Laboratory Task 5 - PyTorch Basics

Laboratory Task 5 - PyTorch Basics#

DS Elective 4 - Deep Learning#

Name: Keith Laspoña
Year & Section: DS4A

1. Perform Standard Imports#

import numpy as np
import torch
import sys
import random

2. Create a function called set_seed() that accepts seed: int as a parameter, this function must return nothing but just set the seed to a certain value.#

def set_seed(seed:int):
    np.random.seed(seed)
    torch.manual_seed(seed)

3. Create a NumPy array called “arr” that contains 6 random integers between 0 (inclusive) and 5 (exclusive), call the set_seed() function and use 42 as the seed parameter.#

set_seed(42)

arr = np.random.randint(0,5, size=6)
print(arr)
print(arr.dtype)
print(type(arr))

[3 4 2 4 4 1]
int32
<class 'numpy.ndarray'>

4. Create a tensor “x” from the array above#

x = torch.from_numpy(arr)
print(x)

tensor([3, 4, 2, 4, 4, 1], dtype=torch.int32)

5. Change the dtype of x from int32 to int64#

x = x.type(torch.int64)
print(x)
print(x.dtype)

tensor([3, 4, 2, 4, 4, 1])
torch.int64

6. Reshape x into a 3x2 tensor#

x = x.reshape(3, 2)
print (x)
print (x.dtype)

tensor([[3, 4],
        [2, 4],
        [4, 1]])
torch.int64

7. Return the right-hand column of tensor x#

x = x
right_hand_col = x[:, 1:]
right_hand_col

tensor([[4],
        [4],
        [1]])

8. Without changing x, return a tensor of square values of x#

There are several ways to do this.

x = x
square_val = x ** 2
square_val

tensor([[ 9, 16],
        [ 4, 16],
        [16,  1]])

9. Create a tensor y with the same number of elements as x, that can be matrix-multiplied with x#

Use PyTorch directly (not NumPy) to create a tensor of random integers between 0 (inclusive) and 5 (exclusive). Use 42 as seed. Think about what shape it should have to permit matrix multiplication.

y = torch.randint(0, 5, (2, 3))
set_seed(42)
y

tensor([[0, 4, 1],
        [2, 0, 0]])

10. Find the matrix product of x and y.#

matrix_prod = torch.matmul(x,y)
matrix_prod

tensor([[ 8, 12,  3],
        [ 8,  8,  2],
        [ 2, 16,  4]])
Contents