TensorFlow 模型构建

Question

我正在创建一个基本的 Tensorflow 深度学习模型。 我的代码是：-

# Creating the data 
x = np.array(\[-7.0,-4.0,-1.0,2.0,5.0,8.0,11.0,14.0])
y = np.array(\[3.0,6.0,9.0,12.0,15.0,18.0,21.0,24.0])

## Turning the data into tensors
x = tf.cast(tf.constant(x ), dtype = tf.float32)
y = tf.cast(tf.constant(y ), dtype = tf.float32)

x = tf.expand_dims(x, axis = 0)
y = tf.expand_dims(y, axis = 0)

我的型号是：-

# Set the random seed
tf.random.set_seed(42)

# Create a model 
model = tf.keras.Sequential([
    tf.keras.layers.Dense(1)
])

# Compile the model 
model.compile(loss = tf.keras.losses.mae,
              optimizer = tf.keras.optimizers.SGD(),
              metrics = ['accuracy']
              )

# Fitting the model 
model.fit(x,y, epochs = 5)

在使用模型进行预测时，我希望模型能够进行预测，但它给出了错误。

我的预测代码是：-

model. Predict([17.0])

错误是：-

TypeError                                 Traceback (most recent call last)
<ipython-input-28-914f309df50b> in <cell line: 1>()
----> 1 model.predict([17.0], dtype = tf.float32)

1 frames
/usr/local/lib/python3.10/dist-packages/keras/utils/traceback_utils.py in error_handler(*args, **kwargs)
     63         filtered_tb = None
     64         try:
---> 65             return fn(*args, **kwargs)
     66         except Exception as e:
     67             filtered_tb = _process_traceback_frames(e.__traceback__)

TypeError: Model.predict() got an unexpected keyword argument 'dtype'

Answer 1

在 Tensorflow Keras API 中预测模型时，不接受 dtype argumnet。因此，您需要将输入数据作为 Numpy 数组传递。请找到下面的代码，我已经尝试过这个代码。我们不会收到任何错误。

# Creating the data 
x = np.array(\[-7.0,-4.0,-1.0,2.0,5.0,8.0,11.0,14.0])
y = np.array(\[3.0,6.0,9.0,12.0,15.0,18.0,21.0,24.0])

## Turning the data into tensors
x = tf.cast(tf.constant(x ), dtype = tf.float32)
y = tf.cast(tf.constant(y ), dtype = tf.float32)

x = tf.expand_dims(x, axis = 0)
y = tf.expand_dims(y, axis = 0)


# Set the random seed
tf.random.set_seed(42)

# Create a model 
model = tf.keras.Sequential([
    tf.keras.layers.Dense(1)
])

# Compile the model 
model.compile(loss = tf.keras.losses.mae,
optimizer = tf.keras.optimizers.SGD(),
metrics = ['accuracy'])

# Fitting the model 
model.fit(x,y, epochs = 5)
 
# Model Predict
prediction = model.predict(np.array([17.0]))
print(prediction)