Transfer Learning in Neural Network is a technique used in machine learning where knowledge gained from training one model (source domain) is transferred and applied to a different but related model (target domain). In neural networs, this involves taking a pre-trained model developed for one task and fine-tuned or using its learned features to solve another related task.
In this project I will be implementing a model using transfer learning with MobileNetV2 as the source model. The model will predict an image is an Alpaca image or not Alpaca image.
This project is based on Images stored in the disk. I have used image_data_set_from_directory()
function provided by Keras
to prepare Train/Validation datasets.
- Tensorflow
- Keras
- MobileNetV2
I have used TensorFlow framework for this project.
pip install tensorflow
- Creat dataset from a directory
- Preprocess and augment data using the Sequential API
- Adapt a pretrained model to new data and train a classifier using the functional API MobileNet
- Fine-tune a classifier's final layer to improve accuracy