Question

我正在用python和keras做一个聊天机器人，所以我用keras创建了一个CNN模型，现在我想训练它。我创建了两个类，一个用于问候，另一个用于再见。当我运行代码进行训练时，由于形状引起了错误。

 Training Data Shape:  [[1. 1.]
 [1. 1.]]
Target Data Shape:  [1. 1.]
Number of classes:  2
Classes:  ['byes' 'greeting']
Epoch 1/100
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-8-95b45bf4ab5b> in <module>()
     78 #Call fns
     79 create_class()
---> 80 model()
     81 
     82 def chat():

11 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    971           except Exception as e:  # pylint:disable=broad-except
    972             if hasattr(e, "ag_error_metadata"):
--> 973               raise e.ag_error_metadata.to_exception(e)
    974             else:
    975               raise

ValueError: in user code:

    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:806 train_function  *
        return step_function(self, iterator)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:796 step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1211 run
        return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2585 call_for_each_replica
        return self._call_for_each_replica(fn, args, kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2945 _call_for_each_replica
        return fn(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:789 run_step  **
        outputs = model.train_step(data)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:749 train_step
        y, y_pred, sample_weight, regularization_losses=self.losses)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:204 __call__
        loss_value = loss_obj(y_t, y_p, sample_weight=sw)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:149 __call__
        losses = ag_call(y_true, y_pred)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:253 call  **
        return ag_fn(y_true, y_pred, **self._fn_kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1535 categorical_crossentropy
        return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
        return target(*args, **kwargs)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:4687 categorical_crossentropy
        target.shape.assert_is_compatible_with(output.shape)
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_shape.py:1134 assert_is_compatible_with
        raise ValueError("Shapes %s and %s are incompatible" % (self, other))

    ValueError: Shapes (None, 1) and (None, 2) are incompatible

以下是重现该错误的代码：

 #Create arrays
nn = [2, 4, 6, 8, 12, 10, 8, 2]
labels = []
words = []
docs_x = []
docs_y = []

with open("intents.json") as file:
    data = json.load(file)

for intent in data["intents"]:
    for pattern in intent["patterns"]:
          pattern = intent["tag"]
    for response in intent["responses"]:
          response = intent["responses"]
    for tags in intent["tag"]:
          tags = intent["tag"]

    #Add tags to labels[]
    if intent["tag"] not in labels:
      labels.append(intent["tag"])

    #Add patterns to docs_y[]
    if intent["patterns"] not in words:
      docs_y.append(intent["patterns"])

def create_class():
  y = np.array(labels)
  x = np.array(words)

  classes = np.unique(y)
  nClasses = len(classes)

  print("Number of classes: " , nClasses)
  print("Classes: " , classes)

def create_training_data():
  training_data = np.ones(np.shape(docs_y))
  target_data = np.ones(np.shape(labels))

  print("Training Data Shape: " , training_data)
  print("Target Data Shape: " , target_data)

#Create training shapes:
create_training_data()

def model():
  INIT_LR = 1e-3
  epochs = 6
  batch_size = 64

  model = kr.Sequential()

  model.add(kr.layers.Dense(nn[1], activation='relu'))
  model.add(kr.layers.Dense(nn[2], activation='relu'))
  model.add(kr.layers.Dense(nn[3], activation='relu'))
  model.add(kr.layers.Dense(nn[4], activation='relu'))
  model.add(kr.layers.Dense(nn[5], activation='relu'))
  model.add(kr.layers.Dense(nn[6], activation='relu'))
  model.add(kr.layers.Dense(nn[7], activation='sigmoid'))

  model.compile(loss=kr.losses.categorical_crossentropy, optimizer=kr.optimizers.Adagrad(lr=INIT_LR, decay=INIT_LR / 100),metrics=['accuracy'])

  #Training
  model.fit(training_data , target_data , epochs=100)

#Call fns
create_class()
model()

有人可以帮助我吗？

谢谢。

Answer 1

具有sigmoid激活的最后一个密集层（输出层）应仅具有1个神经元，而不是2个。您又有两个输出类。对于“正”类，尽管输出层仅需要是0-1之间的单个概率，但仍是二进制分类。另一个类别的概率就是一个减去该概率的概率。

因此，请尝试将model.add(kr.layers.Dense(nn[7], activation='sigmoid'))更改为model.add(kr.layers.Dense(1, activation='sigmoid'))。

ValueError：形状1和2不兼容

1 个答案: