weight_init_types = {'std=0.01': 0.01, 'Xavier': 'sigmoid', 'He': 'relu'}
optimizer = SGD(lr=0.01)
networks = {}
train_loss = {}
for key, weight_type in weight_init_types.items():
networks[key] = MultiLayerNet(input_size=784,
hidden_size_list=[100, 100, 100, 100],
output_size=10,
weight_init_std=weight_type)
train_loss[key] = []
# 2:訓練の開始==========
for i in range(max_iterations):
x_batch, t_batch = get_one_batch(train_x,
train_y,
batch_size=batch_size)
for key in weight_init_types.keys():
grads = networks[key].gradient(x_batch, t_batch)
optimizer.update(networks[key].params, grads)
loss = networks[key].loss(x_batch, t_batch)
train_loss[key].append(loss)
if i % 100 == 0:
print("===========" + "iteration:" + str(i) + "===========")
for key in weight_init_types.keys():
loss = networks[key].loss(x_batch, t_batch)
print(key + ":" + str(loss))
# ax.hist(data_non_zero, bins=bins_range, range=ran)
# if idx != 0:
# plt.yticks([], [])
plt.tight_layout()
plt.show()
if __name__ == '__main__':
mnist = MNIST('datasets\\mnist')
train_x, train_y, test_x, test_y = mnist.load(normalize=True,
image_flat=True,
label_one_hot=False)
# show sample images
sample_train_x, sample_train_y = get_one_batch(train_x,
train_y,
batch_size=5)
# show_imgs(sample_train_x.reshape(-1, 28, 28), sample_train_y)
learning_rate = 0.05
train_acc_list = []
test_acc_list = []
train_loss_list = []
test_loss_list = []
network = TwoLayerNet(input_size=28 * 28, hidden_size=50, output_size=10)
# print(network.params["W1"][0])
# show(network.params)
epoch = 200
# train & evaluate
for i in range(2000):
},
pool_param_2={
'pool_h': 2,
'pool_stride': 2
},
hidden_size_1=120,
hidden_size_2=84,
output_size=10,
weight_init_std=0.01)
# for layer in network.layers.values():
# print(layer)
# print(network.lossLayer)
# print('****** Print structure without values: OK ******')
train_x_batch, train_y_batch = get_one_batch(train_x,
train_y,
batch_size=10)
show_structure(network, train_x_batch, train_y_batch)
op = optimizer.Adam(lr=0.001)
epoch = 100
for i in range(5000):
train_x_batch, train_y_batch = get_one_batch(train_x,
train_y,
batch_size=30)
grads = network.gradient(train_x_batch, train_y_batch)
try:
op.update(network.params, grads)
except ZeroDivisionError as e:
print('Handling run-time error:', e)
