Compare commits
9 Commits
master
...
master_2.1
Author | SHA1 | Date | |
---|---|---|---|
|
06bf4fd57a | ||
|
a790f0ba5a | ||
|
be0f333181 | ||
|
1a0e89c1e7 | ||
4564030f27 | |||
|
5cfb8fdc21 | ||
|
ea24f48acc | ||
|
45a6113acf | ||
|
294c0fbf73 |
9
.vscode/settings.json
vendored
Normal file
@ -0,0 +1,9 @@
|
||||
{
|
||||
"python.analysis.extraPaths": [
|
||||
"./sources",
|
||||
"/usr/local/lib/python3.10/site-packages",
|
||||
"/Users/alexeybrown/development",
|
||||
"/Users/alexeybrown/development/flutter/",
|
||||
"./agent"
|
||||
]
|
||||
}
|
10
README.md
@ -1,10 +0,0 @@
|
||||
# si23traktor
|
||||
|
||||
Projekt zaliczeniowy przedmiotu Sztuczna Inteligencja w semestrze letnim 2023.
|
||||
|
||||
Skład zespołu:
|
||||
- Jakub Chmielecki
|
||||
- Mikołaj Mazur
|
||||
- Szymon Szczubkowski
|
||||
- Tobiasz Przybylski
|
||||
- Aliaksei Shauchenka
|
BIN
agent/.DS_Store
vendored
Normal file
BIN
agent/methods/.DS_Store
vendored
Normal file
BIN
agent/methods/__pycache__/a_star.cpython-310.pyc
Normal file
BIN
agent/methods/__pycache__/genetic_algorithm.cpython-310.pyc
Normal file
BIN
agent/methods/__pycache__/genetic_algorithm.cpython-311.pyc
Normal file
BIN
agent/methods/__pycache__/graph_search.cpython-310.pyc
Normal file
BIN
agent/methods/__pycache__/graph_search.cpython-311.pyc
Normal file
136
agent/methods/a_star.py
Normal file
@ -0,0 +1,136 @@
|
||||
class Node:
|
||||
def __init__(self, state, parent='', action='', distance=0):
|
||||
self.state = state
|
||||
self.parent = parent
|
||||
self.action = action
|
||||
self.distance = distance
|
||||
|
||||
class Search:
|
||||
def __init__(self, cell_size, cell_number):
|
||||
self.cell_size = cell_size
|
||||
self.cell_number = cell_number
|
||||
|
||||
def succ(self, state):
|
||||
x = state[0]
|
||||
y = state[1]
|
||||
angle = state[2]
|
||||
match(angle):
|
||||
case 'UP':
|
||||
possible = [['left', x, y, 'LEFT'], ['right', x, y, 'RIGHT']]
|
||||
if y != 0: possible.append(['move', x, y - 1, 'UP'])
|
||||
return possible
|
||||
case 'RIGHT':
|
||||
possible = [['left', x, y, 'UP'], ['right', x, y, 'DOWN']]
|
||||
if x != (self.cell_number-1): possible.append(['move', x + 1, y, 'RIGHT'])
|
||||
return possible
|
||||
case 'DOWN':
|
||||
possible = [['left', x, y, 'RIGHT'], ['right', x, y, 'LEFT']]
|
||||
if y != (self.cell_number-1): possible.append(['move', x, y + 1, 'DOWN'])
|
||||
return possible
|
||||
case 'LEFT':
|
||||
possible = [['left', x, y, 'DOWN'], ['right', x, y, 'UP']]
|
||||
if x != 0: possible.append(['move', x - 1, y, 'LEFT'])
|
||||
return possible
|
||||
|
||||
def cost(self, node, stones, goal, flowers):
|
||||
# cost = node.distance
|
||||
cost = 0
|
||||
# cost += 10 if stones[node.state[0], node.state[1]] == 1 else 1
|
||||
cost += 1000 if (node.state[0], node.state[1]) in stones else 1
|
||||
cost += 10 if ((node.state[0]), (node.state[1])) in flowers else 1
|
||||
|
||||
if node.parent:
|
||||
node = node.parent
|
||||
cost += node.distance # should return only elem.action in prod
|
||||
return cost
|
||||
|
||||
def heuristic(self, node, goal):
|
||||
