307 - Segment your images in python without training using Segment Anything Model (SAM)

Segment your images in python without training using Segment Anything Model (SAM) by Meta AI

Useful links:

[Lalit-ywtb]

This model is brilliant. When I read the news, I was blown away that they made it open-source and allowing commercial use as well.
We are living in wild times.
As usual love your content Sreeni.

[jurischaber]

Hey DigitalSreeni,
I must thank you for your videos helping me a lot with my master thesis,
I even got the best degree.
Thanks....

[datapro]

Wow! I watched your video again and ran through the example you provided. SAM is a great annotation tool and a real labor saver. Fabulous presentation Sreeni.

[biswanathsaha]

The model is so good, in our lab we need segmentation for multi-channel images, it definitely streamlines lot of things

[yoverale]

Thanks! Impressive results and perfectly short explanation. Fast and clear

[datapro]

What a great and timely video. Thank you! I wasn't aware of SAM prior to seeing your presentation.

[OlgaChambers-xz]

thanks a lot, it works great for my microscopic data, just very slow segmentation for live monitoring

[texasfossilguy]

How do you apply labels to them? Making a mask is one thing, but how do you label classes?

[maxgadd]

your contributions are amazing. wow. thank you so much

[sara_kassani]

ViT stands for Vision Transformers. I used UNETR and SwinUNTER (vision transformers) and both of them had excellent performance specifically if your dataset size is very small.

[ozanapaydin]

Thank you for preparing this really really helpful tutorial and also teaching this model in a very simple way!

[edmald]

To extract labels I did this function maybe can help:

def create_labeled_mask(anns, height, width, max_num_classess):
if len(anns) == 0:
return

sorted_anns = sorted(anns, key=(lambda x: x['area']), reverse=True)
sorted_anns =

label = 1
labeled_mask = np.zeros((height, width))

for ann in sorted_anns:
m = ann['segmentation']
labeled_mask[m > 0] = label
label += 1
labeled_mask =
return labeled_mask

[Brickkzz]

A video for fine tuning Segement Anything Model would be great

[yangyang]

Thank you for sharing! By the way, I like your Spyder IDE.

[hikvruzhunter]

Hi, could you make a tutorial on how to connect SAM outputs with convolutional networks to determine what object it is or extract information? Regards.
Great video!

[niteshtakarker]

Thank you for the informative video tutorial! I'm currently working on agriculture land cover monitoring, and I'm wondering if this model can be used for that purpose. Can you confirm if it's suitable for agriculture land cover monitoring?

[sithibanu]

This is a useful information for my research. Sir can you make a video for prior setting like installing sam, transformer, checkpoints.

[ajaypatro]

Hy, sir I am from Geoinformatics background, and I want to get started with Py to process image processing on remote sensed data, where should I start what Gui would you recommend for Py Spyder or vs code is fine i want to visualize the data too while working on it.

[aprashnani]

Does this make the other models we discussed on this channel, like UNet, ResNet etc., obsolete? Is it still worth it to learn about them?

[streamingdev]

I would love to know how they do the hover and onclick segment / mask