# Retrain image classifier using MobileNet v2

I am using my own dataset to retrain mobilenet_v2_100_224 model, I currently have 4 classes where each class have more than 100 images still I'm observing overfitting even though I've used --random_scale and --random_brightness parameters, how should I overcome this overfitting problem when there's no such regularization technique available in the retrain.py script? following is my TensorBoard visualization:

Retrain command:

python retrain.py --tfhub_module https://tfhub.dev/google/imagenet/mobilenet_v2_100_224/feature_vector/2 --how_many_training_steps 500 --random_scale=5 --random_brightness=10 --output_graph=./retrained_graph.pb --output_labels=./retrained_labels.txt --image_dir ./data --summaries_dir /tmp/log


• How many images do you have? If your dataset is small you will always suffer from overfitting if you train long enough. – J_Heads Jan 24 '19 at 14:52
• Currently have 4 classes where each class have more than 100 images. – Ali Jan 24 '19 at 14:56