def train(net: NeuralNet,
inputs: Tensor,
targets: Tensor,
num_epochs: int = 5000,
iterator: DataIterator = BatchIterator(),
loss: Loss = MSE(),
optimizer: Optimizer = SGD()
) -> None:
for epoch in range(num_epochs):
epoch_loss = 0.0
for batch in iterator(inputs, targets):
predicted = net.forward(batch.inputs)
epoch_loss += loss.loss(predicted, batch.targets)
grad = loss.grad(predicted, batch.targets)
net.backward(grad)
optimizer.step(net)
print(epoch, epoch_loss)
def train(net: NetWork,
inputs: Tensor,
targets: Tensor,
epochs: int = 500,
loss: Loss = MSE(),
optimizer: Optimizer = SGD(),
iterator: DataIterator = BatchIterator(),
show_info: bool = False):
for epoch in range(epochs):
epoch_loss = .0
for batch_inputs, batch_targets in iterator(inputs, targets):
predictions = net.forward(batch_inputs)
epoch_loss += loss.loss(predictions, batch_targets)
grad = loss.grad(predictions, batch_targets)
net.backward(grad)
optimizer.step(net)
if show_info:
print('epoch:{}, loss:{}'.format(epoch, epoch_loss))