def main2():
dnn = DNN(input=28 * 28,
layers=[DropoutLayer(160, LQ),
Layer(10, LCE)],
eta=0.05,
lmbda=1) # 98%
dnn.initialize_rand()
train, test, vadilation = load_mnist_simple()
f_names = [f'mnist_expaned_k0{i}.pkl.gz' for i in range(50)]
shuffle(f_names)
for f_name in f_names:
print(f_name)
with timing("load"):
raw_data = load_data(f_name)
with timing("shuffle"):
shuffle(raw_data)
with timing("reshape"):
data = [(x.reshape((784, 1)), y)
for x, y in islice(raw_data, 100000)]
del raw_data
with timing("learn"):
dnn.learn(data)
del data
print('TEST:', dnn.test(test))
def main():
train, test, vadilation = load_mnist_simple()
# x, y = train[0]
# print("x: ", x.shape)
# print("y: ", y)
with timing(f""):
# dnn = DNN(input=28 * 28, layers=[Layer(30, LQ), Layer(10, LCE)], eta=0.05) # 96%
# dnn = DNN(input=28 * 28, layers=[Layer(30, LQ), Layer(10, SM)], eta=0.001) # 68%
# dnn = DNN(input=28 * 28, layers=[Layer(100, LQ), Layer(10, LCE)], eta=0.05, lmbda=5) # 98%
# dnn = DNN(input=28 * 28, layers=[DropoutLayer(100, LQ), Layer(10, LCE)], eta=0.05) # 97.5%
dnn = DNN(input=28 * 28, layers=[DropoutLayer(160, LQ), Layer(10, LCE)], eta=0.05, lmbda=3)
dnn.initialize_rand()
dnn.learn(train, epochs=30, test=vadilation, batch_size=29)
print('test:', dnn.test(test))
print(dnn.stats())
512,
train=train_mode,
isnorm=True,
name='w_%s' % str(num),
graph=g,
scale=[0.1, 100, 100]) # 定义网络
memory_norm = net.norm(memory)
if train_mode != 0:
# 训练模式
X = memory_norm[:, 1:].copy()
Y = memory_norm[:, 0:1].copy()
losses = []
for i in range(5000):
sample_index = np.random.choice(len(X), size=1000)
batch_x = X[sample_index, :]
batch_y = Y[sample_index, :]
loss, mae = net.learn(batch_x, batch_y)
losses.append(loss)
print(i + 1, '预测平均误差是', mae)
plt.plot(losses)
net.store()
plt.show()
else:
# 测试模式
cav = AircraftEnv()
info = guidance(cav, net)
print(info['range_error'])
state_record, h_cmds = info['state_records'], info['hcmd_records']
cav.plot(state_record, h_cmds)
plt.show()
if train:
# 进行训练
# 通过x_old和x_new来计算出来x导数
# 然后利用神经网络来进行学习
for _ in range(5):
observation = env.reset()
my_observation = observation
mu = 0
for epi in range(20000):
u = env.action_space.sample()
my_observation, target = step_my(observation, u, net,mu)
observation, reward, done, info = env.step(u)
mu = get_mu(mu, observation, my_observation)
net.store_sample(observation, target)
if epi % 100 == 0:
result = net.learn()
if result:
print(epi, result)
net.store_net()
# 进行测试
# 画出三组对比图
observation = env.reset()
my_observation = observation
for epi in range(5000):
u = env.action_space.sample()
my_observation, d = step_my(observation, u, net)
observation, reward, done, info = env.step(u)
record_tru.append(observation)
record_pre.append(my_observation)
record_tru = np.array(record_tru)