return abs(node.state[0] - goal[0]) + abs(node.state[1] - goal[1])
|
||||
|
||||
#bandaid to know about stones
|
||||
def astarsearch(self, istate, goaltest, stone_list, plant_list):
|
||||
|
||||
#to be expanded
|
||||
def cost_old(x, y):
|
||||
if (x, y) in stones:
|
||||
return 10
|
||||
else:
|
||||
return 1
|
||||
|
||||
x = istate[0]
|
||||
y = istate[1]
|
||||
angle = istate[2]
|
||||
stones = []
|
||||
flowers = []
|
||||
|
||||
for obj in stone_list:
|
||||
stones.append((obj.xy[0]*50, obj.xy[1]*50))
|
||||
for obj in plant_list:
|
||||
if obj.name == 'flower':
|
||||
flowers.append((obj.xy[0]*50, obj.xy[1]*50))
|
||||
|
||||
# stones = [(x*50, y*50) for (x, y) in stone_list]
|
||||
# flowers = [(x*50, y*50) for (x, y) in plant_list]
|
||||
|
||||
print(stones)
|
||||
|
||||
# fringe = [(Node([x, y, angle]), cost_old(x, y))] # queue (moves/states to check)
|
||||
fringe = [(Node([x, y, angle]))] # queue (moves/states to check)
|
||||
fringe[0].distance = self.cost(fringe[0], stones, goaltest, flowers)
|
||||
fringe.append((Node([x, y, angle]), self.cost(fringe[0], stones, goaltest, flowers)))
|
||||
fringe.pop(0)
|
||||
|
||||
explored = []
|
||||
|
||||
while True:
|
||||
if len(fringe) == 0:
|
||||
return False
|
||||
|
||||
fringe.sort(key=lambda x: x[1])
|
||||
elem = fringe.pop(0)[0]
|
||||
|
||||
# if goal_test(elem.state):
|
||||
# return
|
||||
# print(elem.state[0], elem.state[1], elem.state[2])
|
||||
if elem.state[0] == goaltest[0] and elem.state[1] == goaltest[1]: # checks if we reached the given point
|
||||
steps = []
|
||||
while elem.parent:
|
||||
steps.append([elem.action, elem.state[0], elem.state[1]]) # should return only elem.action in prod
|
||||
elem = elem.parent
|
||||
|
||||
steps.reverse()
|
||||
print(steps) # only for dev
|
||||
return steps
|
||||
|
||||
explored.append(elem.state)
|
||||
|
||||
for (action, state_x, state_y, state_angle) in self.succ(elem.state):
|
||||
x = Node([state_x, state_y, state_angle], elem, action)
|
||||
x.parent = elem
|
||||
|
||||
priority = self.cost(elem, stones, goaltest, flowers) + self.heuristic(elem, goaltest)
|
||||
elem.distance = priority
|
||||
# priority = cost_old(x, y) + self.heuristic(elem, goaltest)
|
||||
fringe_states = [node.state for (node, p) in fringe]
|
||||
|
||||
if x.state not in fringe_states and x.state not in explored:
|
||||
fringe.append((x, priority))
|
||||
elif x.state in fringe_states:
|
||||
for i in range(len(fringe)):
|
||||
if fringe[i][0].state == x.state:
|
||||
if fringe[i][1] > priority:
|
||||
fringe[i] = (x, priority)
|
||||
|
||||
|
||||
def closest_point(self, x, y, name, plant_list):
|
||||
self.max_distance = self.cell_number*self.cell_number
|
||||
for obj in plant_list:
|
||||
if obj.name == name:
|
||||
if obj.state == 0:
|
||||
self.distance = (abs(obj.xy[0] - x) + abs(obj.xy[1] - y))
|
||||
if self.distance <= self.max_distance:
|
||||
self.max_distance = self.distance
|
||||
x_close = obj.xy[0]
|
||||
y_close = obj.xy[1]
|
||||
#print("distance: ",self.distance, obj.xy[0], "+", obj.xy[1], "-" ,x, "+",y)
|
||||
return (x_close, y_close)
|
113
agent/methods/genetic_algorithm.py
