在基本Tensorflow 2.0中运行简单回归

问题描述

我正在学习Tensorflow 2.0，我认为在Tensorflow中实现最基本的简单线性回归是一个好主意。不幸的是，我遇到了几个问题，我想知道这里是否有人可以提供帮助。

I'm learning Tensorflow 2.0 and I thought that it would be a good idea to implement the most basic simple linear regression in Tensorflow. Unfortunately, I ran into several issues and I was wondering if anyone here might be able to help.

请考虑以下设置：

import tensorflow as tf # 2.0.0-alpha0
import numpy as np

x_data = np.random.randn(2000, 1)

w_real = [0.7] # coefficients
b_real = -0.2 # global bias
noise = np.random.randn(1, 2000) * 0.5 # level of noise
y_data = np.matmul(w_real, x_data.T) + b_real + noise

现在使用模型定义：

# modelling this data with tensorflow (manually!)
class SimpleRegressionNN(tf.keras.Model):

    def __init__(self):
        super(SimpleRegressionNN, self).__init__()
        self.input_layer = tf.keras.layers.Input
        self.output_layer = tf.keras.layers.Dense(1)


    def call(self, data_input):
        model = self.input_layer(data_input)
        model = self.output_layer(model)
        # open question: how to account for the intercept/bias term?
        # Ideally, we'd want to generate preds as matmult(X,W) + b
        return model

nn_regressor = SimpleRegressionNN()

reg_loss = tf.keras.losses.MeanSquaredError()
reg_optimiser = tf.keras.optimizers.SGD(0.1)
metric_accuracy = tf.keras.metrics.mean_squared_error

# define forward step
@tf.function
def train_step(x_sample, y_sample):
  with tf.GradientTape() as tape:
    predictions = nn_regressor(x_sample)
    loss = reg_loss(y_sample, predictions)
    gradients = tape.gradient(loss, nn_regressor.trainable_variables) # had to indent this!
  reg_optimiser.apply_gradients(zip(gradients, nn_regressor.trainable_variables))
  metric_accuracy(y_sample, predictions)

#%%
# run the model
for epoch in range(10):
    for x_point, y_point in zip(x_data.T[0], y_data[0]): # batch of 1
        train_step(x_sample=x_point, y_sample=y_point)
    print("MSE: {}".format(metric_accuracy.result()))

不幸的是，我收到以下错误：

Unfortunately, I'm getting the following error:

TypeError: You are attempting to use Python control flow in a layer that was not declared to be dynamic. Pass `dynamic=True` to the class constructor.
Encountered error:
"""
Tensor objects are only iterable when eager execution is enabled. To iterate over this tensor use tf.map_fn.
"""

完整的错误输出在这里：

The full error output is here:

---------------------------------------------------------------------------

TypeError                                 Traceback (most recent call last)

/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
    611                                                       inputs)) as auto_updater:
--> 612                 outputs = self.call(inputs, *args, **kwargs)
    613                 auto_updater.set_outputs(outputs)

<ipython-input-5-8464ad8bcf07> in call(self, data_input)
      7     def call(self, data_input):
----> 8         model = self.input_layer(data_input)
      9         model = self.output_layer(model)

/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/input_layer.py in Input(shape, batch_size, name, dtype, sparse, tensor, **kwargs)
    232       sparse=sparse,
--> 233       input_tensor=tensor)
    234   # Return tensor including `_keras_history`.

/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/input_layer.py in __init__(self, input_shape, batch_size, dtype, input_tensor, sparse, name, **kwargs)
     93       if input_shape is not None:
---> 94         batch_input_shape = (batch_size,) + tuple(input_shape)
     95       else:

/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in __iter__(self)
    448       raise TypeError(
--> 449           "Tensor objects are only iterable when eager execution is "
    450           "enabled. To iterate over this tensor use tf.map_fn.")

TypeError: Tensor objects are only iterable when eager execution is enabled. To iterate over this tensor use tf.map_fn.


