Keras，顺序神经网络模型

Question

这是 Keras 模型的代码，它给出了类型错误

    model=keras.Sequential()
    model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
    model.add(Dropout(0,5))
 
    model.add(Dense(64, activation='relu'))
    model.add(Dropout(0,5))
 
    model.add(Dense(len(train_y[0]), activation='softmax'))
    sgd= SGD(lr=0.01, decay=1e-6, momentum=0.9,nesterov=True)
    model.compile(loss='categorical_crossentropy', optimizer= sgd, metrics= 
    ['accuracy'])
 
    model.fit(np.array(train_x),np.array(train_y),epochs=200,batch_size=5,
    verbose=1)
    model.save("chatbot.model")
    print("training is done")

here i 'm creating a chat bot using Keras Sequential Model and encountered 
the TypeError which shows on the Training the Neural Network,  exact on model.fit line

注意：意图是我以字典格式给出的消息，这是示例 {"intents":[{"tag": "welcome", "patterns":["Hi","Hello"],"responses":["Hello","Hi"]}

我已经导入了 nltk、nltk.stem-WordNetLemmatizer、numpy、pickle、random、tensorflow、keras、Keras.Model-Sequential、Keras.Layers-Dense、Activation 和 Dropout。 Keras.Optimizers-新元


    > TypeError: in user code: /usr/local/lib/python3.6/dist-
    > 
    > packages/tensorflow/python/keras/engine/training.py:805 train_function
    > * return step_function(self, iterator)  /usr/local/lib/python3.6/dist- 
     packages/tensorflow/python/keras/engine/training.py:795
    > step_function ** outputs = model.distribute_strategy.run(run_step,
    > args=(data,)) 
    > /usr/local/lib/python3.6/dist- 
    packages/tensorflow/python/distribute/distribute_lib.py:1259
    > 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:2730
    > 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:3417
    > _call_for_each_replica return fn(*args, **kwargs) 
    /usr/local/lib/python3.6/dist- 
    packages/tensorflow/python/keras/engine/training.py:788
    > run_step ** outputs = model.train_step(data)
    > /usr/local/lib/python3.6/dist- 
    packages/tensorflow/python/keras/engine/training.py:754
    > train_step y_pred = self(x, training=True) 
    > /usr/local/lib/python3.6/dist- 
    packages/tensorflow/python/keras/engine/base_layer.py:1012
    > __call__ outputs = call_fn(inputs, *args, **kwargs)  
    /usr/local/lib/python3.6/dist- 
    packages/tensorflow/python/keras/engine/sequential.py:375
    > call return super(Sequential, self).call(inputs, training=training,
    > mask=mask) 
     > /usr/local/lib/python3.6/dist- 
    packages/tensorflow/python/keras/engine/functional.py:425
    > call inputs, training=training, mask=mask)
    > /usr/local/lib/python3.6/dist- 
    packages/tensorflow/python/keras/engine/functional.py:560
    > _run_internal_graph outputs = node.layer(*args, **kwargs)  
    /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py:1012
> __call__ outputs = call_fn(inputs, *args, **kwargs)  /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/core.py:231
> call lambda: array_ops.identity(inputs)) 
> /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/utils/control_flow_util.py:115
> smart_cond pred, true_fn=true_fn, false_fn=false_fn, name=name) 
> /usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/smart_cond.py:54
> smart_cond return true_fn() 
> /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/core.py:226
> dropped_inputs noise_shape=self._get_noise_shape(inputs), 
> /usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/core.py:215
> _get_noise_shape for i, value in enumerate(self.noise_shape): 
> 
> TypeError: 'int' object is not iterable

Answer 1

我的建议是这些行是错误的：

model.add(Dropout(0.5)) # replace comma by dot

Answer 2

@Andrey 是正确的。还有其他一些小问题，但这是错误的原因。

这里是固定代码-

from tensorflow import keras
from tensorflow.keras.layers import Dense, Dropout 
from tensorflow.keras.optimizers import SGD
import numpy as np

train_x = np.random.random((100,8))
train_y = np.random.random((100,4))

model=keras.Sequential()
model.add(Dense(128, input_shape=(len(train_x[0]),), activation='relu'))
model.add(Dropout(0.5))

model.add(Dense(64, activation='relu'))
model.add(Dropout(0.5))

model.add(Dense(len(train_y[0]), activation='softmax'))
sgd= SGD(lr=0.01, decay=1e-6, momentum=0.9,nesterov=True)
model.compile(loss='categorical_crossentropy', optimizer= sgd, metrics= 
['accuracy'])

model.fit(np.array(train_x),np.array(train_y),epochs=3,batch_size=5,
verbose=1)
print("training is done")
print(model.summary())

Epoch 1/3
20/20 [==============================] - 0s 820us/step - loss: 2.6962 - accuracy: 0.0820
Epoch 2/3
20/20 [==============================] - 0s 807us/step - loss: 2.9444 - accuracy: 0.3395
Epoch 3/3
20/20 [==============================] - 0s 741us/step - loss: 336196611196720054272.0000 - accuracy: 0.2951

training is done

Model: "sequential_24"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
dense_66 (Dense)             (None, 128)               1152      
_________________________________________________________________
dropout_8 (Dropout)          (None, 128)               0         
_________________________________________________________________
dense_67 (Dense)             (None, 64)                8256      
_________________________________________________________________
dropout_9 (Dropout)          (None, 64)                0         
_________________________________________________________________
dense_68 (Dense)             (None, 4)                 260       
=================================================================
Total params: 9,668
Trainable params: 9,668
Non-trainable params: 0
_________________________________________________________________

Keras，顺序神经网络模型

Keras, Sequential Neural Network Model

typeerror

sequential

keras

tensorflow