07 PyTorch tutorial - What are linear classifiers and how to use them in PyTorch

Welcome back to another video in the PyTorch series. In todays tutorial we learned what linear classifiers are and how we can use them to classify data in PyTorch.
If you found this video helpful, please drop a like and subscribe to our channel. If you have any questions, write them in the comment section below.
💻 Blog:datahacker.rs/0...
🎞 TH-cam: / @datahackerrs
🎞 Link for google collab script: github.com/mat...
.
.
.
.
.
.
#machinelearning​ #artificialintelligence​ #ai​ #datascience​ #python​ #deeplearning​ #technology​ #programming​ #coding​ #bigdata​ #computerscience​ #data​ #dataanalytics​ #tech​ #datascientist​ #iot​ #pythonprogramming​ #programmer​ #ml​ #developer​ #software​ #robotics​ #java​ #innovation​ #coder​ #javascript​ #datavisualization​ #analytics​ #neuralnetworks​ #bhfyp

[@krishnakabi9957]

How were you able to calculate criterion(output, labels) when 'output' has 10 dimensions and 'labels' has 1 ? It's throwing me error.

[@datahackerrs]

Hi, thanks for the question.
So, PyTorch's CrossEntropyLoss expects raw-score logits as input and it applies a softmax function internally to convert them to probabilities.
The best way to check why you get an error is by sending me an email of the code on: [e-mail]

[@krishnakabi9957]

@@datahackerrs yeah thank you. I got it. I was using MSE loss function so got error. I had to convert them to categorical. Nevertheless your code really helped to get a clear understanding. Thanks 😌

[@datahackerrs]

No problem, I'm glad to hear that !