def test_lambda_lr(self, lr_mock):
state = {torchbearer.OPTIMIZER: 'optimizer'}
scheduler = ExponentialLR(0.4, last_epoch=-4, step_on_batch='batch')
scheduler.on_start(state)
lr_mock.assert_called_once_with('optimizer', 0.4, last_epoch=-4)
self.assertTrue(scheduler._step_on_batch == 'batch')
def test_lambda_lr(self, lr_mock):
state = {torchbearer.OPTIMIZER: 'optimizer', torchbearer.EPOCH: 0}
scheduler = ExponentialLR(gamma=0.4, step_on_batch=True)
scheduler.on_start(state)
lr_mock.assert_called_once_with('optimizer', gamma=0.4, last_epoch=-1)
self.assertTrue(scheduler._step_on_batch)
alpha=0.5)
else:
state['contour'] = plt.contourf(x,
y,
z,
cmap=plt.cm.jet,
alpha=0.5)
plt.tight_layout()
plt.show()
mypause(0.001)
svm = LinearSVM()
model = Model(svm, optim.SGD(svm.parameters(), 0.1), hinge_loss,
['loss']).to('cuda')
model.fit(X,
Y,
batch_size=32,
epochs=50,
verbose=1,
callbacks=[
scatter, draw_margin,
ExponentialLR(0.999, step_on_batch=True),
L2WeightDecay(0.01, params=[svm.w])
])
plt.ioff()
plt.show()
if state[torchbearer.BATCH] % 10 == 0:
w = state[torchbearer.MODEL].w[0].detach().to('cpu').numpy()
b = state[torchbearer.MODEL].b[0].detach().to('cpu').numpy()
z = (w.dot(xy) + b).reshape(x.shape)
z[np.where(z > 1.)] = 4
z[np.where((z > 0.) & (z <= 1.))] = 3
z[np.where((z > -1.) & (z <= 0.))] = 2
z[np.where(z <= -1.)] = 1
if CONTOUR in state:
for coll in state[CONTOUR].collections:
coll.remove()
state[CONTOUR] = plt.contourf(x, y, z, cmap=plt.cm.jet, alpha=0.5)
else:
state[CONTOUR] = plt.contourf(x, y, z, cmap=plt.cm.jet, alpha=0.5)
plt.tight_layout()
plt.show()
mypause(0.001)
svm = LinearSVM()
model = Trial(svm, optim.SGD(svm.parameters(), 0.1), hinge_loss, ['loss'],
callbacks=[scatter, draw_margin, ExponentialLR(0.999, step_on_batch=True), L2WeightDecay(0.01, params=[svm.w])]).to('cuda')
model.with_train_data(X, Y, batch_size=32)
model.run(epochs=50, verbose=1)
plt.ioff()
plt.show()