Transfer Learning with the VGG16 Model
Transfer learning (TL) is a research problem in machine learning (ML) that focuses on storing knowledge gained while solving one problem and applying it to a different but related problem. For example, knowledge gained while learning to recognize cars could apply when trying to recognize trucks.
What is VGG16?
VGG16 is a convolutional neural network model .The model achieves 92.7% top-5 test accuracy in ImageNet, which is a dataset of over 14 million images belonging to 1000 classes. It was one of the famous model submitted to ILSVRC-2014. It 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.
In this model we have 16 layers in the model.
- 13 convolve layers
- 3 dense layers
Problem statement:Create a project using transfer learning solving Face Recognition using Deep Learning models like VGG16.
Step 1: preparation of dataset.
I clicked 250 images for training and 40 for test with the use of open-cv to capture real time images of the face and use them as training and test datasets.
Step 2: Training VGG16 model
Using VGG16 model.ipynb we are going to train our VGG16 model based on the training and validation images.
layers classification
Freezing all the layers of the model except input and output layer.
All the layers are set to false, which means that they will not train again.
Loading our Data Set
Training our Layers
our final accuracy is 99.4%
Step 3: Loading our model
Here’s my github repository link : https://github.com/kritika2812/MLOPS_task4..git
Thankyou !!!!!
