def main(stdscr, filename: str, num: int, result_logger: ResultLogger):
terminal = Terminal(stdscr, create_char_map())
terminal.init_window(FIELD_WIDTH, FIELD_ROW)
program_set = AdditionProgramSet()
addition_env = AdditionEnv(FIELD_ROW, FIELD_WIDTH, FIELD_DEPTH)
questions = create_questions(num)
teacher = AdditionTeacher(program_set)
npi_runner = TerminalNPIRunner(terminal, teacher)
npi_runner.verbose = DEBUG_MODE
steps_list = []
for data in questions:
addition_env.reset()
q = copy(data)
run_npi(addition_env, npi_runner, program_set.ADD, data)
steps_list.append({"q": q, "steps": npi_runner.step_list})
result_logger.write(data)
terminal.add_log(data)
if filename:
with open(filename, 'wb') as f:
pickle.dump(steps_list, f, protocol=pickle.HIGHEST_PROTOCOL)
def main(stdscr, model_path: str, num: int, result_logger: ResultLogger):
terminal = Terminal(stdscr, create_char_map())
terminal.init_window(FIELD_WIDTH, FIELD_ROW)
program_set = AdditionProgramSet()
addition_env = AdditionEnv(FIELD_ROW, FIELD_WIDTH, FIELD_DEPTH)
questions = create_questions(num)
if DEBUG_MODE:
questions = questions[-num:]
system = RuntimeSystem(terminal=terminal)
npi_model = AdditionNPIModel(system, model_path, program_set)
npi_runner = TerminalNPIRunner(terminal, npi_model, recording=False)
npi_runner.verbose = DEBUG_MODE
correct_count = wrong_count = 0
for data in questions:
addition_env.reset()
run_npi(addition_env, npi_runner, program_set.ADD, data)
result_logger.write(data)
terminal.add_log(data)
if data["correct"]:
correct_count += 1
else:
wrong_count += 1
return correct_count, wrong_count
def main(stdscr, model_path: str, num: int, result_logger: ResultLogger):
terminal = Terminal(stdscr, create_char_map())
terminal.init_window(FIELD_WIDTH, FIELD_ROW)
program_set = AdditionProgramSet()
addition_env = AdditionEnv(FIELD_ROW, FIELD_WIDTH, FIELD_DEPTH)
questions = create_questions(num)
if DEBUG_MODE:
questions = questions[-num:]
system = RuntimeSystem(terminal=terminal)
npi_model = AdditionNPIModel(system, model_path, program_set)
npi_runner = TerminalNPIRunner(terminal, npi_model, recording=False)
npi_runner.verbose = DEBUG_MODE
correct_count = wrong_count = 0
for data in questions:
addition_env.reset()
run_npi(addition_env, npi_runner, program_set.ADD, data)
result_logger.write(data)
terminal.add_log(data)
if data['correct']:
correct_count += 1
else:
wrong_count += 1
return correct_count, wrong_count
def test_to_subset(self, questions):
addition_env = AdditionEnv(FIELD_ROW, FIELD_WIDTH, FIELD_DEPTH)
teacher = AdditionTeacher(self.program_set)
npi_runner = TerminalNPIRunner(None, self)
teacher_runner = TerminalNPIRunner(None, teacher)
correct_count = wrong_count = 0
wrong_steps_list = []
for idx, question in enumerate(questions):
question = copy(question)
if self.question_test(addition_env, npi_runner, question):
correct_count += 1
else:
self.question_test(addition_env, teacher_runner, question)
wrong_steps_list.append({
"q": question,
"steps": teacher_runner.step_list
})
wrong_count += 1
return correct_count, wrong_count, wrong_steps_list
def do_learn(self, steps_list, epoch, pass_rate=1.0, skip_correct=False):
addition_env = AdditionEnv(FIELD_ROW, FIELD_WIDTH, FIELD_DEPTH)
npi_runner = TerminalNPIRunner(None, self)
last_weights = None
correct_count = Counter()
no_change_count = 0
last_loss = 1000
for ep in range(1, epoch + 1):
correct_new = wrong_new = 0
losses = []
ok_rate = []
np.random.shuffle(steps_list)
for idx, steps_dict in enumerate(steps_list):
question = copy(steps_dict['q'])
question_key = self.dict_to_str(question)
if self.question_test(addition_env, npi_runner, question):
if correct_count[question_key] == 0:
correct_new += 1
correct_count[question_key] += 1
print("GOOD!: ep=%2d idx=%3d :%s CorrectCount=%s" %
(ep, idx, self.dict_to_str(question),
correct_count[question_key]))
ok_rate.append(1)
cc = correct_count[question_key]
if skip_correct or int(math.sqrt(cc))**2 != cc:
continue
else:
ok_rate.append(0)
if correct_count[question_key] > 0:
print(
"Degraded: ep=%2d idx=%3d :%s CorrectCount=%s -> 0"
% (ep, idx, self.dict_to_str(question),
correct_count[question_key]))
correct_count[question_key] = 0
wrong_new += 1
steps = steps_dict['steps']
xs = []
ys = []
ws = []
for step in steps:
xs.append(self.convert_input(step.input))
y, w = self.convert_output(step.output)
ys.append(y)
ws.append(w)
self.reset()
for i, (x, y, w) in enumerate(zip(xs, ys, ws)):
loss = self.model.train_on_batch(x, y, sample_weight=w)
if not np.isfinite(loss):
print("Loss is not finite!, Last Input=%s" %
([i, (x, y, w)]))
self.print_weights(last_weights, detail=True)
raise RuntimeError("Loss is not finite!")
losses.append(loss)
last_weights = self.model.get_weights()
if losses:
cur_loss = np.average(losses)
print(
"ep=%2d: ok_rate=%.2f%% (+%s -%s): ave loss %s (%s samples)"
% (ep, np.average(ok_rate) * 100, correct_new, wrong_new,
cur_loss, len(steps_list)))
# self.print_weights()
if correct_new + wrong_new == 0:
no_change_count += 1
else:
no_change_count = 0
if math.fabs(1 - cur_loss /
last_loss) < 0.001 and no_change_count > 5:
print(
"math.fabs(1 - cur_loss/last_loss) < 0.001 and no_change_count > 5:"
)
return False
last_loss = cur_loss
print("=" * 80)
self.save()
if np.average(ok_rate) >= pass_rate:
return True
return False