FasterViT: Fast Vision Transformers with Hierarchical Attention

In this tutorial, you will get a brief overview of FasterViT. Following that, I will demonstrate how to use a pre-trained FasterViT model on both images and videos.
GitHub: github.com/AarohiSingla/Faste...
Email: [e-mail]
#computervision #transformers #nvidia #imageclassification

[@arnavthakur5409]

Your content & way of explaination is simple amazing ma'am.. Thanks for sharing

[@CodeWithAarohi]

It's my pleasure

[@mohammadyahya78]

amazing as always

[@CodeWithAarohi]

Thank you :)

[@pifordtechnologiespvtltd5698]

Very well explained

[@CodeWithAarohi]

Glad it was helpful!

[@soravsingla8782]

Amazing content

[@CodeWithAarohi]

Thanks!

[@UsamaShahzore]

Just completed my MPhil thesis on VIT. Your videos helped a lot. Thank you from Pakistan.

[@CodeWithAarohi]

Congratulations on completing your MPhil thesis! I'm glad to hear that my videos were helpful to you. Thank you for your kind words and best wishes for your future endeavors. 🙂

[@sumits.parale8735]

🙌 Great

[@CodeWithAarohi]

Thank you! I'm glad you enjoyed it!

[@mohammadyahya78]

I have a metal storage tank that is part of a water heater. During production of tank, leaking happen so early detection using either image processing or computer vision would be great to drop that storage tank and never let it through. I tried thermal image processing and contrast lighting but it's very difficult to see the leaking due to the water spraying and the coating around it that makes it difficult to find potential leaking holes. The video shows employee spraying water onto a pressured storage tank. Even when employee detect leaking while spraying, nothing can be detected from camera still. Any help with that please? Not sure if this one or another could work?

[@aiforeveryone]

Great

[@CodeWithAarohi]

Thank you! I'm glad you enjoyed it!

[@nakulmali1413]

Mam thanks for your videos and knowledge sharing, I am following your channel for study. Mam i request you please upload video on object classification using yolov8s, model training, validation, and testing done with python script.

[@CodeWithAarohi]

I will make it soon

[@CodeWithAarohi]

email me at [e-mail] I will send you the related code there.

[@rickyS-D76]

Thanks for all of your videos, learning a lot from those... I am having error import on "from fastervit import create_model" this line while using "L_1_pretrained" script. Any idea?

[@CodeWithAarohi]

Check if you have installed fastervit, pytorch and the requirements from official github repo of fastervit.

[@fouziaanjums6475]

Is your error resolved?

[@rickyS-D76]

@@fouziaanjums6475 No, are you facing the same problem

[@fouziaanjums6475]

@@rickyS-D76 Yes this error right??
ImportError: cannot import name '_update_default_kwargs' from 'timm.models._builder' (C:\Anaconda\lib\site-packages\timm\models\_builder.py)

[@fouziaanjums6475]

Hi Mam, I am getting an error "ImportError: cannot import name '_update_default_kwargs' from 'timm.models._builder' (/usr/local/lib/python3.10/dist-packages/timm/models/_builder.py)" while running the Step 1: from fastervit import create_model, I have installed all the necessary requirements, I am running the code in Google Colab, I have even tried through jupyter notebook but getting the same error, Request you to please help me out....

[@CodeWithAarohi]

I have added the steps in readme file. Please follow those steps: github.com/AarohiSingla/FasterViT

[@abdurahmanhussain8666]

Hi can I use this for brain mri segmentaion ? benchmark on TCIA dataset

[@CodeWithAarohi]

This is a classification model.

[@abdurahmanhussain8666]

based on the base model could be use build right ?

[@jasonchen6623]

i think training is more important than detect. please teach us how to train on FasterViT model

[@CodeWithAarohi]

I agree and here is the video to train and test your custom model: ua-cam.com/video/m5iWjkewmtk/v-deo.html

[@shahidulislamzahid]

Thank you so much, code link not working

[@CodeWithAarohi]

Try now

[@shahidulislamzahid]

@@CodeWithAarohi ok