sys.path.append(os.path.join(Path(os.getcwd()).parent, 'lib'))
from layers import SoftmaxWithLoss
from common import softmax
import twolayernet as network
except ImportError:
print('Library Module Can Not Found')
# 1. load training/test data
_x, _t = np.array([2.6, 3.9, 5.6]), np.array([0, 0, 1])
# 2. hyperparameter
# 3. initialize layer
layer = SoftmaxWithLoss()
# Test
loss = layer.forward(_x, _t)
dout = layer.backward(1)
print(loss, dout)
# ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
def forward_propagation(x):
y = softmax(x)
return y
network.forward_progation = forward_propagation
loss = network.loss(_x, _t)
print(loss)
# 4-1. fetch mini-batch
batch_mask = np.random.choice(sztrain, szbatch)
train_x_batch = train_x[batch_mask] # 100 x 784
train_t_batch = train_t[batch_mask] # 100 x 10
# 4-2 gradient
stime = time.time() # stopwatch: start
gradient = network.numerical_gradient_net(train_x_batch, train_t_batch)
elapsed = time.time() - stime # stopwatch: end
# 4-3. update parameter
for key in network.params:
network.params[key] -= ratelearning * gradient[key]
# 4-4. train loss
loss = network.loss(train_x_batch, train_t_batch)
train_losses.append(loss)
# 4-5. accuracy per epoch
if idx / szepoch == 0:
train_accuracy = network.accuracy(train_x, train_t)
train_accuracies.append(train_accuracy)
test_accuracy = network.accuracy(test_x, test_t)
test_accuracies.append(test_accuracy)
print(f'#{idx}: loss:{loss}, elapsed time: {elapsed}s')
#5. serialization
now = datetime.datetime.now()
