class CNN3_Model(ModelBase):
u"""see: http://aidiary.hatenablog.com/entry/20151007/1444223445"""
def __init__(self, input_size=32):
super(CNN3_Model, self).__init__()
# F.Convolution2D(in_channel, out_channel, filter_size)
self.model = FunctionSet( # 1*32*32 -(conv)-> 20*28*28 -(pool)-> 20*14*14
conv1=F.Convolution2D(1, 20, 5),
# 20*14*14 -(conv)-> 50*10*10 -(pool)-> 50*5*5=1250
conv2=F.Convolution2D(20, 50, 5),
l1=F.Linear(1250, 300),
l2=F.Linear(300, 2))
def forward(self, x_data, y_data, train=True):
u"""return loss, accuracy"""
x, t = Variable(x_data), Variable(y_data)
h1 = F.max_pooling_2d(F.relu(self.model.conv1(x)), 2)
h2 = F.max_pooling_2d(F.relu(self.model.conv2(h1)), 2)
h3 = F.dropout(F.relu(self.model.l1(h2)), train=train)
y = self.model.l2(h3)
# 多クラス分類なので誤差関数としてソフトマックス関数の
# 交差エントロピー関数を用いて、誤差を導出。最低でもlossは必要
return {
"loss": F.softmax_cross_entropy(y, t),
"accuracy": F.accuracy(y, t)
}
class CNN3_Model(ModelBase):
u"""see: http://aidiary.hatenablog.com/entry/20151007/1444223445"""
def __init__(self, input_size=32):
super(CNN3_Model, self).__init__()
# F.Convolution2D(in_channel, out_channel, filter_size)
self.model = FunctionSet( # 1*32*32 -(conv)-> 20*28*28 -(pool)-> 20*14*14
conv1=F.Convolution2D(1, 20, 5),
# 20*14*14 -(conv)-> 50*10*10 -(pool)-> 50*5*5=1250
conv2=F.Convolution2D(20, 50, 5),
l1=F.Linear(1250, 300),
l2=F.Linear(300, 2))
def forward(self, x_data, y_data, train=True):
u"""return loss, accuracy"""
x, t = Variable(x_data), Variable(y_data)
h1 = F.max_pooling_2d(F.relu(self.model.conv1(x)), 2)
h2 = F.max_pooling_2d(F.relu(self.model.conv2(h1)), 2)
h3 = F.dropout(F.relu(self.model.l1(h2)), train=train)
y = self.model.l2(h3)
# 多クラス分類なので誤差関数としてソフトマックス関数の
# 交差エントロピー関数を用いて、誤差を導出。最低でもlossは必要
return {
"loss": F.softmax_cross_entropy(y, t),
"accuracy": F.accuracy(y, t)
}
class DQN_CNN(object):
def __init__(self,n_act):
N_output = n_act
self.model = FunctionSet(
conv1=F.Convolution2D(1, 16, 3, pad=1),
conv2=F.Convolution2D(16, 16, 3, pad=1),
l1=F.Linear(256, 256),
l2=F.Linear(256, N_output))
def Q_func(self,x):
N,h,w=x.shape
x=x.reshape(N,1,h,w)
x = Variable(x)
h = F.relu(self.model.conv1(x))
h = F.max_pooling_2d(F.relu(self.model.conv2(h)), 2)
h = F.relu(self.model.l1(h))
y = self.model.l2(h)
return y
class CNN:
file_names = None
def __init__(self):
self.optimizer = optimizers.Adam()
self.model_name = "cnn_nantyara"
if os.path.exists(self.model_name):
self.load_model()
else:
self.crete_model()
self.optimizer.setup(self.model.collect_parameters())
def crete_model(self):
self.model = FunctionSet(
conv1=F.Convolution2D(3, 32, 3),
bn1=F.BatchNormalization(32),
conv2=F.Convolution2D(32, 64, 3, pad=1),
bn2=F.BatchNormalization(64),
conv3=F.Convolution2D(64, 64, 3, pad=1),
fl4=F.Linear(1024, 256),
fl5=F.Linear(256, 2),
)
def get_data(self, ifpath, image_categories, reshape_size=(3, 32, 32)):
x = []
x_apd = x.append
y = []
y_apd = y.append
for i_category, category in enumerate(image_categories):
for i_num in xrange(1, self.get_num_of_images(ifpath, category)):
image = np.array(Image.open(ifpath + "/" + category + str(i_num) + ".jpeg"), dtype=np.float32).reshape(
reshape_size
)
x_apd(image)
y_apd(i_category)
self.N = len(x)
return x, np.array(y, dtype=np.int32)
def get_data_for_predict(self, ifpath, image_name, reshape_size=(3, 32, 32)):
image = np.array(Image.open(ifpath + "/" + image_name), dtype=np.float32)
image = cv2.resize(image, (reshape_size[1], reshape_size[2]))
# print image.shape
image = image.reshape(reshape_size)
return [image]
def forward(self, x_data, y_data, train=True):
x, t = Variable(np.array(x_data)), Variable(y_data)
h1 = F.max_pooling_2d(F.relu(self.model.bn1(self.model.conv1(x))), 2)
h2 = F.max_pooling_2d(F.relu(self.model.bn2(self.model.conv2(h1))), 2)
h3 = F.max_pooling_2d(F.relu(self.model.conv3(h2)), 2)
h4 = F.dropout(F.relu(self.model.fl4(h3)), train=train)
y = self.model.fl5(h4)
if train:
return F.softmax_cross_entropy(y, t), F.accuracy(y, t)
else:
res = [d for data in F.softmax(y).data for d in data]
# print res
return np.array(res).argmax() if len([r for r in res if r > 0.5]) > 0 else "unknown"
def get_num_of_images(self, path, image_name):
cmd = "ls images|grep %s|wc -l" % (image_name)
return int(subprocess.check_output(cmd, shell=True))
def dump_model(self):
self.model.to_cpu()
with open(self.model_name, "wb") as f:
pickle.dump(self.model, f, -1)
def load_model(self):
with open(self.model_name, "rb") as f:
self.model = pickle.load(f)
def fit(self, x_train, y_train, epoch=20, batchsize=100):
for epoch in xrange(1, epoch + 1):
print "epoch", epoch
# training
sum_accuracy = 0
sum_loss = 0
for i in xrange(0, self.N, batchsize):
self.optimizer.zero_grads()
loss, acc = self.forward(x_train[i : i + batchsize], y_train[i : i + batchsize])
loss.backward()
self.optimizer.update()
print "train mean loss=%s, accuracy =%s" % (str(loss.data), str(acc.data))
self.dump_model()
def predict(self, x):
y = self.forward(x, np.zeros(1, dtype=np.int32), train=False)
sys.stdout.write(str(self.file_names[y]) if y != "unknonw" else "unknonw")
