Exercise 6

MNIST/b_3.txt

@@ -0,0 +1 @@
+-0.3120380938053131	0.057060789316892624	0.5383008718490601	-0.4334142804145813	0.20545503497123718	0.8229865431785583	0.26446419954299927	1.3929160833358765	0.40466466546058655	-0.06923668831586838

MNIST/main.py

@@ -0,0 +1,108 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Thu Sep 28 08:23:56 2023
+
+@author: Mohamad Mohannad al Kawadri (mohamad.mohannad.al.kawadri@nmbu.no), Trygve Børte Nomeland (trygve.borte.nomeland@nmbu.no)
+"""
+from abc import ABC, abstractmethod
+import numpy as np
+from copy import deepcopy
+from torchvision import datasets, transforms
+
+class Network:
+    def __init__(self, layers, W_file_list, b_file_list):
+        self.layers = layers
+        self.W_file_list = W_file_list
+        self.b_file_list = b_file_list
+        self.x = input
+
+    def run(self, x):
+        result = x
+        for n, W_file, b_file in zip(self.layers, self.W_file_list, self.b_file_list):
+            y = deepcopy(result)
+            l = n(y, W_file = W_file, b_file = b_file)
+            result = l.run()
+        return result
+
+    def evaluate(self, x, expected_value):
+        result = list(self.run(x))
+        max_value_index = result.index(max(result))
+        return int(max_value_index) == expected_value
+
+class Layer:
+    def __init__(self, x, W_file, b_file):
+        self.x = x
+        files = read(W_file, b_file)
+        self.W = files.get('W')
+        self.b = files.get('b')
+        
+    @abstractmethod
+    def run(self):
+        pass
+
+class SigmaLayer(Layer):
+    def run(self):
+        return layer(self.W,  self.x, self.b)
+
+class ReluLayer(Layer):
+    def run(self):
+        return relu_layer(self.W,  self.x, self.b)
+
+def read(W_file, b_file):
+    return {'W': np.loadtxt(W_file), 'b': np.loadtxt(b_file)}
+
+# define activation function
+def sigma(y):
+    if y > 0:
+        return y
+    else:
+        return 0
+sigma_vec = np.vectorize(sigma)
+
+def relu_scalar(x):
+    if x > 0:
+        return x
+    else:
+        return 0
+relu = np.vectorize(relu_scalar)
+
+
+# define layer function for given weight matrix, input and bias
+def layer(W, x, b):
+    return sigma_vec(W @ x + b)
+
+def relu_layer(W, x, b):
+    return sigma_vec(W @ x + b)
+
+# Function from example file "read.py"
+def get_mnist():
+    return datasets.MNIST(root='./data', train=True, transform=transforms.ToTensor(), download=True)
+
+# Function from example file "read.py"
+def return_image(image_index, mnist_dataset):
+    image, label = mnist_dataset[image_index]
+    image_matrix = image[0].detach().numpy()  # Grayscale image, so we select the first channel (index 0)
+    return image_matrix.reshape(image_matrix.size), image_matrix, label
+
+def evalualte_on_mnist(image_index, expected_value):
+    mnist_dataset = get_mnist()
+    x, image, label = return_image(image_index, mnist_dataset)
+    network = Network([ReluLayer, ReluLayer, ReluLayer], ['W_1.txt', 'W_2.txt', 'W_3.txt'], ['b_1.txt', 'b_2.txt', 'b_3.txt'])
+    return network.evaluate(x, expected_value)
+
+def run_on_mnist(image_index):
+    mnist_dataset = get_mnist()
+    x, image, label = return_image(image_index, mnist_dataset)
+    network = Network([ReluLayer, ReluLayer, ReluLayer], ['W_1.txt', 'W_2.txt', 'W_3.txt'], ['b_1.txt', 'b_2.txt', 'b_3.txt'])
+    return network.run(x)
+
+def main():
+    print(f'Check if network works on image 19961 (number 4): {evalualte_on_mnist(19961, 4)}')
+    print(f'Check if network works on image 10003 (number 9): {evalualte_on_mnist(10003, 9)}')
+    print(f'Check if network works on image 117 (number 2): {evalualte_on_mnist(117, 2)}')
+    print(f'Check if network works on image 1145 (number 3): {evalualte_on_mnist(1145, 3)}')
+    print(f'Values image 19961 (number 4): {run_on_mnist(19961)}')
+
+if __name__ == '__main__':
+    main()

