注解
Here we show how to implement various linear regression techniques in TensorFlow. The first two sections show how to do standard matrix linear regression solving in TensorFlow. The remaining six sections depict how to implement various types of regression using computational graphs in TensorFlow.
TensorFLow的线性回归¶
Linear regression iterating through a computational graph with L2 Loss. Here we extend the usage of the computational graph to create multiple layers and show how they appear in Tensorboard.
下载本章 Jupyter Notebook
线性回归的损失函数¶
L2 vs L1 loss in linear regression. We talk about the benefits and limitations of both.
下载本章 Jupyter Notebook
Deming回归(全回归)¶
Deming (total) regression implemented in TensorFlow by changing the loss function.
下载本章 Jupyter Notebook
套索(Lasso)回归和岭(Ridge)回归¶
Lasso and Ridge regression are ways of regularizing the coefficients. We implement both of these in TensorFlow via changing the loss functions.
下载本章 Jupyter Notebook
弹性网(Elastic Net)回归¶
Elastic net is a regularization technique that combines the L2 and L1 loss for coefficients. We show how to implement this in TensorFlow.
下载本章 Jupyter Notebook
逻辑(Logistic)回归¶
We implement logistic regression by the use of an activation function in our computational graph.
下载本章 Jupyter Notebook
本章学习模块¶
tensorflow.zeros¶
Creates a tensor with all elements set to zero.
This operation returns a tensor of type dtype with shape shape and all elements set to zero.
>>> tf.zeros([3, 4], tf.int32)
<tf.Tensor: shape=(3, 4), dtype=int32, numpy=
array([[0, 0, 0, 0],
[0, 0, 0, 0],
[0, 0, 0, 0]], dtype=int32)>
| param shape: | A list of integers, a tuple of integers, or a 1-D Tensor of type int32. |
|---|---|
| param dtype: | The DType of an element in the resulting Tensor. |
| param name: | Optional string. A name for the operation. |
| returns: | A Tensor with all elements set to zero. |
tensorflow.ones¶
Creates a tensor with all elements set to one (1).
See also tf.ones_like.
This operation returns a tensor of type dtype with shape shape and all elements set to one.
>>> tf.ones([3, 4], tf.int32)
<tf.Tensor: shape=(3, 4), dtype=int32, numpy=
array([[1, 1, 1, 1],
[1, 1, 1, 1],
[1, 1, 1, 1]], dtype=int32)>
| param shape: | A list of integers, a tuple of integers, or a 1-D Tensor of type int32. |
|---|---|
| param dtype: | Optional DType of an element in the resulting Tensor. Default is tf.float32. |
| param name: | Optional string. A name for the operation. |
| returns: | A Tensor with all elements set to one (1). |