def train(model, optim, steps, BS=128, gpu=False):
if gpu is True: [x.cuda_() for x in get_parameters([model, optim])]
losses, accuracies = [], []
for i in (t := trange(steps, disable=os.getenv('CI') is not None)):
samp = np.random.randint(0, X_train.shape[0], size=(BS))
x = Tensor(X_train[samp].reshape((-1, 28 * 28)).astype(np.float32),
gpu=gpu)
Y = Y_train[samp]
y = np.zeros((len(samp), 10), np.float32)
# correct loss for NLL, torch NLL loss returns one per row
y[range(y.shape[0]), Y] = -10.0
y = Tensor(y, gpu=gpu)
# network
out = model.forward(x)
# NLL loss function
loss = out.mul(y).mean()
optim.zero_grad()
loss.backward()
optim.step()
cat = np.argmax(out.cpu().data, axis=1)
accuracy = (cat == Y).mean()
# printing
loss = loss.cpu().data
losses.append(loss)
accuracies.append(accuracy)
t.set_description("loss %.2f accuracy %.2f" % (loss, accuracy))
def train(model, optim, steps, BS=128):
losses, accuracies = [], []
for i in (t := trange(steps)):
samp = np.random.randint(0, X_train.shape[0], size=(BS))
x = Tensor(X_train[samp].reshape((-1, 28*28)).astype(np.float32))
Y = Y_train[samp]
y = np.zeros((len(samp),10), np.float32)
# correct loss for NLL, torch NLL loss returns one per row
y[range(y.shape[0]),Y] = -10.0
y = Tensor(y)
# network
out = model.forward(x)
# NLL loss function
loss = out.mul(y).mean()
loss.backward()
optim.step()
cat = np.argmax(out.data, axis=1)
accuracy = (cat == Y).mean()
# printing
loss = loss.data
losses.append(loss)
accuracies.append(accuracy)
t.set_description("loss %.2f accuracy %.2f" % (loss, accuracy))
