def test():
from barista.baristanet import BaristaNet
baristanet = BaristaNet('models/deepq/train_val.prototxt',
'models/deepq/deepq16.caffemodel',
'Augustus')
print "\nData Norms (before loading):"
print "-"*40
data_norms = compute_data_norms(baristanet.net, ('state', 'next_state'))
pretty_print(data_norms)
baristanet.dummy_load_minibatch()
print "\nData Norms (after loading):"
print "-"*40
data_norms = compute_data_norms(baristanet.net, ('state', 'next_state'))
pretty_print(data_norms)
print "\nGradient norms (before computing):"
print "-"*40
grad_norms = compute_gradient_norms(baristanet.net, ord=2)
pretty_print(grad_norms)
baristanet.full_pass()
print "\nGradient norms (after computing):"
print "-"*40
grad_norms = compute_gradient_norms(baristanet.net, ord=2)
pretty_print(grad_norms)
data = extract_net_data(
baristanet.net,
('Q_sa', 'action', 'reward', 'P_sa', 'loss'))
Q, P = data['Q_sa'], data['P_sa']
action, reward, loss = data['action'], data['reward'], data['loss']
print "\nQ_sa:"
print "-"*40
print Q.reshape((Q.size, 1))
print "P_sa:"
print P
print "Action:"
print action
print "Reward:"
print reward
print "Loss:", loss
def test():
from barista.baristanet import BaristaNet
baristanet = BaristaNet('models/deepq/train_val.prototxt',
'models/deepq/deepq16.caffemodel', 'Augustus')
print "\nData Norms (before loading):"
print "-" * 40
data_norms = compute_data_norms(baristanet.net, ('state', 'next_state'))
pretty_print(data_norms)
baristanet.dummy_load_minibatch()
print "\nData Norms (after loading):"
print "-" * 40
data_norms = compute_data_norms(baristanet.net, ('state', 'next_state'))
pretty_print(data_norms)
print "\nGradient norms (before computing):"
print "-" * 40
grad_norms = compute_gradient_norms(baristanet.net, ord=2)
pretty_print(grad_norms)
baristanet.full_pass()
print "\nGradient norms (after computing):"
print "-" * 40
grad_norms = compute_gradient_norms(baristanet.net, ord=2)
pretty_print(grad_norms)
data = extract_net_data(baristanet.net,
('Q_sa', 'action', 'reward', 'P_sa', 'loss'))
Q, P = data['Q_sa'], data['P_sa']
action, reward, loss = data['action'], data['reward'], data['loss']
print "\nQ_sa:"
print "-" * 40
print Q.reshape((Q.size, 1))
print "P_sa:"
print P
print "Action:"
print action
print "Reward:"
print reward
print "Loss:", loss
