Expalined VGG-16 With Keras on Custom Dataset | Convolutional Neural Network | Deep Learning

VGG16 – Convolutional Network for Classification and Detection

Github: https://github.com/AarohiSingla/VGG-16

VGG16 is a convolution neural net (CNN ) architecture which was used to win ILSVR(Imagenet) competition in 2014. VGG16 makes the improvement over AlexNet by replacing large kernel-sized filters (11 and 5 in the first and second convolutional layer, respectively) with multiple 3×3 kernel-sized filters one after another. VGG16 was trained for weeks and was using NVIDIA Titan Black GPU’s.
Most unique thing about VGG16 is that instead of having a large number of hyper-parameter they focused on having convolution layers of 3x3 filter with a stride 1 and always used same padding and maxpool layer of 2x2 filter of stride 2.
VGG-16 is a convolutional neural network that 16 layers deep.
The default input size for VGG16 model is 224 x 224 pixels with 3 channels for RGB image.

VGG was a breakthrough in the world of Convolutional Neural Networks after

LeNet-5 (1998)
AlexNet (2012)
ZFNet(2013)
GoogleNet/Inception(2014).

Learn how to create your own VGG-16 network on custom dataset.
In this video, I will also explain how to use pre trained VGG-16 network.


If you have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer your queries.
Contact: [email protected]

Please consider clicking the SUBSCRIBE button to be notified for future videos & thank you all for watching.
Channel:    / @codewithaarohi  
Support my channel 🙏 by LIKE ,SHARE & SUBSCRIBE

Check the complete Machine Learning Playlist :    • Machine Learning Tutorial  

Check the complete Deep Learning Playlist :    • Deep Learning Tutorial  

Contact: [email protected]



#computervision #VGG-16 #vgg #vggnetwork #vgg16network #AI #ArtificialIntelligence #DeepLearning