October 2018
Intermediate to advanced
246 pages
6h 26m
English
We can now start labeling our images. With TensorFlow, this job becomes easier. Assuming that you have installed TensorFlow already, download the following retraining script:
curl https://github.com/tensorflow/hub/blob/master/examples/ image_retraining/retrain.py
Lets retrain the image with the Python script now:
python retrain.py \ --image_dir ~/MLmobileapps/Chapter5/dataset/ \ --learning_rate=0.0001 \ --testing_percentage=20 \ --validation_percentage=20 \ --train_batch_size=32 \ --validation_batch_size=-1 \ --eval_step_interval=100 \ --how_many_training_steps=1000 \ --flip_left_right=True \ --random_scale=30 \ --random_brightness=30 \ --architecture mobilenet_1.0_224 \ --output_graph=output_graph.pb \ --output_labels=output_labels.txt ...
Read now
Unlock full access