def main():
num_points = 32 * 100 * 2
data = [i * (1 / num_points) for i in range(num_points)]
it = parallel_it.from_items(data, 2, False).for_each(lambda x: [x, x])
# this will create MLDataset with column RangeIndex(range(2))
ds = ml_data.from_parallel_iter(it, True, batch_size=32, repeated=False)
tf_ds = ds.to_tf(feature_columns=[0], label_column=1)
trainer = TFTrainer(
model_creator=model_creator,
data_creator=make_data_creator(tf_ds),
num_replicas=2,
config={
"batch_size": 32,
"fit_config": {
"steps_per_epoch": 100,
},
},
)
for _ in range(10):
trainer.train()
model = trainer.get_model()
print("f(0.5)=", float(model.predict([0.5])))
def main(smoke_test,
num_replicas,
use_gpu=False,
augment_data=False,
batch_size=32):
data_size = 60000
test_size = 10000
batch_size = batch_size
num_train_steps = 10 if smoke_test else data_size // batch_size
num_eval_steps = 10 if smoke_test else test_size // batch_size
trainer = TFTrainer(
model_creator=create_model,
data_creator=(data_augmentation_creator
if augment_data else data_creator),
num_replicas=num_replicas,
use_gpu=use_gpu,
verbose=True,
config={
"batch_size": batch_size,
"fit_config": {
"steps_per_epoch": num_train_steps,
},
"evaluate_config": {
"steps": num_eval_steps,
},
},
)
training_start = time.time()
num_epochs = 1 if smoke_test else 3
for i in range(num_epochs):
# Trains num epochs
train_stats1 = trainer.train()
train_stats1.update(trainer.validate())
print(f"iter {i}:", train_stats1)
dt = (time.time() - training_start) / 3
print(f"Training on workers takes: {dt:.3f} seconds/epoch")
model = trainer.get_model()
trainer.shutdown()
dataset, test_dataset = data_augmentation_creator(
dict(batch_size=batch_size))
training_start = time.time()
model.fit(dataset, steps_per_epoch=num_train_steps, epochs=1)
dt = time.time() - training_start
print(f"Training on workers takes: {dt:.3f} seconds/epoch")
scores = model.evaluate(test_dataset, steps=num_eval_steps)
print("Test loss:", scores[0])
print("Test accuracy:", scores[1])
tensorboard_callback = TensorBoard(log_dir=ssd_log_path)
learning_rate_callback = LearningRateScheduler(train_utils.scheduler,
verbose=0)
training_start = time.time()
num_epochs = 1 if args.smoke_test else args.epochs
for i in range(num_epochs):
# Train num epochs
train_stats1 = trainer.train()
# train_stats1.update(train.validate())
print(f"iter {i}:", train_stats1)
dt = (time.time() - training_start) / num_epochs
print(f"Training on workers takes: {dt:.3f} seconds/epoch")
model = trainer.get_model()
trainer.shutdown()
training_start = time.time()
ssd_model.fit(ssd_train_feed,
steps_per_epoch=step_size_train,
validation_data=ssd_val_feed,
validation_steps=step_size_val,
epochs=opt.epochs,
callbacks=[
checkpoint_callback, tensorboard_callback,
learning_rate_callback
])
dt = (time.time() - training_start)
print(f"Training on workers takes: {dt:.3f} seconds/epoch")