x_batch = x_train_std[batch_mask]
t_batch = y_train[batch_mask]
#quit()
# 勾配の計算
grad = network.gradient(x_batch, t_batch)
# パラメータの更新
for key in ('W1', 'b1', 'W2', 'b2'):
network.params[key] -= learning_rate * grad[key]
loss = network.loss(x_batch, t_batch)
train_loss_list.append(loss)
if i % iter_per_epoch == 0:
train_acc = network.accuracy(x_train, y_train)
# test_acc = network.accuracy(x_test, y_test)
test_acc = 0
train_acc_list.append(train_acc)
test_acc_list.append(test_acc)
print("i=" + str(i) + ", train acc, test acc | " + str(train_acc) +
", " + str(test_acc) + " , loss=" + str(loss))
print('time : ', time.time() - global_start_time)
#pred
#train_acc = network.accuracy(x_train, y_train)
#test_acc = network.accuracy(x_test, y_test)
#
print("train acc, test acc | " + str(train_acc) + ", " + str(test_acc) +
" , loss=" + str(loss))
print('time : ', time.time() - global_start_time)
#
x_batch = x_train[batch_mask]
t_batch = y_train[batch_mask]
#quit()
# 勾配の計算
grad = network.gradient(x_batch, t_batch)
# パラメータの更新
for key in ('W1', 'b1', 'W2', 'b2'):
network.params[key] -= learning_rate * grad[key]
loss = network.loss(x_batch, t_batch)
train_loss_list.append(loss)
if i % iter_per_epoch == 0:
train_acc = network.accuracy(x_train, y_train)
test_acc = network.accuracy(x_test, y_test)
# test_acc = 0
train_acc_list.append(train_acc)
test_acc_list.append(test_acc)
print("i=" + str(i) + ", train acc, test acc | " + str(train_acc) +
", " + str(test_acc) + " , loss=" + str(loss))
print('time : ', time.time() - global_start_time)
#pred
train_acc = network.accuracy(x_train, y_train)
test_acc = network.accuracy(x_test, y_test)
#
print("train acc, test acc | " + str(train_acc) + ", " + str(test_acc) +
" , loss=" + str(loss))
print('time : ', time.time() - global_start_time)
#
(x_train, t_train), (x_test, t_test) = mnist.load_data()
t_train_one_hot = one_hot(t_train)
t_test_one_hot = one_hot(t_test)
x_train_reshape = x_train.reshape(60000, 784)
x_test_reshape = x_test.reshape(10000, 784) # 将之转化为我想要的数据格式
train_loss_list = []
iters_num = 10000
train_size = x_train.shape[0]
batch_size = 100
rate = 0.1
network = SimpleNet(input_size=784, hidden_size=50, output_size=10)
for i in range(iters_num):
batch_mask = np.random.choice(train_size, batch_size)
x_batch = x_train_reshape[batch_mask] # little bracket is using function
t_batch = t_train_one_hot[batch_mask] # 在样本中随机选择一小撮
grads = network.numerical_gradient(x_batch, t_batch)
for key in ('w1', 'b1', 'w2', 'b2'):
network.param[key] -= rate * grads[key] # 对参数进行了调整,发现梯度值太小
loss = network.loss_function(x_batch, t_batch)
print(loss)
train_loss_list.append(loss)
print(network.accuracy(x_batch, t_batch)) # 是随机概率，根本就没有提高
y = np.array(train_loss_list)
x = np.array(range(len(train_loss_list)))
plot.plot(x, y)
plot.show()