DECAY = np.random.random_sample([number_of_exp])
DECAY = np.append(DECAY, 0.96)
number_of_exp += 1
DECAY.sort()
results = []
duration = []
info = []
for i, de in enumerate(DECAY):
print("\n ({0} of {1})".format(i + 1, number_of_exp))
my_config = Config(tunning=True, decay_rate=de)
attrs = vars(my_config)
config_info = ["%s: %s" % item for item in attrs.items()]
info.append(config_info)
my_model = CNNModel(my_config, my_dataholder)
train_model(my_model, my_dataholder, 10001, 1000, False)
current_dur = get_time(train_model, 10001)
score = check_valid(my_model)
results.append(score)
duration.append(current_dur)
DECAY = list(DECAY)
best_result = max(list(zip(results, DECAY, duration, info)))
result_string = """In an experiment with {0} decay rate values
the best one is {1} with valid accuracy = {2}.
\nThe training takes {3:.2f} seconds using the following params:
\n{4}""".format(number_of_exp,
best_result[1],
best_result[0],
best_result[2],
best_result[3])
DP = np.random.random_sample([number_of_exp])
DP = np.append(DP, 0.99)
number_of_exp += 1
DP.sort()
results = []
duration = []
info = []
for i, dro in enumerate(DP):
print("\n ({0} of {1})".format(i + 1, number_of_exp))
my_config = Config(tunning=True, dropout=dro)
attrs = vars(my_config)
config_info = ["%s: %s" % item for item in attrs.items()]
info.append(config_info)
my_model = CNNModel(my_config, my_dataholder)
train_model(my_model, my_dataholder, 3, 2, False)
current_dur = get_time(train_model, 3)
score = check_valid(my_model)
results.append(score)
duration.append(current_dur)
DP = list(DP)
best_result = max(list(zip(results, DP, duration, info)))
result_string = """In an experiment with {0} dropout values
the best one is {1} with valid accuracy = {2}.
\nThe training takes {3:.2f} seconds using the following params:
\n{4}""".format(number_of_exp, best_result[1], best_result[0], best_result[2],
best_result[3])
file = open("dropout.txt", "w")
file.write(result_string)