CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutSign UpSign In
amanchadha

Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place. Commercial Alternative to JupyterHub.

GitHub Repository: amanchadha/coursera-deep-learning-specialization
 Path: blob/master/C4 - Convolutional Neural Networks/Week 2/KerasTutorial/kt_utils.py
Views: 4804
1
import keras.backend as K

2
import math

3
import numpy as np

4
import h5py

5
import matplotlib.pyplot as plt

6


7


8
def mean_pred(y_true, y_pred):

9
    return K.mean(y_pred)

10


11
def load_dataset():

12
    train_dataset = h5py.File('datasets/train_happy.h5', "r")

13
    train_set_x_orig = np.array(train_dataset["train_set_x"][:]) # your train set features

14
    train_set_y_orig = np.array(train_dataset["train_set_y"][:]) # your train set labels

15


16
    test_dataset = h5py.File('datasets/test_happy.h5', "r")

17
    test_set_x_orig = np.array(test_dataset["test_set_x"][:]) # your test set features

18
    test_set_y_orig = np.array(test_dataset["test_set_y"][:]) # your test set labels

19


20
    classes = np.array(test_dataset["list_classes"][:]) # the list of classes

21
    

22
    train_set_y_orig = train_set_y_orig.reshape((1, train_set_y_orig.shape[0]))

23
    test_set_y_orig = test_set_y_orig.reshape((1, test_set_y_orig.shape[0]))

24
    

25
    return train_set_x_orig, train_set_y_orig, test_set_x_orig, test_set_y_orig, classes

26


27


28