def auto_encoder():
if not osp.exists(osp.join(get_model_save_base(), 'feat_dim_120.pkl')):
print("Cannot Find {}".format(
osp.join(get_model_save_base(), 'feat_dim_120.pkl')))
x_train, x_test, y_train, y_test = train_test_split(feat_all,
feat_all,
test_size=0.2,
random_state=42)
encoding_dim = 120
input_ = Input(shape=(8051, ))
encoded = Dense(encoding_dim, activation='relu')(input_)
decoded = Dense(8051, activation='sigmoid')(encoded)
autoencoder = Model(input=input_, output=decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
autoencoder.fit(x_train,
x_train,
nb_epoch=500,
batch_size=10,
shuffle=True,
validation_data=(x_test, x_test))
# 根据上面我们训练的自编码器，截取其中编码部分定义为编码模型
encoder = Model(input=input_, output=encoded)
# 对特征进行编码降维
feat_dim_120 = encoder.predict(feat_all)
with open(osp.join(get_model_save_base(), 'feat_dim_120.pkl'),
'wb') as f:
pickle.dump(feat_dim_120, f)
else:
print("Find {}".format(
osp.join(get_model_save_base(), 'feat_dim_120.pkl')))
with open(osp.join(get_model_save_base(), 'feat_dim_120.pkl'),
'rb') as f:
feat_dim_120 = pickle.load(f)
return feat_dim_120
concatlayer = ConcatLayer()
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'mnist')
model_save_dir = osp.join(get_model_save_base(), 'mnist')
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
stop_by_test=True,
n_classes=10,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir)
model = Graph()
model.add(mgs)
model.add(pool)
model.add(concatlayer)
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
print('x_train shape: {}'.format(x_train.shape))
print('x_test.shape: {}'.format(x_test.shape))
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'uci_yeast')
model_save_dir = osp.join(get_model_save_base(), 'uci_yeast')
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
n_classes=10,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir,
distribute=False,
seed=0)
model = Graph()
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
print("time cost: {}".format(time.time() - start_time))
concatlayer = ConcatLayer()
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'fashion_mnist')
model_save_dir = osp.join(get_model_save_base(), 'fashion_mnist')
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
stop_by_test=True,
n_classes=10,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir)
model = Graph()
model.add(mgs)
model.add(pool)
model.add(concatlayer)
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
start_time = time.time()
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'uci_iris')
model_save_dir = osp.join(get_model_save_base(), 'uci_iris')
auto_cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
n_classes=3,
stop_by_test=False,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir,
distribute=False,
dis_level=0,
verbose_dis=False,
seed=0)
model = Graph()
model.add(auto_cascade)
model.fit_transform(x_train, y_train, x_test, y_test)
rf1 = ExtraRandomForestConfig(n_folds=3,
n_jobs=-1,
min_samples_leaf=10,
max_features='auto')
rf2 = RandomForestConfig(n_folds=3, n_jobs=-1, min_samples_leaf=10)
windows = [
Window(win_x=8, win_y=8, stride_x=2, stride_y=2, pad_x=0, pad_y=0),
Window(11, 11, 2, 2),
Window(16, 16, 2, 2)
]
est_for_windows = [[rf1, rf2], [rf1, rf2], [rf1, rf2]]
data_save_dir = osp.join(get_data_save_base(), 'cifar10')
model_save_dir = osp.join(get_model_save_base(), 'cifar10')
mgs = MultiGrainScanLayer(windows=windows,
est_for_windows=est_for_windows,
n_class=10,
distribute=False,
dis_level=0,
keep_in_mem=False,
data_save_dir=data_save_dir,
cache_in_disk=False,
seed=0)
pools = [[MeanPooling(2, 2), MeanPooling(2, 2)],
[MeanPooling(2, 2), MeanPooling(2, 2)],
[MeanPooling(2, 2), MeanPooling(2, 2)]]
print('x_train.shape', x_train.shape, x_train.dtype)
print('x_test.shape', x_test.shape, x_test.dtype)
est_configs = [
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
ExtraRandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig(),
RandomForestConfig()
]
data_save_dir = osp.join(get_data_save_base(), 'imdb')
model_save_dir = osp.join(get_model_save_base(), 'imdb')
cascade = AutoGrowingCascadeLayer(est_configs=est_configs,
early_stopping_rounds=4,
stop_by_test=True,
n_classes=2,
data_save_dir=data_save_dir,
model_save_dir=model_save_dir,
distribute=True,
dis_level=0,
seed=0)
cascade.fit_transform(x_train, y_train, x_test, y_test)
print("Time cost: {}".format(time.time() - start_time))
print('train shape and plus shape', x_train.shape, x_train_plus.shape)
print('test shape and plus shape', x_test.shape, x_test_plus.shape)
rf1 = ExtraRandomForestConfig(n_folds=3, n_jobs=-1, min_samples_leaf=10, max_features='auto')
rf2 = RandomForestConfig(n_folds=3, n_jobs=-1, min_samples_leaf=10)
windows = [Window(win_x=24, win_y=24, stride_x=2, stride_y=2, pad_x=0, pad_y=0),
Window(34, 34, 2, 2),
Window(48, 48, 2, 2)]
est_for_windows = [[rf1, rf2],
[rf1, rf2],
[rf1, rf2]]
data_save_dir = osp.join(get_data_save_base(), 'small_norb')
model_save_dir = osp.join(get_model_save_base(), 'small_norb')
mgs = MultiGrainScanLayer(windows=windows,
est_for_windows=est_for_windows,
n_class=10,
distribute=False,
keep_in_mem=False,
data_save_dir=data_save_dir,
cache_in_disk=True,
seed=0)
model = Graph()
model.add(mgs)
# model.add(pool)
# model.add(concatlayer)
# model.add(auto_cascade)