def main():
# Show info when training
log = logging.getLogger('tensorflow')
log.setLevel(logging.INFO)
classifier = get_classifier(8)
train_spec = tf.estimator.TrainSpec(input_fn=lambda: input.batch_dataset(
"dataset/reflected-train.tfrecords", tf.estimator.ModeKeys.TRAIN, 8),
max_steps=2000)
eval_spec = tf.estimator.EvalSpec(input_fn=lambda: input.batch_dataset(
"dataset/reflected-eval.tfrecords", tf.estimator.ModeKeys.EVAL, 8))
tf.estimator.train_and_evaluate(classifier, train_spec, eval_spec)
def main():
# Show info when training
log = logging.getLogger('tensorflow')
log.setLevel(logging.INFO)
classifier = get_classifier(8)
for i in range(1,51):
train_spec = tf.estimator.TrainSpec(
input_fn=lambda:input.batch_dataset("dataset/shape-train-???.tfrecords", tf.estimator.ModeKeys.TRAIN, 8),
max_steps= 10000 * i
)
eval_spec = tf.estimator.EvalSpec(
input_fn=lambda:input.batch_dataset("dataset/shape-eval-???.tfrecords", tf.estimator.ModeKeys.EVAL, 8)
)
tf.estimator.train_and_evaluate(classifier, train_spec, eval_spec)