Laboratory Task 5

Genheylou Felisilda - DS4A

Instructions: Pytorch Excercises

1. Perform Standard Imports

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

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.

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

5. Change the dtype of x from int32 to int64

6. Reshape x into a 3x2 tensor
   There are several ways to do this.

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

8. Without changing x, return a tensor of square values of `x
   There are several ways to do this.

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.

10. Find the matrix product of x and `y

#1 Perform Standard Imports

import torch
import numpy as np
import sys

#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.

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

array([4, 4, 2, 4, 4, 2], dtype=int32)

#4 Create a tensor "x" from the array above

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

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

#5 Change the dtype of x from int32 to int64

print("Old:", x.dtype)
x = x.type(torch.int64)

print("New:", x.dtype)

Old: torch.int32
New: torch.int64

#6 Reshape x into a 3x2 tensor
reshaped = x.reshape(3,2)
reshaped

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

#7 Return the right-hand column of tensor x

right_col = reshaped[:, 1:]
right_col

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

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

x_squared = reshaped ** 2 
x_squared

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

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

torch.manual_seed(42)
y = torch.rand(2,3)
y

tensor([[0.8823, 0.9150, 0.3829],
        [0.9593, 0.3904, 0.6009]])

#10 Find the matrix product of x and y.

product = y.mul(y)
product

tensor([[0.7784, 0.8372, 0.1466],
        [0.9203, 0.1524, 0.3611]])