November 2017
Intermediate to advanced
304 pages
6h 58m
English
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:\datasets\diabetic\checkpoints --dataset_name=diabetic --dataset_split_name=train --dataset_dir=D:\datasets\diabetic\tfrecords --model_name=inception_v3 --checkpoint_path=D:\datasets\diabetic\checkpoints\inception_v3\inception_v3.ckpt --checkpoint_exclude_scopes=InceptionV3/Logits,InceptionV3/AuxLogits --trainable_scopes=InceptionV3/Logits,InceptionV3/AuxLogits --learning_rate=0.000001 --learning_rate_decay_type=exponential ...
Read now
Unlock full access