PyTorch Tutorial 14 - Convolutional Neural Network (CNN)

You uploaded 3 years ago and im so glad you did, university didnt teach this much istg THANKS ALLOT !!!! KEEP UPLOADING MORE. and tell a toolkit other than cuda for intel UHD graphics

Thank you so much! Everything is so clear. And even though English is not my mother tongue, I can catch up without caption. (*^_^*)

May I ask why you don't just use nn.Sequential to define the model? It is much more straightforward and easier to read I think. Or perhaps this is a newer feature? Anyway, for anyone interested, I just replaced the class definition with:

model = nn.Sequential(
nn.Conv2d(3,6,5,stride=1),
nn.ReLU(),
nn.MaxPool2d(2,2),
nn.Conv2d(6,16,5,stride=1),
nn.ReLU(),
nn.MaxPool2d(2,2),
nn.Flatten(),
nn.Linear(16*5*5,120),
nn.ReLU(),
nn.Linear(120,84),
nn.ReLU(),
nn.Linear(84,10)
).to(device)

I am confused, why doesn't max pooling change the input dimension of the next convolution layer?

Hey, just wanted to let you know how much these videos helped me. I started working to learn ML three years ago and now, as I'm about to graduate, have come to the point of independently building and training nets for my Undergrad Senior Project. I don't think I ever would have gotten off the ground if not for these and even now reference them when I'm starting with new types of nets or data prep. Thanks for all the time and effort you put into these.

Hi, Thank you for great video;
Please have y made before an example on which you show how to load images from local directory + labels from extrac csv or pkl file ?
Thank you

Great Video . One simple question, you explain very well how the hardcoded values came to be. Could the values for the inner layers (pool, conv2, fc1, fc2,...) be obtained programmatically from the previous layer ?

You are the best considering the strength of explanation!

wow its very awesome thx :)

brother please send me this code

I am studying at FAU and watching your videos to crack the coding part of DL exam ✌

please upload more advance pytorch videos and projects and keep doing great work

keep going. Please continue to upload. Great Content and support.

Writing my Bachelor thesis about this, you are a life saver :-)

Hello. Is it the same a "train_loader" than a minibatch?

Great video! Keep it up!

Great work
Thank you very much

The best CNN python video!!! Thank you so much!!!

What is the difference between view and reshape? reshape was used in FFN video and view is used here. Thanks!

Loved the video as always, thank you! Short question: I was wondering how you came (or have been comming) up with the simple CNN architecture(s), is this for example a common vanilla network or do you maybe have a paper at hand that you use. Would be interesting to know. Thanks ahead - big fan!

I really love your videos

Awesome video thank you very much!

Hello thanks for that great video, but I have a question how can we choose the number of units in the hidden layers is it random or what please help and thanks

On 14.03, what if we have multiple filters, i.e 4 filters with size of 3 x 3 ? Does the equation change ?

your course is saving my life, EVERY SINGLE VIDEO is a gold material

Could you please clarify why you flatten to columns instead of rows i.e. x.view(-1, 16 * 5 * 5) instead of x.view(16*5*5, -1). In my program, I noticed that there are errors like NaN happening when I flatten to rows (with a higher learning rate of 0.5), rather than columns. Seems like you have done this for some reason, could you please explain it?

hi, the Conv2d has the Relu activation?

Thank you good man

Thanks

Hello! I always look at your work carefully and I want to thank you for what you do!
I have one question about the code. Please explain why you use exactly such parameters in: transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5)). Thank you!

Awasome precise and insighful tutorials, indeed the best about PyTorch and CNN. Thank you

you are a LIFESAVER

You are truly talented and understand the material in such a way you can really teach it in simple terms and everything. Thank you for these videos, I am getting more and more confident with Pytorch because of you!

There is one question though, do we need to keep track of the shapes after each convolution and/or pooling layer? So that we can enter the correct amount of input neurons in the first Linear layer. Isn't there a convenient method for this?

BTW Thanks for the awesome tutorial !!

thank you, very good explanation.

Thank you for the tutorial as well as the github. I need to mess around with things to get a solid grasp of them so I greatly appreciate this. :D

Hi, I just want to thank you for your work. I think those videos are really helpful to me and we are very appreciative of those. :-D They are really useful and you have a clear explaining structure. Thank you a lot!

Very helpful, thank you!

Dude...can't thank you enough....You saved my life hehe

Why not use flatten layer?

Hello! Thanks for the videos. Quick question: i've seen people use the methods "model.train()" and "model.eval()". Can you tell me why they are not necessary here? Thank you in advance!

This video really want to goes in trading page sir your teaching style is awesome ! you are too cool thank your for this video . I fall in love with your teaching

what if i want to do this but with a data which is not one of the torchvision datasets how would I load it then

Why do you choose 6 and 16 for ouput size in conv layer? Is this just trying out what works the best? I read when the image has more features the outputsize should be greater. Is this correct? Would be size if you do some more content about cnn or gan

hi! Thank you so much for this awesome tutorials. we calculate the n_total_steps = len(train_loader). why is the train loader length is 12500? where did we define it?

This equation saved me. I am literally in a masters program and I was struggling with getting the right number of dimensions. Not anymore thanks to you!!

Excellent work but I want to know will this model work on a dataset that has classes that aren't mutually exclusive? For ex: Street View House Number Dataset (SVHN).

This, as with all videos on this channel, needs more views. Every time I need to learn something on ML, this channel has the best and most enjoyable videos.