Normal file
@ -0,0 +1,113 @@
|
||||
import numpy as np
|
||||
import random
|
||||
import math
|
||||
|
||||
def create_initial_population(num_cities, population_size, list):
|
||||
population = []
|
||||
for _ in range(population_size):
|
||||
chromosome = list.copy()
|
||||
chromosome.remove((1, 1)) # Usuń punkt (1, 1) z listy
|
||||
random.shuffle(chromosome)
|
||||
chromosome.insert(0, (1, 1)) # Dodaj punkt (1, 1) na początku trasy
|
||||
population.append(chromosome)
|
||||
return population
|
||||
|
||||
def calculate_distance(city1, city2):
|
||||
x1, y1 = city1
|
||||
x2, y2 = city2
|
||||
distance = math.sqrt((x2 - x1) ** 2 + (y2 - y1) ** 2)
|
||||
return distance
|
||||
|
||||
def calculate_fitness(individual):
|
||||
total_distance = 0
|
||||
|
||||
num_cities = len(individual)
|
||||
|
||||
for i in range(num_cities - 1):
|
||||
city1 = individual[i]
|
||||
city2 = individual[i + 1]
|
||||
distance = calculate_distance(city1, city2)
|
||||
total_distance += distance
|
||||
|
||||
fitness = 1 / total_distance
|
||||
|
||||
return fitness
|
||||
|
||||
def crossover(parent1, parent2):
|
||||
child = [(1, 1)] + [None] * (len(parent1) - 1) # Inicjalizacja dziecka z punktem (1, 1) na początku
|
||||
start_index = random.randint(1, len(parent1) - 1)
|
||||
end_index = random.randint(start_index + 1, len(parent1))
|
||||
# Skopiuj fragment miast od parent1 do dziecka
|
||||
child[start_index:end_index] = parent1[start_index:end_index]
|
||||
# Uzupełnij brakujące miasta z parent2
|
||||
remaining_cities = [city for city in parent2 if city not in child]
|
||||
child[1:start_index] = remaining_cities[:start_index - 1]
|
||||
child[end_index:] = remaining_cities[start_index - 1:]
|
||||
return child
|
||||
|
||||
def mutate(individual, mutation_rate):
|
||||
for i in range(1, len(individual)): # Rozpoczynamy od indeksu 1, aby pominąć punkt (1, 1)
|
||||
if random.random() < mutation_rate:
|
||||
j = random.randint(1, len(individual) - 1) # Wybieramy indeks od 1 do ostatniego indeksu
|
||||
individual[i], individual[j] = individual[j], individual[i]
|
||||
return individual
|
||||
|
||||
def genetic_algorithm(list):
|
||||
chromosome_length = 21
|
||||
max_generations = 200
|
||||
population_size = 200
|
||||
crossover_rate = 0.25
|
||||
mutation_rate = 0.1
|
||||
num_cities = chromosome_length
|
||||
population = create_initial_population(num_cities, population_size, list)
|
||||
|
||||
best_individual = None
|
||||
best_fitness = float('-inf')
|
||||
|
||||
for generation in range(max_generations):
|
||||
# # Oblicz wartości fitness dla każdego osobnika w populacji
|
||||
# fitness_values = [calculate_fitness(individual) for individual in population]
|
||||
# population = [x for _, x in sorted(zip(fitness_values, population), reverse=True)]
|
||||
# fitness_values.sort(reverse=True)
|
||||
# max_fitness_index = np.argmax(fitness_values)
|
||||
# # Wybierz najlepszego osobnika z ostatniej populacji
|
||||
# if fitness_values[max_fitness_index] > best_fitness:
|
||||
# best_fitness = fitness_values[max_fitness_index]
|
||||
# best_individual = population[max_fitness_index]
|
