YOLOv8 | How to Train for Instance Segmentation on a Custom Dataset | Computer Vision

[@kemaldarc9665]

Thanks for the video.

[@AbdullahJirjees]

Thanks for the video, any idea how to remove the bounding box (the thick frame) around the object that is segmented?

[@Iztheticgaming]

Sorry but this is my honest opinion: This is the worst video on training int segmentation on custom dataset, you simply used the example notebook from ultralytics, and just worded off as whatsoever was there in the notebook and downloaded a already configured dataset for instance segmentation and trained the model on it.

[@kvnptl4400]

Hey, why do you call this as a instance segmentation? isn't it just a semantic segmentation? here you have same id for all the classes belong to same class.

[@usmanumer9925]

After cloning yolov8 from git repository how we will train it by python train.py its working fine but doesnt show any progress showing no result after execution

[@AseelKareem-ns7ql]

if I want just segmentation in yolov8 and I don't need a bounding box what i have to do @DSwithBappy

[@eleftherito824]

Hey thanks for your incredible work! I did this custom training and try to put a video in the "source" and didnt worked....
specifically i get the error "Sentry is attempting to send 2 pending events
Waiting up to 2 seconds
Press Ctrl-C to quit"
Do you have any idea on this??

[@ashfaqtest]

RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 47 but got size 0 for tensor number 1 in the list.
Sentry is attempting to send 1 pending events
I am getting this error continuously when I train it

[@shruthiap2652]

I need a pre-training model with a resolution size of 4096 * 4096. The default size is 640.. how to handle this larger image sizes in yolov8

[@AnshumanSamanta_45]

change the "imgsz" to 4096 and do not forget to collect all the images for train , valid and test dataset of 4096*4096 pixels .

[@ashfaqtest]

RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 47 but got size 0 for tensor number 1 in the list.
Sentry is attempting to send 1 pending events

[@arpittalmale6468]

Thank you sir

[@sayedhasan5997]

how to perform classification on custom dataset?

[@dswithbappy]

will create soon.

[@sayedhasan5997]

@@dswithbappy thank you. Plz upload that part as soon as possible..

[@mdriad4521]

please make videos about Encoder Decoder,Attention Models, Transformers.

[@gjin2518]

how can we get high accuracy?

[@filipelyrio]

Thanks.

[@srihariswain2128]

😍😍😍

[@shuvroislam3836]

❤❤

[@obaidulhasansouhag985]

In my code it is showing -
Ultralytics YOLOv8.0.28 🚀 Python-3.10.12 torch-2.3.0+cu121 CPU
yolo/engine/trainer: task=segment, mode=train, model=yolov8s-seg.pt, data=data.yaml, epochs=10, patience=50, batch=16, imgsz=640, save=True, cache=False, device=None, workers=8, project=None, name=None, exist_ok=False, pretrained=False, optimizer=SGD, verbose=True, seed=0, deterministic=True, single_cls=False, image_weights=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, show=False, save_txt=False, save_conf=False, save_crop=False, hide_labels=False, hide_conf=False, vid_stride=1, line_thickness=3, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, boxes=True, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, fl_gamma=0.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0, cfg=None, v5loader=False, save_dir=runs/segment/train24
Traceback (most recent call last):
File "/usr/local/bin/yolo", line 8, in
sys.exit(entrypoint())
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/cfg/__init__.py", line 266, in entrypoint
getattr(model, mode)(**vars(cfg))
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/engine/model.py", line 210, in train
self.trainer = self.TrainerClass(overrides=overrides)
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/v8/segment/train.py", line 25, in __init__
super().__init__(cfg, overrides)
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/engine/trainer.py", line 121, in __init__
self.data = check_det_dataset(self.data)
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/data/utils.py", line 190, in check_det_dataset
data = check_file(dataset)
File "/usr/local/lib/python3.10/dist-packages/ultralytics/yolo/utils/checks.py", line 258, in check_file
raise FileNotFoundError(f"'{file}' does not exist")
FileNotFoundError: 'data.yaml' does not exist

[@ashfaqtest]

RuntimeError: Sizes of tensors must match except in dimension 1. Expected size 47 but got size 0 for tensor number 1 in the list.
Sentry is attempting to send 1 pending events

[@Entertainment.x06]

same brother what to do for this