Accelerate Image Annotation with SAM and Grounding DINO | Python Tutorial

Description:

In this comprehensive tutorial, discover how to speed up your image annotation process using Grounding DINO and Segment Anything Model (SAM). Learn how to convert object detection datasets into instance segmentation datasets, and see the potential of using these models to automatically annotate your datasets for real-time detectors like YOLOv8. Stay tuned for the upcoming release of a Python library that will make this process even more effortless.

Chapters:

00:00 Introduction
00:58 Python Environment Setup
04:13 Load Grounding DINO and Segment Anything Models
05:42 Single Image Mask Autoannotation
08:24 Full Dataset Mask Autoannotation
09:58 Save Labels to Pascal VOC XML
14:17 Upload Annotations to Roboflow
15:23 Review and Refine Annotations in Roboflow UI
17:11 Convert Object Detection to Instance Segmentation Dataset
22:35 Conclusions
23:28 Announcement

Resources:

Don't forget to like, comment, and subscribe for more content on AI, computer vision, and the latest technological breakthroughs! 🚀

#MetaAI #SegmentAnythingModel #SAM #ImageSegmentation #Python #FoundationModels #ComputerVision #ZeroShot #GroundingDINO #ObjectDetection #DataLabeling

[igor.kasianenko]

Thank you so much for the video explanation. The walk through makes all the difference. For example that 5:53 prompt engineering explanation is so useful.

[cyberhard]

Nice! Looking forward to seeing the new library in action.

[praveen]

wow... excited for the auto distill! :)

[_ABDULGHANI]

Thank you this is exactly what I was waiting for.

[kevinkibebe]

Just completed creating annotations in VOC pascal format🙂😊. cant wait to train my mask rcnn model. Thanks #SAM, #GNO

[SadiyaRasool-xc]

Hi! I was wondering if you could let me know how i can use custom images to detect different objects (other than the labels already in the notebook, like camera, hat, light, etc) and how to add their labels so they can be detected
I'm a beginner in this field and would really appreciate the help!

[lorisdeluca]

It's a very cool concept and surely helpful for some segmentation tasks. However, I see this working mainly with clear and not crowded images. With many tests I did, quite often a lot of items were mislabeled. Nonetheless cool idea and love the channel!

[mentarus]

Great video and notebook! However it looks like supervision install step fails with: groundingdino 0.1.0 requires supervision==0.4.0

[johnpoc]

Very nice video and explanation, thank you very much!

[newahmeddresses]

You're awesome man, thank you so much

[kobic]

I have noticed you use in the supervision awesome package a method to load datasets in PASCAL-VOC format, are you planning to also support COCO formats (also for export?)?

[adolfusadams]

Hey Peter, could you do a video showing how to integrate SuperGradients/Yolo NAS with Roboflow's Autodistill for custom detections on a live real-time webcam feed.
Could you also show maybe in another video how to add custom objects to an existing dataset like the coco dataset?

This would be Epic.🔥

[omh]

I'm not sure why configuring your workspace is stuck and take forever without finishing, any suggestions regarding that?

[akminecraft]

I get this error on cell number 23 (or 6:22 ):
NameError Traceback (most recent call last)
in <cell line: 0>()
6
7 # detect objects
----> 8 detections =
9 image=image,
10 classes=enhance_class_name(class_names=CLASSES),

23 frames
in forward(ctx, value, value_spatial_shapes, value_level_start_index, sampling_locations, attention_weights, im2col_step)
51 ):
52 ctx.im2col_step = im2col_step
---> 53 output = _C.ms_deform_attn_forward(
54 value,
55 value_spatial_shapes,

NameError: name '_C' is not defined

[alassanesakande]

Incredible video ! I was just reading the Grounded-SAM this morning, and boum you're making a tutorial on it. Great job ! I'm just wondering if I could find ways to use it in a medical imagery task ! What do you think ?

[dilshodbazarov]

Awesome tutorial!!!

But while I am running during 6:25, I got error: "NameError: name '_C' is not defined" (after long error description). Anyone can help?

[marinahulscher]

I'd lke to cite this in my work, what is the correct reference?

[kaisbedioui]

As always a very cool video!
Really curious to see Autodistill tool🎉
Does smart polygon tool leverage SAM as well?

[shamukshi]

for "solar panel counting from UAV image"...which approach is better ? 1. creating bounding box (BB) for solar panel using object detection model and then using BB as input for SAM....or.... 2. segmenting everything in the image from SAM...and then classifying each segment as solar panel and non solar panel.

[cantstopthefunk]

So could this technology be used in conjunction with a generative AI to allow "guided generations"? For example I can use a segmentation for "person 1", and tell the AI tool to only change features of person 1 and leave everything else the same?