-
### Describe the project you are working on
In our projects, we have an animation and palettization system that is presently relying heavily on custom EditorImportPlugins to process png and ascii f…
-
If the pair_constraint = false, the code will use DatasetNoPair. Like DatasetPair, the DatasetNoPair also can call transform (RandomRot, RandomFlip). In paired mode, the cover and stego images will be…
-
Great job, I have benefited a lot. I would like to train on the videos I have collected. What should I do if I want to train with my video dataset? Thank you.
-
Hello @AloshkaD ,
I've read your comments on https://github.com/rykov8/ssd_keras/issues/94, SSD implementation in Keras. In one comment you mentioned something about a generator, to generate equali…
-
### Deep Learning Simplified Repository (Proposing new issue)
:red_circle: **Project Title** : Kashmiri Apple Plant Disease Detection
:red_circle: **Aim** : Create a DL model which will identify the…
-
**Describe the bug**
When using my run command: `python train.py --outdir C:\Users\User\Documents\machinelearning\6\styleganfunresults --cfg=stylegan2 --data C:\Users\User\Documents\machinelearning\6…
-
Training DNNs uses random resize, crop, rotation, etc. for data augmentation. How do you do this with jpeg2dct?
-
The functionality of our augmentation interface should be strong enough to support a generic wrapper that can wrap any augmentations in imgaug/albumentations into a subclass of our `Augmentation`.
…
-
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 'patch-based' train…
-
I have a strange problem. I'm using YOLOv4-tiny. Project is very repetitive, assembly line images which look very similar to each other. I have 3000 images with 50745 marked up objects, and I train…