def main():
batch_size = 100
mnist_train = datasets.MNIST("/hdd/Data/MNIST/",
train=True,
transform=transforms.ToTensor(),
download=True)
mnist_test = datasets.MNIST("/hdd/Data/MNIST/",
train=False,
transform=transforms.ToTensor(),
download=True)
data_feeder = DataFeeder(mnist_train,
preprocess_workers=1,
cuda_workers=1,
cpu_size=10,
cuda_size=10,
batch_size=batch_size,
use_cuda=True,
volatile=False)
data_feeder.start_queue_threads()
cnn = ModelStruct(CNN().cuda(), 0.001)
fcc = ModelStruct(FCC().cuda(), 0.001)
test_data = make_batch(len(mnist_test), 0, mnist_test, use_cuda=True)
for i in range(100001):
images, labels = data_feeder.get_batch()
train(cnn, images, labels, i)
train(fcc, images, labels, i)
if i % 100 == 0:
evaluate_acc(cnn, test_data, i)
evaluate_acc(fcc, test_data, i)
if i in [33333, 66666]:
decrease_lr(cnn)
decrease_lr(fcc)
if i % 20000 == 0:
torch.save(cnn.model, "savedir/cnn_it" + str(i // 1000) + "k.pt")
torch.save(fcc.model, "savedir/fcc_it" + str(i // 1000) + "k.pt")
print(max(cnn.acc))
print(max(fcc.acc))
graph(fcc, cnn)
cnn.losses = losses_to_ewma(cnn.losses)
cnn.val_losses = losses_to_ewma(cnn.val_losses, alpha=0.3)
cnn.acc = losses_to_ewma(cnn.acc)
fcc.losses = losses_to_ewma(fcc.losses)
fcc.val_losses = losses_to_ewma(fcc.val_losses, alpha=0.3)
fcc.acc = losses_to_ewma(fcc.acc)
graph(fcc, cnn)
data_feeder.kill_queue_threads()
def get(self, *args, **kwargs):
'''
Retrieve objects from remote server
'''
extra_fields = kwargs.pop('extra_fields', {})
# extra_fields['fetched'] = datetime.now()
response = graph(self.resource_path % args[0], **kwargs)
return self.parse_response(response.toDict(), extra_fields)
import utils print(utils.graph(3, 5))
def traverse(tree):
machines = []
if not tree:
return
r = traverse(tree.right)
l = traverse(tree.left)
machines.append(r) if r else None
machines.append(l) if l else None
if tree.data in operations:
result = create(machines, tree.data)
print(result.start.transitions, 'Transitions')
else:
result = create(tree.data, None)
return result
if __name__ == "__main__":
inp = input('Regex: ')
symbols = set(inp) - set(operations) - set(EPSILON) - set('()')
Tree, pos = evaluate(inp, 0)
print2D(Tree)
nfa = traverse(Tree)
t = getTransitionTable(nfa, symbols)
graph(t)
while 1:
match = input('String: ')
print(t[0].matches(match, []))
Tree, pos = evaluate(inp, 0)
DFATree, pos1 = evaluate(inp + '.#', 0)
print2D(Tree)
follow = {}
for p in range(pos1):
follow[p + 1] = set()
nfa = traverse(Tree)
nfa_table, accepting, _s = nfa.transition_table()
dfaFromNFA = getTransitionTable(nfa, symbols)
dfaFromRegex = build(DFATree, symbols.union(set('#')), follow)
graph(dfaFromNFA, inp + 'fromNFA')
graph(dfaFromRegex, inp + 'fromRegex')
graphNFA(nfa_table, accepting, inp + 'NFA')
match = True
while match:
match = input('String: ')
start = time.time()
print(dfaFromNFA[0].matches(match, []))
end = time.time()
print('DFA from NFA took', end - start, 'seconds')
start = time.time()
print(dfaFromRegex[0].matches(match, []))
end = time.time()
def draw_graph(self):
if not self.graphing and self.game_state != GAMEOVER:
self.level_scores.append(self.score)
self.graphing = True
if graph(self.level_scores, self):
self.game_state = GAMEOVER