (rt) that controls the augmentation strength in the ada pipeline? In augments.py the code is the following:
`strength += nimg_ratio * np.s…
-
I try to implement the mosaic and mixup augmentation in your code, but I confused because the dataset is wrapped around the SemiDataset wrapper and the mosaic or mixup augmentation need the dataset to…
-
- As a data engineer/data science engineer, why do I need augmentations for my problem/ML task?
- As a data science team, I want to know how augmentation helps solve my problem, also by how much?
…
-
This issue is a continuation of #404 and #406.
As mentioned in the Issue/PR above, there is room for improvement regarding the augmentation pipeline.
Before going in one direction or another, we s…
-
Can you please tell me where in the code teacher model is being updated by the EMA of the student model?
-
I've been hand-rolling augmenters using imgaug (https://github.com/aleju/imgaug), as I really like some of the options that are not available in the tf object detection api (https://stackoverflow.com/…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussions) and fou…
-
### What is the feature?
I'm working on a project that requires me to try many combinations of models, datasets, tasks and augmentation pipelines. You can do this pretty well without manually definin…
-
Currently, there are many data modules:
- data_utils.py: a set of utilities for numpy (to_categorical for labels, featurewise/samplewise transformations), for images (load_images, resize, etc...), for…