Wil*_*son 5 python keras tensorflow
我收到 ValueError 错误：函数的输入张量必须来自tf.keras.Input。已收到：0（缺少上一层元数据），我找不到原因
这是我的错误跟踪和我的代码
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-15-8058f3a2fd50> in <module>()
6 test_loss, test_accuracy = eg.test(dg.user_test)
7 print('Test set: Loss=%.4f ; Accuracy=%.1f%%' % (test_loss, test_accuracy * 100))
----> 8 eg.save_embeddings('embeddings.csv')
7 frames
<ipython-input-5-54ff9897b1c3> in save_embeddings(self, file_name)
66 inp = self.m.input # input placeholder
67 outputs = [layer.output for layer in self.m.layers] # all layer outputs
---> 68 functor = K.function([inp, K.learning_phase()], outputs ) # evaluation function
69
70 #append embeddings to vectors
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py in function(inputs, outputs, updates, name, **kwargs)
3934 from tensorflow.python.keras import models # pylint: disable=g-import-not-at-top
3935 from tensorflow.python.keras.utils import tf_utils # pylint: disable=g-import-not-at-top
-> 3936 model = models.Model(inputs=inputs, outputs=outputs)
3937
3938 wrap_outputs = isinstance(outputs, list) and len(outputs) == 1
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in __new__(cls, *args, **kwargs)
240 # Functional model
241 from tensorflow.python.keras.engine import functional # pylint: disable=g-import-not-at-top
--> 242 return functional.Functional(*args, **kwargs)
243 else:
244 return super(Model, cls).__new__(cls, *args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
455 self._self_setattr_tracking = False # pylint: disable=protected-access
456 try:
--> 457 result = method(self, *args, **kwargs)
458 finally:
459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py in __init__(self, inputs, outputs, name, trainable)
113 # 'arguments during initialization. Got an unexpected argument:')
114 super(Functional, self).__init__(name=name, trainable=trainable)
--> 115 self._init_graph_network(inputs, outputs)
116
117 @trackable.no_automatic_dependency_tracking
/usr/local/lib/python3.6/dist-packages/tensorflow/python/training/tracking/base.py in _method_wrapper(self, *args, **kwargs)
455 self._self_setattr_tracking = False # pylint: disable=protected-access
456 try:
--> 457 result = method(self, *args, **kwargs)
458 finally:
459 self._self_setattr_tracking = previous_value # pylint: disable=protected-access
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py in _init_graph_network(self, inputs, outputs)
142 base_layer_utils.create_keras_history(self._nested_outputs)
143
--> 144 self._validate_graph_inputs_and_outputs()
145
146 # A Network does not create weights of its own, thus it is already
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/functional.py in _validate_graph_inputs_and_outputs(self)
637 'must come from `tf.keras.Input`. '
638 'Received: ' + str(x) +
--> 639 ' (missing previous layer metadata).')
640 # Check that x is an input tensor.
641 # pylint: disable=protected-access
ValueError: Input tensors to a Functional must come from `tf.keras.Input`. Received: 0 (missing previous layer metadata).
这是我的代码片段：
class EmbeddingsGenerator:
def __init__(self, train_users, data):
self.train_users = train_users
#preprocess
self.data = data.sort_values(by=['timestamp'])
#make them start at 0
self.data['userId'] = self.data['userId'] - 1
self.data['itemId'] = self.data['itemId'] - 1
self.user_count = self.data['userId'].max() + 1
self.movie_count = self.data['itemId'].max() + 1
self.user_movies = {} #list of rated movies by each user
for userId in range(self.user_count):
self.user_movies[userId] = self.data[self.data.userId == userId]['itemId'].tolist()
self.m = self.model()
def model(self, hidden_layer_size=100):
m = Sequential()
m.add(Dense(hidden_layer_size, input_shape=(1, self.movie_count)))
m.add(Dropout(0.2))
m.add(Dense(self.movie_count, activation='softmax'))
m.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
return m
def generate_input(self, user_id):
'''
Returns a context and a target for the user_id
context: user's history with one random movie removed
target: id of random removed movie
'''
user_movies_count = len(self.user_movies[user_id])
#picking random movie
random_index = np.random.randint(0, user_movies_count-1) # -1 avoids taking the last movie
#setting target
target = np.zeros((1, self.movie_count))
target[0][self.user_movies[user_id][random_index]] = 1
#setting context
context = np.zeros((1, self.movie_count))
context[0][self.user_movies[user_id][:random_index] + self.user_movies[user_id][random_index+1:]] = 1
return context, target
def train(self, nb_epochs = 300, batch_size = 10000):
'''
Trains the model from train_users's history
'''
for i in range(nb_epochs):
print('%d/%d' % (i+1, nb_epochs))
batch = [self.generate_input(user_id=np.random.choice(self.train_users) - 1) for _ in range(batch_size)]
X_train = np.array([b[0] for b in batch])
y_train = np.array([b[1] for b in batch])
self.m.fit(X_train, y_train, epochs=1, validation_split=0.5)
def test(self, test_users, batch_size = 100000):
'''
Returns [loss, accuracy] on the test set
'''
batch_test = [self.generate_input(user_id=np.random.choice(test_users) - 1) for _ in range(batch_size)]
X_test = np.array([b[0] for b in batch_test])
y_test = np.array([b[1] for b in batch_test])
return self.m.evaluate(X_test, y_test)
def save_embeddings(self, file_name):
'''
Generates a csv file containg the vector embedding for each movie.
'''
inp = self.m.input # input placeholder
outputs = [layer.output for layer in self.m.layers] # all layer outputs
functor = K.function([inp, K.learning_phase()], outputs ) # evaluation function
#append embeddings to vectors
vectors = []
for movie_id in range(self.movie_count):
movie = np.zeros((1, 1, self.movie_count))
movie[0][0][movie_id] = 1
layer_outs = functor([movie])
vector = [str(v) for v in layer_outs[0][0][0]]
vector = '|'.join(vector)
vectors.append([movie_id, vector])
#saves as a csv file
embeddings = pd.DataFrame(vectors, columns=['item_id', 'vectors']).astype({'item_id': 'int32'})
embeddings.to_csv(file_name, sep=';', index=False)
files.download(file_name)
这是调用 save_embeddings 方法的代码部分
if True: # Generate embeddings?
eg = EmbeddingsGenerator(dg.user_train, pd.read_csv('ml-100k/u.data', sep='\t', names=['userId', 'itemId', 'rating', 'timestamp']))
eg.train(nb_epochs=300)
train_loss, train_accuracy = eg.test(dg.user_train)
print('Train set: Loss=%.4f ; Accuracy=%.1f%%' % (train_loss, train_accuracy * 100))
test_loss, test_accuracy = eg.test(dg.user_test)
print('Test set: Loss=%.4f ; Accuracy=%.1f%%' % (test_loss, test_accuracy * 100))
eg.save_embeddings('embeddings.csv')