MNIST/requirements.txt

@@ -0,0 +1,3 @@
+numpy
+setuptools
+torchvision

ex6.py

@@ -0,0 +1,83 @@
+class Person:
+    def __init__(self, name: str, age: int, email: str) -> None:
+        self._name: str = name
+        self._age: int = age
+        self._email: str = email
+
+    def get_details(self) -> str:
+        return f"Name: {self._name}, Age: {self._age}, Email: {self._email}"
+
+
+class Student(Person):
+    def __init__(self, name: str, age: int, email: str, student_id: int) -> None:
+        super().__init__(name, age, email)
+        self._student_id: int = student_id
+        self._courses: list = []
+        self._grades: dict[str, str] = {}
+
+    def enroll_in_course(self, course: 'Course') -> None:
+        self._courses.append(course)
+    
+    def assign_grade(self, course_name: str, grade: str) -> None:
+        self._grades[course_name] = grade
+
+    def get_grades(self) -> dict[str, str]: 
+        return self._grades
+
+
+class Teacher(Person):
+    def __init__(self, name: str, age: int, email: str, subject: str) -> None:
+       super().__init__(name, age, email)
+       self._subject: str = subject
+
+    def assign_grade(self, student: Student, course: 'Course', grade: str) -> None:
+        student.assign_grade(course._course_name, grade)
+
+class Course:
+    def __init__(self, course_name: str, course_code: str) -> None:
+        self._course_name: str = course_name
+        self._course_code: str = course_code
+        self._enrolled_students: list[Student] = []
+
+    def add_student(self, student: Student) -> None: 
+        self._enrolled_students.append(student)
+        student.enroll_in_course(self)
+    
+    def list_students(self) -> list[str]: 
+        return [x.get_details() for x in self._enrolled_students]
+
+def main() -> None:
+    thorvald = Student("Thorvald", 28, "thorvald@example.com", 456)
+    johannes = Student("Johannes", 19, "Johannes@example.com", 35198)
+    tora = Student("Tora", 21, "Tora@example.com", 984555)
+
+    ola = Teacher("Ola Normann", 56, "ola_normann@example.com", "FYS101")
+    kari = Teacher("Kari Normann", 104, "kari.normann@example.com", "MATH999")
+
+    FYS101 = Course("Mekanikk", "FYS101")
+    MATH999 = Course("Matte", "MATH999")
+
+    students = [thorvald, johannes, tora]
+
+    for student in students:
+        FYS101.add_student(student)
+        MATH999.add_student(student)
+
+    ola.assign_grade(thorvald, FYS101, "F")
+    ola.assign_grade(johannes, FYS101, "E")
+    ola.assign_grade(tora, FYS101, "A")
+
+    kari.assign_grade(thorvald, MATH999, "B")
+    kari.assign_grade(johannes, MATH999, "D")
+    kari.assign_grade(tora, MATH999, "A+")
+
+    print(f"{thorvald._name}'s grades: {thorvald.get_grades()}")
+    print(f"{thorvald._name}'s grades: {johannes.get_grades()}")
+    print(f"{tora._name}'s grades: {tora.get_grades()}")
+
+    print("Students in FYS101:")
+    for student in FYS101.list_students():
+        print(student)
+
+if __name__ == "__main__":
+    main()

uke1.py

@@ -0,0 +1,110 @@
+# Task 1
+def task1():
+    name = input("Enter your name here:")
+    print(f"What's up {name}!")
+
+# Task 2
+def putinframe(text):
+    l = len(text)
+    print("-"*(l+6))
+    print("‖"+" "*(l+4) + "‖")
+    print("‖"+ "  " + text + "  "+ "‖")
+    print("‖"+" "*(l+4) + "‖")
+    print("-"*(l+6))
+
+def task2():
+    name = input("Type your name:")
+    putinframe(f"Have a lovely day {name}!")
+
+
+# Task 3
+def square_table(c1, c2, c3):
+    t = "{:^10}|{:^10}|{:^10}|\n".format(c1[0],c2[0],c3[0])
+    t += ("-"*len(t)+"\n")
+    for n in range(1, len(c1)):
+        t += ("{:^10}|{:^10}|{:^10}|\n".format(c1[n],c2[n],c3[n]))
+    return(t)
+
+def task3():
+    n_list = ["x"]
+    sq_list = ["x²"]
+    cube_list = ["x³"]
+    for n in range(11):
+        n_list.append(n)
+        sq_list.append(n**2)
+        cube_list.append(n**3)
+    print(square_table(n_list, sq_list, cube_list))
+
+# task 4
+def district_table(data, head):
+    # Formats the data into a nice table in a string
+    t = "{:^25}|{:^10}|\n".format(head[0],head[1])
+    t += ("-"*len(t)+"\n")
+    for n,p in data.items():
+        t += ("{:^25}|{:^10}|\n".format(n, p))
+    return(t)
+
+def task4():
+    with open('norway_municipalities_2017.csv') as f:
+        # we will make a dict where the the kei is the district and the value the population
+        d = {}
+        # assume the csv file always has a header
+        l_iter = iter(f)
+        l_iter.__next__()
+        for l in l_iter:
+            # we get a list where 0 is the kommune name, 1 is what fylke it is in and 2 is the population
+            ll = l.strip("\n").split(',')
+            name = ll[1]
+            if name in d.keys():
+                d.update({name: d.get(name) + int(ll[2])})
+            else:
+                d.update({name: int(ll[2])})
+        
+        head = ["District", "Population"]
+        res = {key: val for key, val in sorted(d.items(), key = lambda ele: ele[1], reverse=True)}
+        print(district_table(res, head))
+
+# Task 5
+
+import matplotlib.pyplot as plt
+import numpy as np
+
+def task5():
+    with open('norway_municipalities_2017.csv') as f:
+        # we will make a dict where the the kei is the district and the value the population
+        d = {}
+        # assume the csv file always has a header
+        l_iter = iter(f)
+        l_iter.__next__()
+        for l in l_iter:
+            # we get a list where 0 is the kommune name, 1 is what fylke it is in and 2 is the population
+            ll = l.strip("\n").split(',')
+            name = ll[1]
+            if name in d.keys():
+                d.update({name: d.get(name) + int(ll[2])})
+            else:
+                d.update({name: int(ll[2])})
+        
+        head = ["District", "Population"]
+        res = {key: val for key, val in sorted(d.items(), key = lambda ele: ele[1], reverse=True)}
+        
+        n = len(res.keys())
+        x = 0.5 + np.arange(n)
+        y = res.values()
+        fig, ax = plt.subplots()
+        ax.bar(res.keys(), y, edgecolor="white", linewidth=0.7)
+        ax.set(xlabel=head[0], ylabel=head[1])
+        plt.xticks(rotation = 90)
+        plt.show()
+
+if __name__ == "__main__":
+    print("Task 1:")
+    task1()
+    print("\nTask 2:")
+    task2()
+    print("\nTask 3:")
+    task3()
+    print("\nTask 4:")
+    task4()
+    print("\nTask 5:")
+    task5()

uke1/1:io.py

@@ -1,2 +0,0 @@
-name = input("Enter your name here:")
-print(f"What's up {name}!")

uke1/2:pp.py

@@ -1,15 +0,0 @@
-def putinframe(text):
-    l = len(text)
-    print(l)
-    print("෴"*(l+6))
-    print("‖"+" "*(l+4) + "‖")
-    print("‖"+ "  " + text + "  "+ "‖")
-    print("‖"+" "*(l+4) + "‖")
-    print("෴"*(l+6))
-
-def main():
-    name = input("Type yo name:")
-    putinframe(f"What's up {name}!")
-
-if __name__ == "__main__":
-    main()

uke1/3:sq_table.py

@@ -1,18 +0,0 @@
-def table(c1, c2, c3):
-    t = "{:^10}|{:^10}|{:^10}|\n".format(c1[0],c2[0],c3[0])
-    t += ("-"*len(t)+"\n")
-    for n in range(1, len(c1)):
-        t += ("{:^10}|{:^10}|{:^10}|\n".format(c1[n],c2[n],c3[n]))
-    return(t)
-def main():
-    n_list = ["x"]
-    sq_list = ["x²"]
-    cube_list = ["x³"]
-    for n in range(11):
-        n_list.append(n)
-        sq_list.append(n**2)
-        cube_list.append(n**3)
-    print(table(n_list, sq_list, cube_list))
-
-if __name__ == "__main__":
-    main()

