Skip to content

Instantly share code, notes, and snippets.

@edenau

edenau/NumPy-neural-net-9.py

Last active December 27, 2019 16:40
Show Gist options
  • Save edenau/6d92f4a4be3d4a7af6f36d6a4d19f0c3 to your computer and use it in GitHub Desktop.
Save edenau/6d92f4a4be3d4a7af6f36d6a4d19f0c3 to your computer and use it in GitHub Desktop.
Download ZIP
Raw
NumPy-neural-net-9.py
# test loss
print(get_loss(y_test, forward_prop(X_test)))
def predict(X_raw_any):
X_any = np.array([standardize(X_raw_any[row,:], X_scalers[row]) for row in range(X_num_row)])
y_hat = forward_prop(X_any)
y_hat_any = np.array([unstandardize(y_hat[row,:], y_scalers[row]) for row in range(y_num_row)])
return y_hat_any
predict(np.array([[30,70],[70,30],[3,5],[888,122]]).T)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment