def test_load_empty_memory(self):
current_path = os.path.dirname(os.path.abspath(__file__))
checkpoint_path = os.path.join(current_path, 'test_checkpoint_empty')
model = load_trained_model_from_checkpoint(
config_path=os.path.join(checkpoint_path, 'xlnet_config.json'),
checkpoint_path=os.path.join(checkpoint_path, 'xlnet_model.ckpt'),
batch_size=2,
memory_len=5,
target_len=5,
in_train_phase=False,
mask_index=0,
attention_type=ATTENTION_TYPE_UNI,
)
set_custom_objects()
model_path = os.path.join(tempfile.gettempdir(),
'test_xlnet_%f.h5' % np.random.random())
model.save(model_path)
model = keras.models.load_model(model_path)
model.summary()
def _load_numpy(name):
return np.load(os.path.join(checkpoint_path, name + '.npy'))
input_ids = _load_numpy('input_ids')
seg_ids = _load_numpy('seg_ids')
tune_output = _load_numpy('empty_output')
inputs = [input_ids, seg_ids, np.zeros((2, 1))]
output = model.predict_on_batch(inputs)
self.assertTrue(np.allclose(tune_output, output, atol=1e-6))
def test_build_not_training(self):
model = build_xlnet(
units=6,
training=False,
num_token=31,
num_block=2,
num_head=2,
hidden_dim=12,
batch_size=2,
memory_len=5,
target_len=5,
dropout=0.1,
attention_dropout=0.1,
attention_type=ATTENTION_TYPE_BI,
)
set_custom_objects()
model_path = os.path.join(tempfile.gettempdir(),
'test_xlnet_%f.h5' % np.random.random())
model.save(model_path)
model = keras.models.load_model(model_path)
model.summary()
try:
current_path = os.path.dirname(os.path.abspath(__file__))
visual_path = os.path.join(current_path,
'test_build_not_training.jpg')
keras.utils.vis_utils.plot_model(model,
visual_path,
show_shapes=True)
except Exception as e:
pass
def test_load_training(self):
current_path = os.path.dirname(os.path.abspath(__file__))
checkpoint_path = os.path.join(current_path, 'test_checkpoint_pre')
model = load_trained_model_from_checkpoint(
config_path=os.path.join(checkpoint_path, 'xlnet_config.json'),
checkpoint_path=os.path.join(checkpoint_path, 'xlnet_model.ckpt'),
batch_size=2,
memory_len=5,
target_len=5,
in_train_phase=True,
mask_index=0,
attention_type=ATTENTION_TYPE_UNI,
)
set_custom_objects()
model_path = os.path.join(tempfile.gettempdir(),
'test_xlnet_%f.h5' % np.random.random())
model.save(model_path)
model = keras.models.load_model(model_path)
model.summary()
def _load_numpy(name):
return np.load(os.path.join(checkpoint_path, name + '.npy'))
input_ids = _load_numpy('input_ids')
seg_ids = _load_numpy('seg_ids')
input_mask = _load_numpy('input_mask')
mems_0 = _load_numpy('mems_0')
mems_1 = _load_numpy('mems_1')
pre_output = _load_numpy('pre_output')
pre_new_mems_0 = _load_numpy('pre_new_mems_0')
pre_new_mems_1 = _load_numpy('pre_new_mems_1')
inputs = [input_ids, seg_ids, np.ones((2, 1)) * 5, input_mask]
self._update_memory(model, 'Memory-0', mems_0)
self._update_memory(model, 'Memory-1', mems_1)
output = model.predict_on_batch(inputs)
self.assertTrue(
np.allclose(pre_new_mems_0,
self._get_memory(model, 'Memory-0', 5),
atol=1e-6))
self.assertTrue(
np.allclose(pre_new_mems_1,
self._get_memory(model, 'Memory-1', 5),
atol=1e-6))
self.assertTrue(np.allclose(pre_output, output, atol=1e-6))
def build(self):
from keras_xlnet import load_trained_model_from_checkpoint, set_custom_objects
from keras_xlnet import Tokenizer, ATTENTION_TYPE_BI, ATTENTION_TYPE_UNI
self.embedding_type = 'xlnet'
self.checkpoint_path = os.path.join(self.corpus_path,
'xlnet_model.ckpt')
self.config_path = os.path.join(self.corpus_path, 'xlnet_config.json')
self.spiece_model = os.path.join(self.corpus_path, 'spiece.model')
self.attention_type = self.xlnet_embed.get('attention_type',
'bi') # or 'uni'
self.attention_type = ATTENTION_TYPE_BI if self.attention_type == 'bi' else ATTENTION_TYPE_UNI
self.memory_len = self.xlnet_embed.get('memory_len', 0)
self.target_len = self.xlnet_embed.get('target_len', 5)
print('load xlnet model start!')