||||
|
||||
# # Twórz nową populację z krzyżówek
|
||||
# new_population = []
|
||||
# for _ in range(int(population_size / 2)):
|
||||
# parent1, parent2 = random.choices(population[:population_size // 2], k=2)
|
||||
# child1 = crossover(parent1, parent2)
|
||||
# child2 = crossover(parent2, parent1)
|
||||
# new_population.extend([child1, child2])
|
||||
# # Dokonaj mutacji na nowej populacji
|
||||
# new_population = [mutate(individual, mutation_rate) for individual in new_population]
|
||||
# population = new_population
|
||||
|
||||
# Oblicz wartości fitness dla każdego osobnika w populacji
|
||||
fitness_values = [calculate_fitness(individual) for individual in population]
|
||||
population = [x for _, x in sorted(zip(fitness_values, population), reverse=True)]
|
||||
fitness_values.sort(reverse=True)
|
||||
best_individuals = population[:10] # Wybierz k najlepszych osobników
|
||||
new_population = best_individuals.copy()
|
||||
|
||||
# Twórz nową populację z krzyżówek i mutacji
|
||||
while len(new_population) < population_size:
|
||||
parent1, parent2 = random.choices(best_individuals, k=2) # Wybierz rodziców spośród najlepszych osobników
|
||||
child = crossover(parent1, parent2) # Krzyżowanie
|
||||
child = mutate(child, mutation_rate) # Mutacja
|
||||
new_population.append(child)
|
||||
|
||||
for individual in best_individuals:
|
||||
fitness = calculate_fitness(individual)
|
||||
if fitness > best_fitness:
|
||||
best_fitness = fitness
|
||||
best_individual = individual
|
||||
|
||||
population = new_population[:population_size]
|
||||
|
||||
|
||||
print("Best path:", best_individual)
|
||||
return best_individual
|
73
agent/methods/graph_search.py
Normal file
@ -0,0 +1,73 @@
|
||||
class Node:
|
||||
def __init__(self, state, parent='', action=''):
|
||||
self.state = state
|
||||
self.parent = parent
|
||||
self.action = action
|
||||
|
||||
|
||||
class Search:
|
||||
def __init__(self, cell_size, cell_number):
|
||||
self.cell_size = cell_size
|
||||
self.cell_number = cell_number
|
||||
|
||||
def succ(self, state):
|
||||
x = state[0]
|
||||
y = state[1]
|
||||
angle = state[2]
|
||||
match(angle):
|
||||
case 'UP':
|
||||
possible = [['left', x, y, 'LEFT'], ['right', x, y, 'RIGHT']]
|
||||
if y != 0: possible.append(['move', x, y - self.cell_size, 'UP'])
|
||||
return possible
|
||||
case 'RIGHT':
|
||||
possible = [['left', x, y, 'UP'], ['right', x, y, 'DOWN']]
|
||||
if x != self.cell_size*(self.cell_number-1): possible.append(['move', x + self.cell_size, y, 'RIGHT'])
|
||||
return possible
|
||||
case 'DOWN':
|
||||
possible = [['left', x, y, 'RIGHT'], ['right', x, y, 'LEFT']]
|
||||
if y != self.cell_size*(self.cell_number-1): possible.append(['move', x, y + self.cell_size, 'DOWN'])
|
||||
return possible
|
||||
case 'LEFT':
|
||||
possible = [['left', x, y, 'DOWN'], ['right', x, y, 'UP']]
|
||||
if x != 0: possible.append(['move', x - self.cell_size, y, 'LEFT'])
|
||||
return possible
|
||||
|
||||
def graphsearch(self, istate, goaltest):
|
||||
x = istate[0]
|
||||
y = istate[1]
|
||||
angle = istate[2]
|
||||
|
||||
