How to Code a CNN in PyTorch | Intro to Computer Vision

This content is sponsored by my Udemy courses. Level up your skills by learning to turn papers into code. See the links in the description.

Thanks for informative video. I wish if you could use white board instead of horrible dark board; I see nothing 😓😓

how do you decide when to use maxpooling ?

Why were 32 filters applied when created the Conv2d?

Many thanks mate, you have one a new subscriber

How would you apply this to a non-image dataset? Say I wanted to classify sets numbers as repeating or not repeating, for instance.

Seems like a good tutorial. But it would be helpful if you upload the code somewhere and give the link in the description because watching a video and coding at the same time makes it hard to listen to you. Best regards

why did you use so many conv layers, etc. at the beginning?

When i try to run the code i get an error saying:
AttributeError: 'Tensor' object has no attribute 'items'
Any idea how to fix this?
I have allready updated torch to the latest version, but that didn't help.
Thanks in advance :)

I dont know how to pay back the favor Phil! Why dont you sell more courses on Udemy. :)

line 79, after `self.conv4(batch_data)` , self.bn5 is used. This doesn't cause any runtime errors and apparently doesn't have significant effect on accuracy, however, it perhaps causes the network architecture to be different from what was intended.

Amazing!

Hey man your amazing don’t stop please let me know advice to become very good at this

Still hoping you could do SAC one of these days :3

amazing .....thanx for teaching free