uke1/4:population.py

@@ -1,30 +0,0 @@
-def table(data, head):
-    # Formats the data into a nice table in a string
-    t = "{:^25}|{:^10}|\n".format(head[0],head[1])
-    t += ("-"*len(t)+"\n")
-    for n,p in data.items():
-        t += ("{:^25}|{:^10}|\n".format(n, p))
-    return(t)
-
-def main():
-    with open('norway_municipalities_2017.csv') as f:
-        # we will make a dict where the the kei is the district and the value the population
-        d = {}
-        # assume the csv file always has a header
-        l_iter = iter(f)
-        l_iter.__next__()
-        for l in l_iter:
-            # we get a list where 0 is the kommune name, 1 is what fylke it is in and 2 is the population
-            ll = l.strip("\n").split(',')
-            name = ll[1]
-            if name in d.keys():
-                d.update({name: d.get(name) + int(ll[2])})
-            else:
-                d.update({name: int(ll[2])})
-        
-        head = ["District", "Population"]
-        res = {key: val for key, val in sorted(d.items(), key = lambda ele: ele[1], reverse=True)}
-        print(table(res, head))
-
-if __name__ == "__main__":
-    main()

uke1/5:diagram.py

@@ -1,33 +0,0 @@
-import matplotlib.pyplot as plt
-import numpy as np
-
-def main():
-    with open('norway_municipalities_2017.csv') as f:
-        # we will make a dict where the the kei is the district and the value the population
-        d = {}
-        # assume the csv file always has a header
-        l_iter = iter(f)
-        l_iter.__next__()
-        for l in l_iter:
-            # we get a list where 0 is the kommune name, 1 is what fylke it is in and 2 is the population
-            ll = l.strip("\n").split(',')
-            name = ll[1]
-            if name in d.keys():
-                d.update({name: d.get(name) + int(ll[2])})
-            else:
-                d.update({name: int(ll[2])})
-        
-        head = ["District", "Population"]
-        res = {key: val for key, val in sorted(d.items(), key = lambda ele: ele[1], reverse=True)}
-        
-        n = len(res.keys())
-        x = 0.5 + np.arange(n)
-        y = res.values()
-        fig, ax = plt.subplots()
-        ax.bar(res.keys(), y, edgecolor="white", linewidth=0.7)
-        ax.set(xlabel=head[0], ylabel=head[1])
-        plt.xticks(rotation = 90)
-        plt.show()
-
-if __name__ == "__main__":
-    main()

uke2.py

@@ -57,30 +57,27 @@ def table_from_votes(file_path, num=None):
     return(t)
 
 # Task 2
-def get_friends(text):
-    friends = []
-    for s in text:
-        names = re.findall(r'[A-Z]\w*', s)
-        if len(names) != 2:
-            raise ValueError('String does not contain excactly two capitalized words')
-        friends.append(names)
 
-    t = '{:^20}\n'.format('Venner')
-    t += ("-"*len(t)+"\n")
-    for n in friends:
-        t += (f'{n[0]:^10}-{n[1]:^10}\n')
-    return(t)
+def print_encoding_info(char):
+    char_int = int.from_bytes(bytes(char, 'utf-8'))
+    print(f"Character: '{char}'")
+    if char_int < 129:
+        print(f"- ASCII representation: {format(char_int, 'b')}")
+    else:
+        print("- Not in ASCII range")
+    print(f"- UTF-8: {' '.join(format(x, 'b') for x in bytearray(char, 'utf-8'))}", end='')
+    print(f' ({len(bytearray(char, "utf-8"))} bytes)')
+    print('\n')
+
+def print_encoding_info_list(char_list):
+    for char in char_list:
+        print_encoding_info(char)
 
 def main():
     print(table_from_votes('2021-09-14_party distribution_1_st_2021.csv'))
     print(table_from_votes('2021-09-14_party distribution_1_st_2021.csv', 3))
 
-    text = [
-    'Ali and Per and friends.',
-    'Kari and Joe know each other.',
-    'James has known Peter since school days.'
-    ]
-    print(get_friends(text))
+    print_encoding_info_list(["2", "$", "å"])
 
 if __name__ == '__main__':
     main()

uke3.py

@@ -1,53 +1,77 @@
-#!/usr/bin/env python3
-# -*- coding: utf-8 -*-
-"""
-Created on Thu Sep 28 08:23:56 2023
-
-@author: Inna Gumauri, Trygve Børte Nomeland
-"""
-
-#%% Task 1
-
 import re
 
-def student_information(filename):
-    with open(filename, 'r', newline='', encoding='utf-8') as f:
-        lines = f.readlines()
-    stud=[]
-    for line in lines:
-        if "#" in line:
-            continue
-        d=re.findall(r"[^, :\n]+", line)
-        stud.append({"name":d[0], "age":d[1], "phone number":d[2]})
-    return stud
+# Task 1
+"""
+Assume that we have sentences of the form
+- Ali and Per are friends.
+- Kari and Joe know each other.
+- James has known Peter since school days.
 
