DETECTRON2 Custom Object Detection, Custom Instance Segmentation: Part 2 (Training Custom Models)

Detectron2 custom object detection and custom instance segmentation tutorial. This second part of the tutorial explains how to train custom object detection models using detection2. In the second half of the video, we also show how to train a custom instance segmentation model with detectron2. We are using our custom dataset for license plates detection which we developed in part 1. You can use your own custom dataset as long as it follows the format that detectron2 expects.

**The code and dataset is available for our Patreon supporters**
---------------------------------------------
► Time Stamps:
Introduction: (0:00)
Detectron2 Custom Object Detection: (0:56)
Detectron2 Custom Instance Segmentation: (34:38)
---------------------------------------------
► Links:
---------------------------------------------
Want to discuss more?

#TheCodingBug
---------------------------------------------
► My Other Tutorials:
○ Install TensorFlow Under 90 Seconds
○ Install PyTorch Under 90 Seconds
---------------------------------------------
---------------------------------------------
DISCLAIMER: Links included in this description might be affiliate links. If you purchase a product or service with the links that I provide I may receive a small commission. There is no additional charge to you!

[TheCodingBug]

► My Other Tutorials:
DETECTRON2 Custom Object Detection, Custom Instance Segmentation Tutorial: Part 2 (Training Models)

DETECTRON2 Custom Object Detection, Custom Instance Segmentation Tutorial: Part 1 (Preparing Data)

Detectron2 on Colab

Instance Segmentation as Rendering

Detectron2 Complete Tutorial

Colorize Black and White Images and Videos using Python OpenCV

Build and Install OpenCV 4.5.1 With CUDA GPU Support on Windows 10

Face Detection Using OpenCV Python with CUDA GPU Acceleration

YOLOv4 On Android Using TFLite

Install TensorFlow GPU Under 90 Seconds

Install PyTorch GPU Under 90 Seconds

Custom YOLOv4 Object Detection with TensorFlow and TFLite

Darknet YOLOv4 Custom Object Detection: Part 2 (Training YOLOv4 Darknet)

Darknet YOLOv4 Custom Object Detection: Part 1 (Preparing Custom Dataset)

YOLOv4 Object Detection with TensorFlow, TFLite and TensorRT

Darknet YOLOv4 Object Detection for Windows 10 on Images, Videos, and Webcams

Real Time Object Detection on Webcam and Videos Using OpenCV With YOLOv3 and YOLOv4 | Windows Linux

Build and Install OpenCV 4.4.0 with CUDA (GPU) Support on Windows 10

Install TensorFlow GPU and PyTorch with CUDA on Windows 10 Anaconda | CUDA 10.1 cuDNN 7.6

Real-time Multiple Object Tracking with YOLOv4 TensorFlow and Deep Sort | Linux, Windows

[gustavosantiago]

Thank you so much!! After almost a week looking for a good tutorial, I finally found one!

[yhnshkn]

Thanks for this tutorial!!! Was trying to implement this on VS code instead of Google Colab and now I can finally do it! My next step is on how to deploy it to Raspberry Pi. If it is possible, hope you can create a video of it soon. Thanks once again

[gauravsingh-sdhw]

Wonderful video!!! Can you please make a detailed video on "Panoptic segmentation using Detectron2"?

[grantrichardet]

THANK YOU SO MUCH! I loved the video. My only question is: if we are doing object detection or instance segmentation on training on a set with more than one class. How do we get the labels to appear as more than just a number when we test the model?.

[kiphaynes]

Hello, Thank you again for this tutorial. I am having the same warning that you are after training: d2.engine.defaults]: No evaluator found. Use `DefaultTrainer.test(evaluators=)`, or implement its `build_evaluator` method. I do not believe the model is doing any testing after training. Suggestions on this?

[ilyassziz]

hy, thank you for this tutoriel
sir i followed all steps but i get
error : cannot find field '_fields'in the given instances

[fernandolee]

Great tutorial! I tried with my own dataset but I got this error (TypeError: 'NoneType' object is not subscriptable) when I run this (plot_samples(dataset_name=train_dataset_name, n=2)). Not sure why?

[tazuddin]

Thanks a lot for the video. How to put the class name on box after object detection ?

[mannversteckter]

thanks very much for this tutorials!!!

[jasonbourn]

Can you do a video on detection and tracking(sort, deepsort,strong sort)with yolov8

[au-yeungwaikwong]

hi there, thanks for the video and it is very useful. in case if we trained the model one time and want to continue improving the performance, how we can train the model again and again with additional data based on the previous trained model. thanks

[陽明交大-高明秀]

Great! can you explain how to count number of parameter in a model? Thanks

[franciscoalberto]

If I want the network to be re-trainable, that is, train the model with the dataset I have and then when I have more images, continue training it. For that in the step where you put I would have to put resume=True??

[otavioaugustomedolaconquis]

Nicely done! Loved the video. One question: do I need to have internet connection once my model is trained? I mean, I have to train the Detectron first, but once I've done this step, will the code run and identify my images without internet connection? Greetings from Brazil!

[SebastianBejas]

Great tutorial! Everything is working like a charm except for the fact the video is extremely slow, why would that be?

[UZMAALFATMI]

Thanks a lot for this tutorial. Just one thing - Please dont include the background music, its disturbing.

[ShravanKumar]

What do you prefer for object detection - Yolo or Detectron2?
How do you compare, and what factors help in the decision?

[damienbrocard]

Hello ! thanks dor this tutorial. Do you know how i can add labels when i do test.py ?

[JoelPrabhod]

Nicely done! how do we calculate the area of each mask from the inference?