330 - Fine tuning Detectron2 for instance segmentation using custom data

This video tutorial explains the process of fine tuning Detectron2 for instance segmentation using custom data. It walks you through the entire process, from annotating your data, to training a model, to segmenting images, to measuring object morphological parameters, to exporting individual masks (results) as images for further processing.

All other code:

Data courtesy of:
Guay, M.D., Emam, Z.A.S., Anderson, A.B. et al. ​
Dense cellular segmentation for EM using 2D–3D neural network ensembles. Sci Rep 11, 2561 (2021). ​

Data annotated for 4 classes:
1: Cell
2: Mitochondria​
3: Alpha granule​
4: Canalicular vessel​

[SkalskiP]

Hi 👋 I'm the creator of MakeSense! Thanks a lot for using the tool in your tutorial!

[temiwale]

I love you Doc. I needed this. Thank you, DigitalSreeni!

[zubairkhalid]

Appreciate your tutorials a lot! Keep the good work going.

[astitva]

your resources have been incredibly helpful. thank you so much

[sozno]

I honestly believe you have the best tutorial videos on youtube for vision ml. It's very thorough providing all the necessary information for somebody to work through it from scratch. Keep it up. Love these

[satwikpandey]

Happy teacher's day bhaiya. You've made me fall in love with machine learning. Your videos are to the point and nicely explained. Thanks❤

[ajay]

The hardest part is annotating the images, I have done a lot of annotations before. You have done a good job by explaining annotations in detail which is very rare. Can you please share the type of applications that are in demand so that we can try out new things with the knowledge you give us here. Thanks for all the extra effort you put in to explain each line of code.

[qsrbtjp]

Thank you very much for this helpful tutorial. God bless!

[patis.IA-AI]

Merci, super tuto, bien clair, bien explique en un mot "amazing"

[QubitsQuantum]

KING YOU ARE A U ARE THE I THINK U SHOULD GET AN AWARD. THANK YOU!!!

[msaoc]

thank you again for this great tutorial. You make amazing job for us. Detectron works a lot better for me then Yolo8 or Faster RCNN. I will play a bit more with parameters in future, but even with small dataset I was able to get reasonable result =)

[buildingconstructioninnova]

Great job. We will reference you. Keep impacting

[acmontesh]

Thank you for such a great explanation. It would be very nice to complement the tutorial with the workflow to build on top of detectron2, i.e., to use the pooled feature map that the object detection and the masking model use to add a new module within the architecture.

[alexiscarlier]

Thanks again. Do you know if it is possible to train mask r cnn using only bounding boxes that still performs the segmentation after training?

[moumitamoitra]

please make a tutorial on DETR instance segmentation. Your videos are really helpful.

[ErikCarrieri]

Do you know how to adapt this process in order to work on images with multiple bands? For instance, for aerial images of homogeneus areas sometimes having just RGB images could not provide enough information and the accuracy of the segmentation could result too poor. Hence, to improve accuracy more bands (such as a Digital Terrain Model, or a slope band) can be used, since they provide more information for the segmentation of the object. Do you think something like this is feasible?

[rariwa]

Thanks for the tutorial, do you know a reference to train instance segmentation using label mask only (same image size with original image) ? I have one class but I would like to differentiate different object.

[minhloinguyen]

Thank you for worderful lecture, but I get in trouble with dataset detached in description. I don't know how to convert it to COCO format to apply detectron2, I think data include image and label so I don't need to use makesense to label it manually. Give me some tips for using data provided.

[nguyenthehoang]

A point you made at the very end of this video is very important. U-NET is not capable of segmenting overlapping objects. Would you think of making a video comparing between different models for segmentation or other computer vision tasks? Thank you!

[alexis.martin-comte]

Hey, i watched your tutorial and it was very clear but i would love to use custom data format (like tiffs with more than 3 bands) and i find it very difficult to do