def train(hidden_size, batch_size):
batcher = Batcher()
print('Data:')
print(batcher.inputs.shape)
print(batcher.targets.shape)
model = get_model(hidden_size, batcher.chars_len())
model.compile(loss={
'op': 'categorical_crossentropy',
'char': 'categorical_crossentropy'
},
optimizer='adam',
metrics=['accuracy'])
model.summary()
for grad_step in range(int(1e9)):
ppp = gen_large_chunk_single_thread(batcher,
batcher.inputs,
batcher.targets,
chunk_size=batch_size)
x_train, y_train_1, y_train_2, x_val, y_val_1, y_val_2, val_sub_inputs, val_sub_targets = ppp
model.train_on_batch(x=x_train, y=[y_train_1, y_train_2])
print(
dict(
zip(model.metrics_names,
model.test_on_batch(x=x_val, y=[y_val_1, y_val_2]))))
# guess = c_table.decode(preds[0], calc_argmax=False)
# top_passwords = predict_top_most_likely_passwords_monte_carlo(model, row_x, 100)
# p = model.predict(row_x, batch_size=32, verbose=0)[0]
# p.shape (12, 82)
# [np.random.choice(a=range(82), size=1, p=p[i, :]) for i in range(12)]
# s = [np.random.choice(a=range(82), size=1, p=p[i, :])[0] for i in range(12)]
# c_table.decode(s, calc_argmax=False)
# Could sample 1000 and take the most_common()
if grad_step % 100 == 0:
row_x, password_target, password_input = x_val, val_sub_targets, val_sub_inputs
ops, char = model.predict(row_x, verbose=0)
predicted_chars = list(batcher.decode(char))
ops = ops.argmax(axis=1)
decoded_op = []
for op in ops:
if op == 0:
decoded_op.append('insert')
elif op == 1:
decoded_op.append('replace')
else:
decoded_op.append('delete')
for i, (x, y, pc, po) in enumerate(
zip(password_input, password_target, predicted_chars,
decoded_op)):
print('x :', x)
print('y :', y)
print('predict char :', pc)
print('predict op :', po)
print('---------------------')
if i >= 100:
break
def predict_top_most_likely_passwords(sed: Batcher, model, row_x, n):
p = model.predict(row_x, batch_size=32, verbose=0)[0]
most_likely_passwords = []
for i in range(n):
# of course should take the edit distance constraint.
pa = np.array([
np.random.choice(a=range(sed.ENCODING_MAX_SIZE_VOCAB + 2),
size=1,
p=p[j, :])
for j in range(sed.ENCODING_MAX_PASSWORD_LENGTH)
]).flatten()
most_likely_passwords.append(sed.decode(pa, calc_argmax=False))
return most_likely_passwords
