Instance Segmentation Using YOLOv9 on custom dataset

Learn how to perform Instance Segmentation Using YOLOv9 on custom dataset.

Instance Segmentation is a computer vision task, The goal of instance segmentation is to put a mask on each detected object in the image, It is a pixel-wise classification
There are various Instance segmentation models available:
Mask R-CNN, YOLOV5, YOLOv7, SAM (Segment anything Model), YOLOv8.

#computervision #imagesegmentation #objectdetection #yolov9 #yolo #yolov8

[arnavthakur]

Ma'am your way of explaination is really far better. Simple & unique,

[uqqqpjh]

Hi madam. Thank you once again, for helping us all further with YOLOV9.

May I ask for your opinion on using this for plant disease detection. Should I be following the segmentation(this video) or the classification(the furniture video) for that?

I am just unsure which one will be better, for my case of detecting plant disease. It means a lot. Hoping to hear from you soon.✨

[JuanRodrigues-hckx]

I'm try to train the model same way as you did but I'm getting this error:

Traceback (most recent call last):
File "/content/yolov9/segment/train.py", line 646, in <module>
main(opt)
File "/content/yolov9/segment/train.py", line 542, in main
train(opt.hyp, opt, device, callbacks)
File "/content/yolov9/segment/train.py", line 220, in train
hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
KeyError: 'obj'

Any guess on how to solve it?

[JuanRodrigues-hckx]

Hello! I'm trying to do the same as you did, but I keep getting this error:

Traceback (most recent call last):
File "/content/yolov9/segment/train.py", line 646, in <module>
main(opt)
File "/content/yolov9/segment/train.py", line 542, in main
train(opt.hyp, opt, device, callbacks)
File "/content/yolov9/segment/train.py", line 220, in train
hyp['obj'] *= (imgsz / 640) ** 2 * 3 / nl # scale to image size and layers
KeyError: 'obj'

Any guess how to solve this?

[Magentak]

Thank you for the video.

Is there a way to test the model on higher resolution images?

I am getting shape error on mask level.

[ommanojsharma]

Mam you have made plenty of videos on yolo model

Mam if possible could make a video human action recognition using lstm cnn and mediapipe

Also make it end to end that would be great

[gmgeefu]

can we use any voice assistant for voice feedback

[AbirGuiz]

Could you provide me with the best database for pedestrian detection using YOLOv9?

[nakulmali]

Hello mam first thanks for your all valuable videos, mam I request you please upload one video on image classification and detection using yolov5 with transformers.

[TUSHARGOPALKA-njjx]

I have the annotated ade20k dataset. How to train the Yolo-v9 model on this dataset since it's not in yolo format

[GianmarcoGoycocheaCasas]

There is any solution for this?: RuntimeError: CUDA error: out of memory
CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing CUDA_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

[GianmarcoGoycocheaCasas]

Thank you for the explanation. However, when i have applied 'python segment/predict.py ....'. I got this error: AttributeError: 'list' object has no attribute 'shape'. Any solution???

[nakulmali]

Mam first upon thanks for your all valuable videos. Mam, please upload one video on image classification using YOLOv5 on a custom dataset in Google Colab. I am facing issues please upload a video on this topic.

[sevenable]

Will u make some training local with labelmg

[oguzkurtoglu]

Your videos are great, Can you make a tutorial about semantic segmentation?

[uqqqpjh]

Hi madam, hope you are doing well. I have a doubt, do you think it’s possible to add more classes and continue training for a trained .pt model in yolov8. So far I have trained it with 4 classes and now I wanna add one more and only run it through the fifth class. Do you have any idea on how to do it?

[rajmeetsingh]

During prediction there is one error.... "AttributeError: 'list' object has no attribute 'shape'" .... Any solution ?

[MarwaGuizani-wljl]

Are these the steps to develop deep learning models with Python?"

Step 1: Prepare the Data
Step 2: Define the Model
Step 3: Train the Model
Step 4: Evaluate the Model
Step 5: Make Predictions