Shay Aharon

Results 35 comments of Shay Aharon

Feature Extraction using YOLO-NAS

@LakshmySanthosh Here's an example: ```python from super_gradients.training import models from super_gradients.common.object_names import Models from torch.nn import Identity import torch model = models.get(Models.YOLO_NAS_S, pretrained_weights="coco") model.heads = Identity() model.eval() x = torch.randn((5,3,640,640))...

Load Model From The Disk

It seems to me that you are trying to load a chackpoint you have created on your own with the models.get(). It is quite hard to know what went wrong...

Change num input channel in resnet during training then i cannot load it again from checkpoint.

@eric-tc thank you for opening this issue. We will introduce a fix in the next release. If you don't want to wait untill then - contributions are always welcome.

AttributeError: 'Grayscale' object has no attribute 'apply_to_sample'AttributeError: 'Grayscale' object has no attribute 'apply_to_sample'

While it is true that torchvision transforms are supported, that is not how you use them for Object Detection. You can: 1. Re-implement the GrayScale as a [AbstractDetectionTransform](https://docs.deci.ai/super-gradients/latest/docstring/training/transforms.html#latest.src.super_gradients.training.transforms.detection.abstract_detection_transform.AbstractDetectionTransform() 2. Just...

Error when trying downgrading super-gradients version

I am closing this issue as @BloodAxe has already proposed a solution quite some time ago without any response. Please fell free to re-open issue if problem persists.