Difference between revisions of "DeepLearning"

From Hawk Wiki
Jump to: navigation, search
 
Line 12: Line 12:
 
*Reshape the datasets such that each example is now a vector of size (num_px * num_px * 3, 1)
 
*Reshape the datasets such that each example is now a vector of size (num_px * num_px * 3, 1)
 
*"Standardize" the data
 
*"Standardize" the data
 +
 +
===Common functions===
 +
<pre class="brush:python">
 +
def sigmoid(z):
 +
    return 1 / (1 + np.exp(-z))
 +
</pre>

Latest revision as of 02:37, 8 January 2018

Deep Learning

Numpy/Python tricks

A trick when you want to flatten a matrix X of shape (a,b,c,d) to a matrix X_flatten of shape (b ∗∗ c ∗∗ d, a) is to use:

X_flatten = X.reshape(X.shape[0], -1).T      # X.T is the transpose of X

Common Steps For Data Pre Processing

Common steps for pre-processing a new dataset are:

  • Figure out the dimensions and shapes of the problem (m_train, m_test, num_px, ...)
  • Reshape the datasets such that each example is now a vector of size (num_px * num_px * 3, 1)
  • "Standardize" the data

Common functions

def sigmoid(z):
    return 1 / (1 + np.exp(-z))