# 模型加载
model = load_trained_model_from_checkpoint(
checkpoint_path=self.checkpoint_path,
attention_type=self.attention_type,
in_train_phase=self.trainable,
config_path=self.config_path,
memory_len=self.memory_len,
target_len=self.target_len,
batch_size=self.batch_size,
mask_index=0)
#
set_custom_objects()
# 字典加载
self.tokenizer = Tokenizer(self.spiece_model)
# debug时候查看layers
self.model_layers = model.layers
len_layers = self.model_layers.__len__()
print(len_layers)
layer_real = [i for i in range(25)] + [-i for i in range(25)]
# 简要判别一下
self.layer_indexes = [
i if i in layer_real else -2 for i in self.layer_indexes
]
len_couche = int((len_layers - 6) / 10)
# 一共246个layer
# 每层10个layer（MultiHeadAttention,Dropout,Add,LayerNormalization）,第一是9个layer的输入和embedding层
# 一共24层
layer_dict = []
layer_0 = 7
for i in range(len_couche):
layer_0 = layer_0 + 10
layer_dict.append(layer_0)
layer_dict.append(247)
# 测试 get_output_at
# def get_number(index):
# try:
# model_node = model.get_output_at(node_index=index)
# gg = 0
# except:
# print('node index wrong!')
# print(index)
# list_index = [i for i in range(25)] + [-i for i in range(25)]
# for li in list_index:
# get_number(li)
# 输出它本身
if len(self.layer_indexes) == 0:
encoder_layer = model.output
# 分类如果只有一层，取得不正确的话就取倒数第二层
elif len(self.layer_indexes) == 1:
if self.layer_indexes[0] in layer_real:
encoder_layer = model.get_layer(
index=layer_dict[self.layer_indexes[0]]).get_output_at(
node_index=0)
else:
encoder_layer = model.get_layer(
index=layer_dict[-1]).get_output_at(node_index=0)
# 否则遍历需要取的层，把所有层的weight取出来并加起来shape:768*层数
else:
# layer_indexes must be [0, 1, 2,3,......24]
all_layers = [
model.get_layer(index=layer_dict[lay]).get_output_at(
node_index=0) if lay in layer_real else model.get_layer(
index=layer_dict[-1]).get_output_at(
node_index=0) # 如果给出不正确，就默认输出倒数第一层
for lay in self.layer_indexes
]
print(self.layer_indexes)
print(all_layers)
all_layers_select = []
for all_layers_one in all_layers:
all_layers_select.append(all_layers_one)
encoder_layer = Add()(all_layers_select)
print(encoder_layer.shape)
# def xlnet_concat(x):
# x_concat = K.concatenate(x, axis=1)
# return x_concat
# encoder_layer = Lambda(xlnet_concat, name='xlnet_concat')(all_layers)
self.output = NonMaskingLayer()(encoder_layer)
self.input = model.inputs
self.model = Model(self.input, self.output)
print("load KerasXlnetEmbedding end")
model.summary(132)
self.embedding_size = self.model.output_shape[-1]
self.vocab_size = len(self.tokenizer.sp)
def build(self):
from keras_xlnet import load_trained_model_from_checkpoint, set_custom_objects
from keras_xlnet import Tokenizer, ATTENTION_TYPE_BI, ATTENTION_TYPE_UNI
self.embedding_type = 'xlnet'
self.checkpoint_path = os.path.join(self.corpus_path, 'xlnet_model.ckpt')
self.config_path = os.path.join(self.corpus_path, 'xlnet_config.json')
self.spiece_model = os.path.join(self.corpus_path, 'spiece.model')
self.attention_type = self.xlnet_embed.get('attention_type', 'bi') # or 'uni'
self.attention_type = ATTENTION_TYPE_BI if self.attention_type == 'bi' else ATTENTION_TYPE_UNI
self.memory_len = self.xlnet_embed.get('memory_len', 0)
self.target_len = self.xlnet_embed.get('target_len', 5)
print('load xlnet model start!')
# 模型加载
model = load_trained_model_from_checkpoint(checkpoint_path=self.checkpoint_path,
attention_type=self.attention_type,
in_train_phase=self.trainable,
config_path=self.config_path,
memory_len=self.memory_len,
target_len=self.target_len,
batch_size=self.batch_size,
mask_index=0)
#
set_custom_objects()
self.build_config(self.config_path)
# 字典加载
self.tokenizer = Tokenizer(self.spiece_model)
# # debug时候查看layers
# self.model_layers = model.layers
# len_layers = self.model_layers.__len__()
# print(len_layers)
num_hidden_layers = self.configs.get("n_layer", 12)
layer_real = [i for i in range(num_hidden_layers)] + [-i for i in range(num_hidden_layers)]
# 简要判别一下
self.layer_indexes = [i if i in layer_real else -2 for i in self.layer_indexes]
output_layer = "FeedForward-Normal-{0}"
layer_dict = [model.get_layer(output_layer.format(i + 1)).get_output_at(node_index=0)
for i in range(num_hidden_layers)]
# 输出它本身
if len(self.layer_indexes) == 0:
encoder_layer = model.output
# 分类如果只有一层，取得不正确的话就取倒数第二层
elif len(self.layer_indexes) == 1:
if self.layer_indexes[0] in layer_real:
encoder_layer = layer_dict[self.layer_indexes[0]]
else:
encoder_layer = layer_dict[-1]
# 否则遍历需要取的层，把所有层的weight取出来并加起来shape:768*层数
else:
# layer_indexes must be [0, 1, 2,3,......24]
all_layers = [layer_dict[lay] if lay in layer_real
else layer_dict[-1] # 如果给出不正确，就默认输出倒数第一层
for lay in self.layer_indexes]
print(self.layer_indexes)
print(all_layers)
all_layers_select = []
for all_layers_one in all_layers:
all_layers_select.append(all_layers_one)
encoder_layer = Add()(all_layers_select)
print(encoder_layer.shape)
# def xlnet_concat(x):
# x_concat = K.concatenate(x, axis=1)
# return x_concat
# encoder_layer = Lambda(xlnet_concat, name='xlnet_concat')(all_layers)
self.output = NonMaskingLayer()(encoder_layer)
self.input = model.inputs
self.model = Model(self.input, self.output)
print("load KerasXlnetEmbedding end")
model.summary(132)
self.embedding_size = self.model.output_shape[-1]
self.vocab_size = len(self.tokenizer.sp)