fringe = [Node([x, y, angle])] # queue (moves/states to check)
|
||||
fringe_state = [fringe[0].state]
|
||||
explored = []
|
||||
|
||||
while True:
|
||||
if len(fringe) == 0:
|
||||
return False
|
||||
|
||||
elem = fringe.pop(0)
|
||||
fringe_state.pop(0)
|
||||
|
||||
# if goal_test(elem.state):
|
||||
# return
|
||||
# print(elem.state[0], elem.state[1], elem.state[2])
|
||||
if elem.state[0] == goaltest[0] and elem.state[1] == goaltest[1]: # checks if we reached the given point
|
||||
steps = []
|
||||
while elem.parent:
|
||||
steps.append([elem.action, elem.state[0], elem.state[1]]) # should return only elem.action in prod
|
||||
elem = elem.parent
|
||||
|
||||
steps.reverse()
|
||||
print(steps) # only for dev
|
||||
return steps
|
||||
|
||||
explored.append(elem.state)
|
||||
|
||||
for (action, state_x, state_y, state_angle) in self.succ(elem.state):
|
||||
if [state_x, state_y, state_angle] not in fringe_state and \
|
||||
[state_x, state_y, state_angle] not in explored:
|
||||
x = Node([state_x, state_y, state_angle])
|
||||
x.parent = elem
|
||||
x.action = action
|
||||
fringe.append(x)
|
||||
fringe_state.append(x.state)
|
BIN
agent/neural_network/.DS_Store
vendored
Normal file
BIN
agent/neural_network/__pycache__/inference.cpython-310.pyc
Normal file
BIN
agent/neural_network/__pycache__/inference.cpython-311.pyc
Normal file
BIN
agent/neural_network/__pycache__/model.cpython-310.pyc
Normal file
BIN
agent/neural_network/__pycache__/model.cpython-311.pyc
Normal file
BIN
agent/neural_network/images/.DS_Store
vendored
Normal file
BIN
agent/neural_network/images/test/.DS_Store
vendored
Normal file
BIN
agent/neural_network/images/test/Bean/0001.jpg
Normal file
After Width: | Height: | Size: 58 KiB |
BIN
agent/neural_network/images/test/Bean/0002.jpg
Normal file
After Width: | Height: | Size: 20 KiB |
BIN
agent/neural_network/images/test/Bean/0003.jpg
Normal file
After Width: | Height: | Size: 11 KiB |
BIN
agent/neural_network/images/test/Bean/0004.jpg
Normal file
After Width: | Height: | Size: 10 KiB |
BIN
agent/neural_network/images/test/Bean/0005.jpg
Normal file
After Width: | Height: | Size: 17 KiB |
BIN
agent/neural_network/images/test/Bean/0006.jpg
Normal file
After Width: | Height: | Size: 21 KiB |
BIN
agent/neural_network/images/test/Bean/0007.jpg
Normal file
After Width: | Height: | Size: 46 KiB |
BIN
agent/neural_network/images/test/Bean/0008.jpg
Normal file
After Width: | Height: | Size: 28 KiB |
BIN
agent/neural_network/images/test/Bean/0009.jpg
Normal file
After Width: | Height: | Size: 60 KiB |
BIN
agent/neural_network/images/test/Bean/0010.jpg
Normal file
After Width: | Height: | Size: 11 KiB |
BIN
agent/neural_network/images/test/Bean/0011.jpg
Normal file
After Width: | Height: | Size: 60 KiB |
BIN
agent/neural_network/images/test/Bean/0012.jpg
Normal file
After Width: | Height: | Size: 65 KiB |
BIN
agent/neural_network/images/test/Bean/0013.jpg
Normal file
After Width: | Height: | Size: 64 KiB |
BIN
agent/neural_network/images/test/Bean/0014.jpg
Normal file
After Width: | Height: | Size: 22 KiB |
BIN
agent/neural_network/images/test/Bean/0015.jpg
