for net in range(nets_to_try):
epoch_count = 20
learning_rates = [0.0001, 0.0001, 0.0001, 0.0001, 0.0001, 0.0001, 0.0001, 0.0001, 0.00001, 0.00001]
model = Model(dataset.training.input_shape, dataset.training.output_shape[0])
for epoch in range(epoch_count):
batch_size = 32
batch_count = (dataset.training.get_count()+batch_size) // batch_size
learning_rate = learning_rates[epoch%len(learning_rates)]
optimizer = torch.optim.Adam(model.parameters(), lr= learning_rate, weight_decay=10**-6)
training_loss_sum = 0.0
for batch_id in range(batch_count):
training_x, training_y = dataset.training.get_batch(batch_size)
training_x = training_x.to(model.device)
training_y = training_y.to(model.device)
predicted_y = model.forward(training_x)
loss = metrics.rms_loss(training_y, predicted_y)
loss.backward()
optimizer.step()
epoch_count = 100
learning_rates = [
0.001, 0.001, 0.0001, 0.0001, 0.0001, 0.0001, 0.0001, 0.0001, 0.00001,
0.00001
]
model = Model(dataset.training.input_shape, dataset.training.output_shape[0])
for epoch in range(epoch_count):
batch_size = 32
batch_count = (dataset.training.get_count() + batch_size) // batch_size
learning_rate = learning_rates[epoch % len(learning_rates)]
optimizer = torch.optim.Adam(model.parameters(),
lr=learning_rate,
weight_decay=10**-6)
training_loss_sum = 0.0
for batch_id in range(batch_count):
training_x, training_y = dataset.training.get_batch(batch_size)
training_x = training_x.to(model.device)
training_y = training_y.to(model.device)
predicted_y = model.forward(training_x)
loss = metrics.rms_loss(training_y, predicted_y)
loss.backward()