Spaces:
Sleeping
Sleeping
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import streamlit as st
|
2 |
+
import numpy as np
|
3 |
+
import torch
|
4 |
+
import torch.nn as nn
|
5 |
+
import random
|
6 |
+
|
7 |
+
# Define the function to optimize
|
8 |
+
def f(x):
|
9 |
+
return x**2
|
10 |
+
|
11 |
+
# Define the neural network
|
12 |
+
class Net(nn.Module):
|
13 |
+
def __init__(self):
|
14 |
+
super(Net, self).__init__()
|
15 |
+
self.fc1 = nn.Linear(1, 10)
|
16 |
+
self.fc2 = nn.Linear(10, 1)
|
17 |
+
|
18 |
+
def forward(self, x):
|
19 |
+
x = torch.relu(self.fc1(x))
|
20 |
+
x = self.fc2(x)
|
21 |
+
return x
|
22 |
+
|
23 |
+
# Define the genetic algorithm
|
24 |
+
class GeneticAlgorithm:
|
25 |
+
def __init__(self, population_size):
|
26 |
+
self.population_size = population_size
|
27 |
+
self.population = [random.uniform(-10, 10) for _ in range(population_size)]
|
28 |
+
|
29 |
+
def selection(self):
|
30 |
+
self.population = sorted(self.population, key=lambda x: f(x), reverse=True)[:self.population_size//2]
|
31 |
+
|
32 |
+
def crossover(self):
|
33 |
+
offspring = []
|
34 |
+
for _ in range(self.population_size//2):
|
35 |
+
parent1, parent2 = random.sample(self.population, 2)
|
36 |
+
child = (parent1 + parent2) / 2
|
37 |
+
offspring.append(child)
|
38 |
+
self.population += offspring
|
39 |
+
|
40 |
+
def mutation(self):
|
41 |
+
for i in range(self.population_size):
|
42 |
+
if random.random() < 0.1:
|
43 |
+
self.population[i] += random.uniform(-1, 1)
|
44 |
+
|
45 |
+
# Streamlit app
|
46 |
+
st.title("Neural Network vs Genetic Algorithm")
|
47 |
+
|
48 |
+
# Parameters
|
49 |
+
st.sidebar.header("Parameters")
|
50 |
+
population_size = st.sidebar.slider("Population size", 10, 100, 50)
|
51 |
+
nn_iterations = st.sidebar.slider("Neural network iterations", 10, 1000, 100)
|
52 |
+
ga_iterations = st.sidebar.slider("Genetic algorithm iterations", 10, 100, 50)
|
53 |
+
|
54 |
+
# Run the experiment
|
55 |
+
if st.button("Run experiment"):
|
56 |
+
# Initialize the neural network and genetic algorithm
|
57 |
+
net = Net()
|
58 |
+
criterion = nn.MSELoss()
|
59 |
+
optimizer = torch.optim.Adam(net.parameters(), lr=0.01)
|
60 |
+
ga = GeneticAlgorithm(population_size)
|
61 |
+
|
62 |
+
# Train the neural network
|
63 |
+
nn_losses = []
|
64 |
+
for i in range(nn_iterations):
|
65 |
+
x = torch.randn(1, 1)
|
66 |
+
y = f(x)
|
67 |
+
y_pred = net(x)
|
68 |
+
loss = criterion(y_pred, y)
|
69 |
+
optimizer.zero_grad()
|
70 |
+
loss.backward()
|
71 |
+
optimizer.step()
|
72 |
+
nn_losses.append(loss.item())
|
73 |
+
|
74 |
+
# Run the genetic algorithm
|
75 |
+
ga_values = []
|
76 |
+
for i in range(ga_iterations):
|
77 |
+
ga.selection()
|
78 |
+
ga.crossover()
|
79 |
+
ga.mutation()
|
80 |
+
ga_values.append(max(map(f, ga.population)))
|
81 |
+
|
82 |
+
# Plot the results
|
83 |
+
st.line_chart({"Neural Network": nn_losses, "Genetic Algorithm": ga_values})
|
84 |
+
|
85 |
+
# Print the final values
|
86 |
+
st.write("Final neural network value:", nn_losses[-1])
|
87 |
+
st.write("Final genetic algorithm value:", ga_values[-1])
|