Normal file
After Width: | Height: | Size: 12 KiB |
BIN
agent/neural_network/images/test/Bean/0016.jpg
Normal file
After Width: | Height: | Size: 7.5 KiB |
BIN
agent/neural_network/images/test/Bean/0017.jpg
Normal file
After Width: | Height: | Size: 19 KiB |
BIN
agent/neural_network/images/test/Bean/0018.jpg
Normal file
After Width: | Height: | Size: 22 KiB |
BIN
agent/neural_network/images/test/Bean/0019.jpg
Normal file
After Width: | Height: | Size: 69 KiB |
BIN
agent/neural_network/images/test/Bean/0020.jpg
Normal file
After Width: | Height: | Size: 17 KiB |
BIN
agent/neural_network/images/test/Bean/0021.jpg
Normal file
After Width: | Height: | Size: 18 KiB |
BIN
agent/neural_network/images/test/Bean/0022.jpg
Normal file
After Width: | Height: | Size: 21 KiB |
BIN
agent/neural_network/images/test/Bean/0100.jpg
Normal file
After Width: | Height: | Size: 12 KiB |
BIN
agent/neural_network/images/test/Bean/0101.jpg
Normal file
After Width: | Height: | Size: 19 KiB |
BIN
agent/neural_network/images/test/Bean/0102.jpg
Normal file
After Width: | Height: | Size: 23 KiB |
BIN
agent/neural_network/images/test/Bean/0103.jpg
Normal file
After Width: | Height: | Size: 18 KiB |
BIN
agent/neural_network/images/test/Bean/0104.jpg
Normal file
After Width: | Height: | Size: 19 KiB |
BIN
agent/neural_network/images/test/Bean/0105.jpg
Normal file
After Width: | Height: | Size: 62 KiB |
BIN
agent/neural_network/images/test/Bean/0106.jpg
Normal file
After Width: | Height: | Size: 22 KiB |
BIN
agent/neural_network/images/test/Bean/0107.jpg
Normal file
After Width: | Height: | Size: 34 KiB |
BIN
agent/neural_network/images/test/Bean/0108.jpg
Normal file
After Width: | Height: | Size: 20 KiB |
BIN
agent/neural_network/images/test/Bean/0109.jpg
Normal file
After Width: | Height: | Size: 16 KiB |
BIN
agent/neural_network/images/test/Bean/0110.jpg
Normal file
After Width: | Height: | Size: 44 KiB |
BIN
agent/neural_network/images/test/Bean/0111.jpg
Normal file
After Width: | Height: | Size: 22 KiB |
BIN
agent/neural_network/images/test/Bean/0112.jpg
Normal file
After Width: | Height: | Size: 11 KiB |
BIN
agent/neural_network/images/test/Bean/0113.jpg
Normal file
After Width: | Height: | Size: 11 KiB |
BIN
agent/neural_network/images/test/Bean/0114.jpg
Normal file
After Width: | Height: | Size: 46 KiB |
BIN
agent/neural_network/images/test/Bean/0115.jpg
Normal file
After Width: | Height: | Size: 34 KiB |
BIN
agent/neural_network/images/test/Bean/0116.jpg
Normal file
After Width: | Height: | Size: 19 KiB |
BIN
agent/neural_network/images/test/Bean/0117.jpg
Normal file
After Width: | Height: | Size: 53 KiB |
BIN
agent/neural_network/images/test/Bean/0118.jpg
Normal file
After Width: | Height: | Size: 12 KiB |
BIN
agent/neural_network/images/test/Bean/0119.jpg
Normal file
After Width: | Height: | Size: 17 KiB |
BIN
agent/neural_network/images/test/Bean/0120.jpg
Normal file
After Width: | Height: | Size: 10 KiB |
BIN
agent/neural_network/images/test/Bean/0121.jpg
Normal file
After Width: | Height: | Size: 20 KiB |
BIN
agent/neural_network/images/test/Bean/0122.jpg
Normal file