-print(student_information("data.txt"))
+The common structure here is that each sentence contains two names and that the names are the only words beginning with capital letters. Create a regular expression that
+- matches these sentences (one sentence at a time)
+- collects the names in groups
+"""
+def get_friends(text):
+    friends = []
+    for s in text:
+        names = re.findall(r'[A-Z]\w*', s)
+        if len(names) != 2:
+            raise ValueError('String does not contain excactly two capitalized words')
+        friends.append(names)
+    
+    t = '{:^20}\n'.format('Venner')
+    t += ("-"*len(t)+"\n")
+    for n in friends:
+        t += (f'{n[0]:^10}-{n[1]:^10}\n')
+    return(t)
 
 
-#%% Task 2
+# Task 2
+"""
+Write a Python function validate_password that checks if a given password string is valid based on the following rules:
 
-import re
-from pathlib import Path
+    Starts with an uppercase letter from I to Z.
+    Contains at least one word character (a-z, A-Z, 0-9, or underscore).
+    Has exactly 4 to 5 characters in length.
+    Ends with a digit.
+    May contain spaces between the characters but cannot start or end with a space.
+    The password must end at the string's end.
+"""
+def validate_password(password):
+    if re.match('[I-Z]', password) == None:
+        return False
+    if re.match('[a-zA-Z0-9|_]', password) == None:
+        return False
+    if len(password) < 4 or len(password) > 5:
+        return False
+    if re.search('[0-9]$', password) == None:
+        return False
+    # Rules 5 and 6 are already fulfilled
+    return True
 
-def get_imp_file(file):
-    with open(file, 'r', encoding='utf-8') as f:
-        txt = f.read()
-        # re.M gjør at ^ matcher starten av hver linje istedet for bare starten av stringen
-        ptr1 = re.compile(r"^import\s(\w+)", flags=re.M)
-        ptr2 = re.compile(r"^from\s(\w+)", flags=re.M)
-        imports = re.findall(ptr1, txt)
-        imports += re.findall(ptr2, txt)
+def main():
+    print('Test task 1:')
+    text = [
+    'Ali and Per and friends.',
+    'Kari and Joe know each other.',
+    'James has known Peter since school days.'
+    ]
+    print(get_friends(text))
     
-        # vi filtrerer ut duplikater:
-        res = []
-        [res.append(x) for x in imports if x not in res]      
-    return res
+    print('Test task 1:')
+    print('Valid:')
+    print(f'J1234: {validate_password("J1234")}')
+    print(f'I_ab5: {validate_password("I_ab5")}')
+    print(f'Z9_w4: {validate_password("Z9_w4")}')
+    print('\n')
+    print('Invalid:')
+    print(f'A1234: {validate_password("A1234")}')
+    print(f'J12345: {validate_password("J12345")}')
+    print(f'I__: {validate_password("I__")}')
+    print(f'?=?=)(=)/&__: {validate_password("?=?=)(=)/&")}')
+    print(f' J1234: {validate_password(" J1234")}')
 
-def print_imp_dir(path="./"):
-    p = Path(path)
-    files = list(p.glob('*.py'))
-    for f in files:
-        print(f'{Path.cwd()}/{f}: {get_imp_file(f)}')
 
-print_imp_dir()
-# %%
+
+if __name__ == '__main__':
+    main()

uke4.py

@@ -0,0 +1,24 @@
+from pathlib import Path
+
+def generate_exercise_list(project_assignments_start, total_exercises):
+    return [str(i) for i in range(1, project_assignments_start)] + [f'{i}{part}' for i in range(project_assignments_start, total_exercises + 1) for part in ['a', 'b']]
+
+def create_directories(directory, exercises, students):
+    parent_directory = Path.cwd() / directory
+
+    for exercise in exercises:
+        exercise_path = parent_directory / Path('exercise_' + exercise)
+        for student in students:
+            student_path = exercise_path / student
+            studentstudent_path.mkdir(parents=True, exist_ok=True)
+    
+    for directory in parent_directory.glob('**/*'):
+        print(directory)
+
+def main():
+    exercises = generate_exercise_list(5, 12)
+    students = ['Ole', 'Sarah', 'Ferdinand', 'Mattis']
+    create_directories('projects', exercises, students)
+
+if __name__ == '__main__':
+    main()

