Hey guys, How can I use an augmentation of random cropping? Thanks

You can use mosaic which is enabled by default.

Thanks. Used it. As far as I understand, it just resizes the image into four tiles and combine them as one puzzle. I want to randomly crop patches from the original image without resizing them.

It crops a portion of the image during the tiling process. You can also use scale and translate augmentations to achieve a combined random crop effect.

Just updating that so far, by looking at the mosaic batches, none of them showed a random crop from the original image. All four of them were resized… Btw, the problem with mosaic is that bounding boxes might be cut off in the new image, resulting in false detections, in my opinion, whereas some ob…

By resizing, do you mean the original image is “squished” to fit the tile? Because Ultralytics never does that. It never squishes the image. Not even for classification. When the image doesn’t fit the tile after resizing, it will crop a square portion out of it. So if the the images are originally a…

[image] redon: Btw, the problem with mosaic is that bounding boxes might be cut off in the new image, resulting in false detections, in my opinion, whereas some objects require the entire bounding box’s context to better detect the object. mosaic as it is currently implemented was found empir…

Good takes. I’ll try to clarify myself: Just to use a common ground: Let’s say that we have an image with resolution of 4K (3840 x 2160 pixels). Then: crop = selecting a smaller patch (say 640x640) out of the original image (4K) resize = resize the resolution from 3840 x 2160 to 1137x640 (with r…

Ah ok. Yes, it’s resized in the dataloader while loading the image. I guess it helps keep the memory requirement low.

I created a branch that uses full resolution during augmentations. You can install it by git clone https://github.com/Y-T-G/ultralytics cd ultralytics git checkout hires_train pip install . Pass hi_res=True during training in model.train() From my brief testing, the results were worse. But you c…

Wow man, impressive work! I’m deeply grateful for your support. I thought you’d guide me where I may modify things in the code, and I’d deep dive into it. So once again, thank you! Appreciating it very much. I’ll try it out :slight_smile:

Random Cropping as an augmentation

Support YOLO

BurhanQ January 7, 2025, 2:36pm 14

Definitely review the Poetry documentation. You might be able to use the add functionality for your project to include your custom forked repository as the install source.

Topic		Replies	Views
Larger obejcts detection boxes being cropped YOLO	5	321	August 20, 2025
How to use Albumentations such as `ToGray` with `Ultralytics.YOLO.train` Discussion yolo , code	4	305	September 1, 2025
Why does `Train()` only support square resolutoins Discussion question	1	250	September 23, 2025
Training an instance segmentation model WITHOUT cropping. [Yolov11] Discussion discussion	1	155	September 6, 2025
Results of save_crop=True differs from result.boxes coordinates YOLO yolo , question , code	2	310	January 16, 2025

Random Cropping as an augmentation

Related topics