After Width: | Height: | Size: 20 KiB |
BIN
agent/neural_network/images/test/Bean/0123.jpg
Normal file
After Width: | Height: | Size: 23 KiB |
BIN
agent/neural_network/images/test/Bean/0124.jpg
Normal file
After Width: | Height: | Size: 41 KiB |
BIN
agent/neural_network/images/test/Bean/0125.jpg
Normal file
After Width: | Height: | Size: 18 KiB |
BIN
agent/neural_network/images/test/Bean/0126.jpg
Normal file
After Width: | Height: | Size: 64 KiB |
BIN
agent/neural_network/images/test/Bean/0127.jpg
Normal file
After Width: | Height: | Size: 18 KiB |
BIN
agent/neural_network/images/test/Bean/0128.jpg
Normal file
After Width: | Height: | Size: 19 KiB |
BIN
agent/neural_network/images/test/Bean/0129.jpg
Normal file
After Width: | Height: | Size: 49 KiB |
BIN
agent/neural_network/images/test/Bean/0130.jpg
Normal file
After Width: | Height: | Size: 8.9 KiB |
BIN
agent/neural_network/images/test/Bean/0131.jpg
Normal file
After Width: | Height: | Size: 7.6 KiB |
BIN
agent/neural_network/images/test/Bean/0132.jpg
Normal file
After Width: | Height: | Size: 48 KiB |
BIN
agent/neural_network/images/test/Bean/0133.jpg
Normal file
After Width: | Height: | Size: 44 KiB |
BIN
agent/neural_network/images/test/Bean/0134.jpg
Normal file
After Width: | Height: | Size: 24 KiB |
BIN
agent/neural_network/images/test/Bean/0135.jpg
Normal file
After Width: | Height: | Size: 12 KiB |
BIN
agent/neural_network/images/test/Bean/0136.jpg
Normal file
After Width: | Height: | Size: 20 KiB |
BIN
agent/neural_network/images/test/Bean/0137.jpg
Normal file
After Width: | Height: | Size: 12 KiB |
BIN
agent/neural_network/images/test/Bean/0138.jpg
Normal file
After Width: | Height: | Size: 66 KiB |
BIN
agent/neural_network/images/test/Bean/0139.jpg
Normal file
After Width: | Height: | Size: 21 KiB |
BIN
agent/neural_network/images/test/Bean/0140.jpg
Normal file
After Width: | Height: | Size: 66 KiB |
BIN
agent/neural_network/images/test/Bean/0141.jpg
Normal file
After Width: | Height: | Size: 13 KiB |
BIN
agent/neural_network/images/test/Bean/0142.jpg
Normal file
After Width: | Height: | Size: 65 KiB |
BIN
agent/neural_network/images/test/Bean/0143.jpg
Normal file
After Width: | Height: | Size: 60 KiB |
BIN
agent/neural_network/images/test/Bean/0144.jpg
Normal file
After Width: | Height: | Size: 70 KiB |
BIN
agent/neural_network/images/test/Bean/0145.jpg
Normal file
After Width: | Height: | Size: 22 KiB |
BIN
agent/neural_network/images/test/Bean/0146.jpg
Normal file
After Width: | Height: | Size: 20 KiB |
BIN
agent/neural_network/images/test/Bean/0147.jpg
Normal file
After Width: | Height: | Size: 9.5 KiB |
BIN
agent/neural_network/images/test/Bean/0148.jpg
Normal file
After Width: | Height: | Size: 64 KiB |
BIN
agent/neural_network/images/test/Bean/0149.jpg
Normal file
After Width: | Height: | Size: 36 KiB |
BIN
agent/neural_network/images/test/Bean/0150.jpg
Normal file
After Width: | Height: | Size: 8.8 KiB |
BIN
agent/neural_network/images/test/Bean/0151.jpg
Normal file
After Width: | Height: | Size: 20 KiB |
BIN
agent/neural_network/images/test/Bean/0152.jpg
Normal file
After Width: | Height: | Size: 11 KiB |