-
### Details
Problem:
Continuously improve and expand the provided codebase in all ways of value, achieving perpetual progress.
Proposed Solution:
Utilize Sweep AI's capabilities to automate t…
-
Hello! Thanks for the great paper and code for AdaTarget, it is very interesting.
I've integrated in a model training framework here:
https://github.com/victorca25/traiNNer/tree/master/codes/mode…
-
Hello,
I am new to this and coming across an issue that I do not quite understand. Appreciate any help here!
I have input images of size 800x1066 (sometimes 1067). I've generated my tfrecords a…
winnf updated
2 years ago
-
Hi!
Thanks a lot for the great work here.
Would you mind sharing how big was the dataset you used to train your model?
Also, which strategies did you use to create the `440x440` images you used fo…
-
Hello everyone.
I have a use case to train model on small images with shape (80, 140).
Objects, that i want to detect on these images are even more small, it's a characters.
Already implemen…
-
Hi, I am trying to merge the PVNet code with your single stage code. As part of training, the images undergo augmentation such as rotation, cropping and scaling. I have applied the corresponding augme…
-
Hello Pytorch vision people !
I am currently working on a project that requires lots of image augmentations
to perform better. And I believe this is not only my case. When reading
about …
-
@nrweir commented on [Wed Apr 17 2019](https://github.com/CosmiQ/cw-nets/issues/44)
Potentially helpful link for making this work with GPU acceleration:
http://deeplearnphysics.org/Blog/2018-10-02…
-
Hello, I've attempted to train the Raft model using the MOVi-f dataset for reproducing the results, but the experiment results are different from those in the paper.
I used the same training code as …
-
## Additional context
import albumentations as A
transform = A.Compose(
[A.RandomCrop(1024,1024)],
bbox_params=A.BboxParams(format='coco', label_fields=['category_ids'], min_visi…