Shape of an array in NumPy

Question

In Neural Networks and Deep Learning by DeepLearning.AI in Coursera I've a doubt in 2nd Week Programming Assignment

train_set_x_orig, train_set_y, test_set_x_orig, test_set_y, classes = load_dataset()

In above code segment they say that train_set_x_orig is a numpy-array of shape (m_train, num_px, num_px, 3)

Someone please help me to understand how shape of train_set_x_orig is (m_train, num_px, num_px, 3) and even i can't able to visualize the contents of numpy-array train_set_x_orig

This is something very specific to that code base. There is a function called load_dataset() that returns a tuple of objects, one of which is a numpy array called train_set_x_orig. What is the data about? Usually, images have three channels. — Hari
– Hari, Commented Nov 10, 2020 at 11:46
Example interpretation: (m_train, num_px, num_px, 3) = n images * n pixels width * n pixels height = n pixels width * 3 color-channels (e.g. RGB) — sascha
– sascha, Commented Nov 10, 2020 at 11:47

faheem · Accepted Answer · 2020-11-13 13:54:41Z

1

look like its an image. in python use this code.

import matplotlib.pyplot as plt

for i in train_set_x_orig:
   img = np.array(i).astype('uint8')
   plt.imshow(img)
   plt.show()

this will show you all images 1 by one. 1st dimension is number of images, 2nd dimension is width 3rd dimension is height 4th dimension is color channel

answered Nov 13, 2020 at 13:54

faheem

6344 silver badges5 bronze badges

Sign up to request clarification or add additional context in comments.

Collectives™ on Stack Overflow

Shape of an array in NumPy

1 Answer 1

Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

Comments

Your Answer

Sign up or log in

Post as a guest

Related