Now let's move towards training and evaluating our model.

The training script is present inside train_image_classifer.py. Since we have followed the workflow of the library, we can leave this file untouched and run our training routine with the following command:

python train_image_classifier.py --train_dir=D:datasetsdiabeticcheckpoints --dataset_name=diabetic --dataset_split_name=train --dataset_dir=D:datasetsdiabetic	frecords --model_name=inception_v3 --checkpoint_path=D:datasetsdiabeticcheckpointsinception_v3inception_v3.ckpt --checkpoint_exclude_scopes=InceptionV3/Logits,InceptionV3/AuxLogits --trainable_scopes=InceptionV3/Logits,InceptionV3/AuxLogits --learning_rate=0.000001 --learning_rate_decay_type=exponential 

In our setup, we have run the training process overnight. Now, we will run the trained model through the validation process to see how it works.