Image Classification with Convolutional Neural Networks | Deep Learning with PyTorch: Zero to GANs |

preview_player
Показать описание


Code and Resources:

Topics covered in this video:
* Working with the 3-channel RGB images from the CIFAR10 dataset
* Introduction to Convolutions, kernels & features maps
* Underfitting, overfitting, and techniques to improve model performance

This course is taught by Aakash N S, co-founder & CEO of Jovian - a data science platform and global community.

--

Рекомендации по теме
Комментарии
Автор

Its so cool that they are giving all this knowledge for free!!

namanmehta
Автор

Excellent course! Eager to learn it to the end.

Carbon-XII
Автор

Thank you it's very interesting, but what about signal classification with this technique ?

amelamoula
Автор

Very nice vedio sir tq
I am having one doubt sir...how to upload the large image dataset in Colab in less time?

ashwiniyadav
Автор

Fantastic!specific code by code explanation
Thank you very much♡

intuitivej
Автор

Can you do a video on video classification?

mostafaezzat
Автор

is the zero to gans course free? and if it is is the certification also free?

Kishimita
Автор

Thank you for this interesting tutorial, I have a question about optimizers, I tried to use the SGD optimizer for this model but it seems that the accuracy does not improve throughout the epochs it remains frozen, do you know the reason for such behavior of the model?

syy
Автор

Thank you man, free code camp is always the best... God will always 🙏 bless you all. I wish I could support this channel by God's Can I make image segmentation using raspberry pi + ipa tourch screen with this course...?

commandolee
Автор

This works for the "cat and dog image classifier" project on FCC curriculum or i need to see another video?

gonzaloescudero
Автор

How about image Classification using RNN model? Thats same model or not sir . Thank u

akt
Автор

Can i build image matching model from this?

muhammaduseram
Автор

Will I be able to get the certificate now also? Please reply

story_teller_
Автор

Thank you for this. Someday, can you do a troubleshooting session? I sometimes get stuck on the simplest of situations: there's a model that classifies flowers so I use that same model on a data set for cats and dogs and I can't even get a result out. Why? I don't understand the error and don't even know how to start troubleshooting it.

lambdamax
Автор

Too much unnecessary abstraction 👎, misleading intuation about CNN and over-fitting happens because of the memorization (which the explained intuation is wrong, we are more complex networks and over-fitting works different than here) of certain patterns that the network learns on the dataset so, if the net trains for more epochs it's gets generalized for this data so it's obvious that validation loss increases, it was never trained so never get to know the features. Regularisation and certain methods as explained here are correct for dealing with this.

sampathkovvali
Автор

‏استغفر الله عدد ماخلق
استغفر الله ملء ماخلق
استغفر الله عدد مافي السموات والارض
استغفر الله ملء مافي السموات والارض
استغفر الله عدد مااحصى كتابه
استغفر الله ملء مااحصى كتابه
استغفر الله عدد كل شيء
استغفر الله ملء كل شيء

khaledal-falihi