Laughing

@AyanPaul2210 > Dataset not found warning, missing paths ['/content/drive/MyDrive/yolo/yolov8/obj_det/datasets/Field-Capsicum-1/valid/images'] hi it seems you didn't give the correct dataset path.

@Edohvin what version of ultralytics are you using? please use the latest package version. :)

@MohamedAtef321 closing the issue as it's solved, feel free to reopen it if you have any related issues. :)

@SheeppLi @himadrivaidya For training a segmentation model, please make sure your dataset labels are all segmentation labels. This error `RuntimeError: Sizes of tensors must match except in dimension 1. Expected...

@himadrivaidya closing this issue as there's a similar issue solved. feel free to reopen it if you still have any related issues. :)

@khengyun You're training detection but looks like you got two types annotations, both detection and segmentation. Please check your data labels.

@sstainba hey I tested [seg_test_v8_loader.zip](https://github.com/ultralytics/ultralytics/files/10549316/seg_test_v8_loader.zip) with the latest package version but never saw the shape error caused by mixed annotations again. Also I noticed you were using `YOLOv8.0.16` and this...

@kyoko9000 hi you can easily show plotted frames by set `show=True`.

@onuralpszr looks like the error raised by model.val(). can you add `data` arg in model.val() and try model.val(data="coco128.yaml")?

@onuralpszr oh we haven't supported this workflow yet: ```python from ultralytics import YOLO model = YOLO("yolov8n.pt") # load a pretrained YOLOv8n model model.train(data="coco128.yaml") # train the model model.export(format="torchscript") ``` the...