Mike

This piece of code : ```python for x in np.arange(0.6, 0.9, 0.1): print('Eval with TH:', x) metrics = [ cdp.utils.metrics.Fscore(activation='argmax2d', threshold=x), cdp.utils.metrics.Precision(activation='argmax2d', threshold=x), cdp.utils.metrics.Recall(activation='argmax2d', threshold=x), ] valid_epoch = cdp.utils.train.ValidEpoch( model,...

### 💡 Your Question Could you provide an example for running inference on a custom YOLO-NAS model? Couldn't find a minimum example for this in the docs. If this exists...

YOLO-NAS + BOXMOT (YOLO-NAS multi-object tracking)

4

### 🚀 Feature Request I have [an example in my repository](https://github.com/mikel-brostrom/yolo_tracking/blob/737b6ae62b206f718781d3de2398859010e6dcd9/examples/yolo_nas_track.py) on how to integrate SOTA tracking methods together with Yolo-NAS. I am using the Yolov8 backend functionality to achieve...

Model outputs negative values

1

### 🐛 Describe the bug I ran Yolo-NAS on an image ```python rgb = cv2.imread("path/to/image.png") prediction = model.predict(rgb, iou=0.5, conf=0.7)[0].prediction concat_preds = np.concatenate([prediction.bboxes_xyxy, prediction.confidence[:, np.newaxis], prediction.labels[:, np.newaxis]], axis=1) ``` Outputs...

How to get `torch.cuda` outputs from Yolo-NAS?

5

### 💡 Your Question No matter what I do the output is always of type: `numpy.ndarray` ```python import torch import numpy as np from super_gradients.common.object_names import Models from super_gradients.training import...

### Search before asking - [X] I have searched the YOLOv6 [issues](https://github.com/meituan/YOLOv6/issues) and found no similar feature requests. ### Description I have a few requests in my repo asking for...

COCO eval results boost by changing NMS function

1

Hi @Tianxiaomo , I just ported your Yolov4 to Pytorch Lightning. I get the following results evaluating with `pycocotools`   | [email protected] | [email protected]:0.95 -- | -- | -- TianXiaomo(pycocotools evaluation)...

RuntimeError: view size is not compatible with input tensor's size and stride

1

Got this error: ```python File "train.py", line 211, in build_target pred_ious = bboxes_iou(pred[b].view(-1, 4), truth_box, xyxy=False) RuntimeError: view size is not compatible with input tensor's size and stride (at least...

Added MixUp augmentation

14

In this PR, I implemented MixUp (https://arxiv.org/pdf/1710.09412v2.pdf) I appreciate any comment and suggetsion. ## Usage: ```python import cv2 import numpy as np import albumentations as A from matplotlib import pyplot...

PadIfNeeded does not pad correclty when using additional targets

2

## 🐛 Bug `A.geometric.transforms.PadIfNeeded` does not work for the additional images ## To Reproduce Steps to reproduce the behavior: ```python import cv2 import numpy as np import albumentations as A...