During handling of the above exception, another exception occurred:

TypeError                                 Traceback (most recent call last)

<ipython-input-22-e1bde858b0fc> in <module>()
      3     #train_step(x_sample=x_data.T[0], y_sample=y_data[0])
      4     for x_point, y_point in zip(x_data.T[0], y_data[0]):
----> 5         train_step(x_sample=x_point, y_sample=y_point)
      6     print("MSE: {}".format(metric_accuracy.result()))
      7

/anaconda3/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
    416       # In this case we have not created variables on the first call. So we can
    417       # run the first trace but we should fail if variables are created.
--> 418       results = self._stateful_fn(*args, **kwds)
    419       if self._created_variables:
    420         raise ValueError("Creating variables on a non-first call to a function"

/anaconda3/lib/python3.6/site-packages/tensorflow/python/eager/function.py in __call__(self, *args, **kwargs)
   1285   def __call__(self, *args, **kwargs):
   1286     """Calls a graph function specialized to the inputs."""
-> 1287     graph_function, args, kwargs = self._maybe_define_function(args, kwargs)
   1288     return graph_function._filtered_call(args, kwargs)  # pylint: disable=protected-access
   1289

/anaconda3/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _maybe_define_function(self, args, kwargs)
   1609           relaxed_arg_shapes)
   1610       graph_function = self._create_graph_function(
-> 1611           args, kwargs, override_flat_arg_shapes=relaxed_arg_shapes)
   1612       self._function_cache.arg_relaxed[rank_only_cache_key] = graph_function
   1613

/anaconda3/lib/python3.6/site-packages/tensorflow/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
   1510             arg_names=arg_names,
   1511             override_flat_arg_shapes=override_flat_arg_shapes,
-> 1512             capture_by_value=self._capture_by_value),
   1513         self._function_attributes)
   1514

/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
    692                                           converted_func)
    693
--> 694       func_outputs = python_func(*func_args, **func_kwargs)
    695
    696       # invariant: `func_outputs` contains only Tensors, IndexedSlices,

/anaconda3/lib/python3.6/site-packages/tensorflow/python/eager/def_function.py in wrapped_fn(*args, **kwds)
    315         # __wrapped__ allows AutoGraph to swap in a converted function. We give
    316         # the function a weak reference to itself to avoid a reference cycle.
--> 317         return weak_wrapped_fn().__wrapped__(*args, **kwds)
    318     weak_wrapped_fn = weakref.ref(wrapped_fn)
    319

/anaconda3/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py in wrapper(*args, **kwargs)
    684                   optional_features=autograph_options,
    685                   force_conversion=True,
--> 686               ), args, kwargs)
    687
    688         # Wrapping around a decorator allows checks like tf_inspect.getargspec

/anaconda3/lib/python3.6/site-packages/tensorflow/python/autograph/impl/api.py in converted_call(f, owner, options, args, kwargs)
    390     return _call_unconverted(f, args, kwargs)
    391
--> 392   result = converted_f(*effective_args, **kwargs)
    393
    394   # The converted function's closure is simply inserted into the function's

/var/folders/8_/pl9fgq297ld3b7kgy5tmvf700000gn/T/tmpluzodr7d.py in tf__train_step(x_sample, y_sample)
      2 def tf__train_step(x_sample, y_sample):
      3   with tf.GradientTape() as tape:
----> 4     predictions = ag__.converted_call(nn_regressor, None, ag__.ConversionOptions(recursive=True, verbose=0, strip_decorators=(tf.function, defun, ag__.convert, ag__.do_not_convert, ag__.converted_call), force_conversion=False, optional_features=(), internal_convert_user_code=True), (x_sample,), {})
      5     loss = ag__.converted_call(reg_loss, None, ag__.ConversionOptions(recursive=True, verbose=0, strip_decorators=(tf.function, defun_1, ag__.convert, ag__.do_not_convert, ag__.converted_call), force_conversion=False, optional_features=(), internal_convert_user_code=True), (y_sample, predictions), {})
      6     gradients = ag__.converted_call('gradient', tape, ag__.ConversionOptions(recursive=True, verbose=0, strip_decorators=(tf.function, defun_2, ag__.convert, ag__.do_not_convert, ag__.converted_call), force_conversion=False, optional_features=(), internal_convert_user_code=True), (loss, nn_regressor.trainable_variables), {})

/anaconda3/lib/python3.6/site-packages/tensorflow/python/autograph/impl/api.py in converted_call(f, owner, options, args, kwargs)
    265
    266   if not options.force_conversion and conversion.is_whitelisted_for_graph(f):
--> 267     return _call_unconverted(f, args, kwargs)
    268
    269   # internal_convert_user_code is for example turned off when issuing a dynamic

/anaconda3/lib/python3.6/site-packages/tensorflow/python/autograph/impl/api.py in _call_unconverted(f, args, kwargs)
    186     return f.__self__.call(args, kwargs)
    187
--> 188   return f(*args, **kwargs)
    189
    190

/anaconda3/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, inputs, *args, **kwargs)
    623                                   'dynamic. Pass `dynamic=True` to the class '
    624                                   'constructor.\nEncountered error:\n"""\n' +
--> 625                                   exception_str + '\n"""')
    626               raise
    627           else:

TypeError: You are attempting to use Python control flow in a layer that was not declared to be dynamic. Pass `dynamic=True` to the class constructor.
Encountered error:
"""
Tensor objects are only iterable when eager execution is enabled. To iterate over this tensor use tf.map_fn.
"""

麻烦的是，默认情况下2.0设置为急于执行！

The trouble is, 2.0 is set to eager execution by default!

