Deci-AI/super-gradients
Easily train or fine-tune SOTA computer vision models with one open source training library. The home of Yolo-NAS.
Jupyter NotebookApache-2.0
Issues
- 0
Custom metrics that depends on image_path?
#2009 opened by Anton-Cherepkov - 0
Work with keypoints for recognize some poses
#2008 opened by abduladolph23 - 0
Correct image transforms for Yolo-NAS
#2006 opened by VadimShabashov - 3
DataParallel Multi-gpu training problem
#2004 opened by JaehwanOh-R - 1
Incorrect arguments in super_gradients/training/utils/distributed_training_utils.py
#2005 opened by ramapriyakj - 0
Any model for instance segmentation?
#2003 opened by roboserg - 1
SSD MobileNet V2 recipe
#2002 opened by Budelon - 2
DiceLoss is unknown object type
#2000 opened by james-imi - 4
Error training yolo_nas_l
#1997 opened by Vdol22 - 0
Issues with Bounding Box Coordinates Exceeding Image Dimensions After ONNX Export
#1998 opened by Venki-code29 - 6
Clarification on license for modifications to Yolo-NAS with pre-trained weights
#1993 opened by MarcA711 - 6
Speed inference Time
#1996 opened by CrasCris - 0
- 1
Change Quantization Precision
#1991 opened by Halafz7 - 1
knowledge distillation to object detection(YOLONAS)
#1992 opened by kimsjpk1 - 2
- 0
RuntimeError: Given groups=1, weight of size [48, 3, 3, 3], expected input[2, 640, 640, 640] to have 3 channels, but got 640 channels instead
#1989 opened by qqqtwh - 1
Enable class agnostic NMS
#1985 opened by kostastsing - 2
quadrangular polygon object detection
#1980 opened by armine105 - 1
WANDB logging not showing
#1981 opened by james-imi - 4
Bad support on some medical images with non RGB format
#1920 opened by james-imi - 6
Save the quantized YoloNAS model
#1914 opened by james-imi - 2
Fine tuning HyperParameters
#1974 opened by CrasCris - 5
Warning: Could not set preprocessing pipeline from the validation dataset: 'AlbumentationsAdaptor' object
#1978 opened by james-imi - 4
- 1
pth or onnx -> pb
#1917 opened by 6894556 - 1
YOLO-NAS - TorchScript output tensor format
#1954 opened by kostastsing - 4
yolo-nas performace
#1939 opened by achen1959 - 1
"DetectionMosaic": {"input_dim": [640, 640], "prob": 0.5} messing up the image size in trainloader
#1970 opened by sandman002 - 1
Possible to use OBS Virtual Webcam as input without capture frame by frame method?
#1967 opened by ikmal-asraf - 1
- 0
`super_gradients.training.utils.predict.prediction_pose_estimation_results.ImagePoseEstimationPrediction.save()` not correctly handling optional parameters and saving image incorrectly
#1972 opened by talhaahussain - 0
How to define a search space
#1971 opened by kaikaizhu - 3
yolo nas pose F.conv2d(input, weight, bias, self.stride, RuntimeError: expected scalar type Byte but found Float
#1969 opened by wesboyt - 3
Onnx model supporting batch prediction
#1964 opened by eyv249 - 4
YOLO NAS: inference time depending on training?
#1960 opened by ullsen - 1
Cache removal
#1935 opened by ShpihanVlad - 2
Error when trying downgrading super-gradients version
#1913 opened by ikmal-asraf - 3
Feature Extraction using YOLO-NAS
#1916 opened by LakshmySanthosh - 1
Installation error: error: subprocess-exited-with-error
#1944 opened by andysingal - 1
- 1
- 10
Yolo Onnx Export -> Experiencing Worse Accuracy
#1952 opened by Budelon - 2
Python 3.11
#1953 opened by davesteps - 2
How to set the lr_warmup_epochs to be greater than 10 ?
#1961 opened by AlfredQin - 2
how to apply post process on openvino inference?
#1938 opened by MinGiSa - 3
How to improve api access speed
#1937 opened by mymuse77 - 1
unidentified image error in model.predict()
#1925 opened by rabion1234 - 1
How to use the knowledge distillation on yolo_nas_pose?
#1926 opened by adam0217 - 0
Error in Quick Start
#1919 opened by dakomura