uke6.py

@@ -2,46 +2,35 @@ import numpy as np
 from copy import deepcopy
 
 class Network:
-    def __init__(self):
-        self.layers = []
-
-class Layer:
-    def __init__(self, w_file=None, b_file=None):
-        # define dimensions
+    def __init__(self, layers, W_file_list, b_file_list):
+        self.layers = layers
+        self.W_file_list = W_file_list
+        self.b_file_list = b_file_list
         self.n_layers = 4
         self.n_inputs = 784
         self.n_outputs = 10
         self.n = [self.n_inputs, 512, 256, self.n_outputs]
         self.x = np.random.rand(self.n_inputs)
 
-        # define weights and biases
-        # generate random wheights if no file is provided. else read the file
-        if w_file == None:
-            self.W_list = []
-            for (self.n_cur, self.n_next) in zip(self.n[:-1], self.n[1:]):
-                self.W_list.append(np.random.rand(self.n_next, self.n_cur))
-        else:
-            with open(w_file) as f:
-                lines = f.readlines()
-                self.W_list = [x.split('	') for x in lines]
-                self.W_list = [[float(n) for n in x] for x in self.W_list]
-                
-                f.close()
-        if b_file == None:
-            self.b_list = []
-            for (self.n_cur, self.n_next) in zip(self.n[:-1], self.n[1:]):
-                self.b_list.append(np.random.rand(self.n_next))
-        else: 
-            with open(b_file) as f:
-                lines = f.readlines()
-                self.b_list = [x.split('	') for x in lines]
-                self.b_list = [[float(n) for n in x] for x in self.W_list]
-                
-                f.close()
-        print(len(self.W_list[0]), len(self.b_list[0]), len(self.x))
-        print(len(self.W_list[-1]), len(self.b_list[-1]), len(self.x))
     def run(self):
-        print(f(self.W_list, self.b_list, self.x))
+        result = self.x
+        for n, W_file, b_file in zip(self.layers, self.W_file_list, self.b_file_list):
+            y = deepcopy(result)
+            l = n(y, W_file = W_file, b_file = b_file)
+            result = l.run()
+        return result
+class Layer:
+    def __init__(self, x, W_file, b_file):
+        self.x = x
+        files = read(W_file, b_file)
+        self.W = files.get('W')
+        self.b = files.get('b')
+
+    def run(self):
+        return layer(self.W,  self.x, self.b)
+
+def read(W_file, b_file):
+    return {'W': np.loadtxt(W_file), 'b': np.loadtxt(b_file)}
 
 # define activation function
 def sigma(y):
@@ -55,53 +44,9 @@ sigma_vec = np.vectorize(sigma)
 def layer(W, x, b):
     return sigma_vec(W @ x + b)
 
-# define neural network with all weights W and all biases b in W_list and b_list
-def f(W_list, b_list, x):
-    y = deepcopy(x) # deepcopy so that input is not changed
-    for W, b in zip(W_list, b_list):
-        y = layer(W, y, b) # call layer multiple times with all weights and biases
-    return y
-
 def main():
-    l = Layer()
-    l.run()
-    l2 = Layer(w_file = 'W_1.txt', b_file = 'b_1.txt')
-    l2.run()
-
-def gamle_greier():
-    # define dimensions
-    n_layers = 4
-    n_inputs = 64
-    n_outputs = 10
-    n = [n_inputs, 128, 128, n_outputs]
-
-    # define weights and biases
-    W_list = []
-    b_list = []
-    for (n_cur, n_next) in zip(n[:-1], n[1:]):
-        W_list.append(np.random.rand(n_next, n_cur))
-        b_list.append(np.random.rand(n_next))
-
-    # generate random input (this would usually be pixels of an image)
-    x = np.random.rand(n_inputs)
-
-    # call the network
-    print(f(W_list, b_list, x))
-
-    for W in W_list:
-        print(W.shape)
+    network = Network([Layer, Layer, Layer], ['W_1.txt', 'W_2.txt', 'W_3.txt'], ['b_1.txt', 'b_2.txt', 'b_3.txt'])
+    print(network.run())
 
 if __name__ == '__main__':
     main()
-    gamle_greier()
-
-
-
-
-
-
-
-
-
-
-