Last active
April 2, 2019 08:08
-
-
Save steermomo/e60c05e1ac6d2c07a60cfd6f73148c1d to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| from keras.utils.data_utils import OrderedEnqueuer | |
| val_generator = DataGenerator(target=target, dataset_type='test', batch_size=12, | |
| dim=img_dim, shuffle=False) | |
| steps_per_epoch = len(val_generator) | |
| val_enqueuer = OrderedEnqueuer( | |
| val_generator, | |
| use_multiprocessing=use_multiprocessing) | |
| val_enqueuer.start(workers=workers, | |
| max_queue_size=max_queue_size) | |
| val_enqueuer_gen = val_enqueuer.get() # 无限循环 ref:https://github.com/keras-team/keras/blob/master/keras/engine/training_generator.py#L180 | |
| steps_done = 0 | |
| batch_index = 0 | |
| while steps_done < steps_per_epoch: | |
| print(f'\r{steps_done}/{steps_per_epoch}', end='') | |
| generator_output = next(val_enqueuer_gen) | |
| x, y = generator_output | |
| y_pred = model.predict_on_batch(x) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Benchmark First !!!