除了这个问题，我还有几个其他问题：

In addition to this problem, I have a few extra questions:

1. 解释拦截项的最佳方法是什么


2. 一般方法是否合理，或者我在这里做任何奇怪的事情？ （忽略批量大小和我必须验证数据的事实，这只是一个玩具示例）

非常感谢！

推荐答案

我有以下评论：

• 您在 SimpleRegression 模型中不需要 Input 层。另外，不要通过 model 名称调用图层的张量输出（就像在 call（）方法）。


• 您没有将正确的形状传递给 train_step 函数。在您传递（ input_dim ，）时，它预期会收到（n_samples，input_dim）。


• 请记住，在 tensorflow 中，张量的第一维始终是批处理大小（即样本数）。


• 为什么要调用 metric_accuracy = tf.keras.metrics.mean_squared_error 精度？您遇到了回归问题，没有回归的准确性。另外，为什么要定义两次并计算两次 mse ？


• 如果使用 tf转换数据。 convert_to_tensor（）执行会更快。


• 函数 train_step（）执行向前和向后传递，


• 使用小的数据集作为玩具示例（2-10个样本，而不是2000个样本），尤其是在您不知道代码是否有效的情况下！
>

• 您的函数 train_step（）不返回任何内容，您希望如何打印 mse 损失。

• You don't need Input layer in your SimpleRegression model. Also, don't call the tensor output of the layer by "model" name (as you do in the call() method). This is really confusing.
• You don't pass correct shapes to your train_step function. It expects to receive (n_samples, input_dim) while you passing (input_dim, ).
• Remember, in tensorflow first dimension of a tensor is always the batch size (i.e. number of samples). Use it always like that, without transposing.
• Why do you call metric_accuracy = tf.keras.metrics.mean_squared_error accuracy? You have a regression problem, there's no such thing as accuracy in regression. Also, why do you define twice and compute twice mse?
• If you convert your data using tf.convert_to_tensor() the execution will be faster.
• Function train_step() performs forward and backward passes and not just a forward pass.
• Use small datasets for toy examples (2-10 samples, not 2000), especially if you don't know whether or not your code works!
• Your function train_step() doesn't return anything, how do you expect to print the value of the mse loss.

这是您的代码的更正版本：

This is a corrected version of your code:

import tensorflow as tf # 2.0.0-alpha0
import numpy as np

x_data = np.random.randn(5, 2)

w_real = 0.7 # coefficients
b_real = -0.2 # global bias
noise = np.random.randn(5, 2) * 0.01 # level of noise
y_data = w_real * x_data + b_real + noise

class SimpleRegressionNN(tf.keras.Model):

    def __init__(self):
        super(SimpleRegressionNN, self).__init__()

        self.output_layer = tf.keras.layers.Dense(1, input_shape=(2, ))

    def call(self, data_input):
        result = self.output_layer(data_input)
        return result

reg_loss = tf.keras.losses.MeanSquaredError()
reg_optimiser = tf.keras.optimizers.SGD(0.1)

nn_regressor = SimpleRegressionNN()

@tf.function
def train_step(x_sample, y_sample):
    with tf.GradientTape() as tape:
        predictions = nn_regressor(x_sample)
        loss = reg_loss(y_sample, predictions)
    gradients = tape.gradient(loss, nn_regressor.trainable_variables) # had to indent this!
    reg_optimiser.apply_gradients(zip(gradients, nn_regressor.trainable_variables))

    return loss

for x_point, y_point in zip(x_data, y_data): # batch of 1
    x_point, y_point = tf.convert_to_tensor([x_point]), tf.convert_to_tensor([y_point])
    mse = train_step(x_sample=x_point, y_sample=y_point)
    print("MSE: {}".format(mse.numpy()))

这篇关于在基本Tensorflow 2.0中运行简单回归的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持！