def main():
show_img("resources/i1geographical_urban.jpg")
time.sleep(3)
simulate_num = 160
mycarly_types = [None, None, None, None]
mycarly_types[0] = int(simulate_num * 0.35)
mycarly_types[1] = int(simulate_num * 0.30)
mycarly_types[2] = int(simulate_num * 0.20)
mycarly_types[3] = int(simulate_num * 0.15)
print("mycarly_types=", mycarly_types)
mydict = {}
visual_data = []
for i in range(len(unit_types)):
print("city_types =", i, "\n")
generated_map = unit_types[i]
for mycarly_type in range(len(mycarly_types)):
car_setting = CarSetting(mycarly_type)
car_setting.myprint()
scores = []
for j in range(mycarly_types[mycarly_type]):
score = single_turn(i, generated_map, car_setting)
scores.append(score)
# time.sleep(random.uniform(0.1, 0.8))
mydict[i, mycarly_type] = scores
print("\n" * 3)
welcome = colored(
"#" * 10 + " This statistics:" + "#" * 10, "red", attrs=["reverse", "blink"]
)
print(welcome, "\n")
time.sleep(0.5)
for i in range(len(unit_types)):
type_data = []
for mycarly_type in range(len(mycarly_types)):
print(
"city type ",
i,
" with mycar_type ",
mycarly_type,
" simulate scores:",
mydict[i, mycarly_type],
)
x = round(statistics.mean(mydict[i, mycarly_type]), 2)
# 数据的总体方差
p = round(statistics.pvariance(mydict[i, mycarly_type]), 2)
print(colored("mean simulate scores =", "red"), x)
print(colored("pvariance simulate scores =", "blue"), p)
type_data.append(x)
# time.sleep(random.uniform(0.1, 0.5))
visual_data.append(type_data)
visual_to_png(visual_data)
i2simulator.main(visual_data)
def main():
show_img("resources/i1geographical_urban.jpg")
time.sleep(3)
simulate_num = 160
mycarly_types = [None, None, None, None]
mycarly_types[0] = int(simulate_num * 0.35)
mycarly_types[1] = int(simulate_num * 0.30)
mycarly_types[2] = int(simulate_num * 0.20)
mycarly_types[3] = int(simulate_num * 0.15)
print('mycarly_types=', mycarly_types)
mydict = {}
visual_data = []
for i in range(len(unit_types)):
print('city_types =', i, '\n')
generated_map = unit_types[i]
for mycarly_type in range(len(mycarly_types)):
car_setting = CarSetting(mycarly_type)
car_setting.myprint()
scores = []
for j in range(mycarly_types[mycarly_type]):
score = single_turn(i, generated_map, car_setting)
scores.append(score)
time.sleep(random.uniform(0.1, 0.8))
mydict[i, mycarly_type] = scores
print('\n' * 3)
welcome = colored('#' * 10 + ' This statistics:' + '#' * 10,
'red',
attrs=['reverse', 'blink'])
print(welcome, '\n')
time.sleep(0.5)
for i in range(len(unit_types)):
type_data = []
for mycarly_type in range(len(mycarly_types)):
print('city type ', i, ' with mycar_type ', mycarly_type,
' simulate scores:', mydict[i, mycarly_type])
x = round(statistics.mean(mydict[i, mycarly_type]), 2)
# 数据的总体方差
p = round(statistics.pvariance(mydict[i, mycarly_type]), 2)
print(colored('mean simulate scores =', 'red'), x)
print(colored('pvariance simulate scores =', 'blue'), p)
type_data.append(x)
# time.sleep(random.uniform(0.1, 0.5))
visual_data.append(type_data)
visual_to_png(visual_data)
i2simulator.main(visual_data)
def train(dataLoader, model, crit, optimizer, epoch, lr, wd):
for i, (input_tensor, target) in enumerate(dataLoader):
if i == 0:
show_img(input_tensor[0:9], label=target[0:9])
losses = AverageMeter()
# switch to train mode
model.train()
# create an optimizer for the last fc layer
optimizer_tl = torch.optim.SGD(
model.top_layer.parameters(),
lr=lr,
weight_decay=10**wd,
)
target = target.cuda(non_blocking=True)
input_var = torch.autograd.Variable(input_tensor.cuda())
#input_var = torch.autograd.Variable(input_tensor)
target_var = torch.autograd.Variable(target)
output = model(input_var)
# print(target.clone().detach().cpu().numpy())
#print(output.clone().detach().cpu().numpy().shape)
loss = crit(output, target_var)
# record loss
#print(loss)
losses.update(loss.data, input_tensor.size(0))
# compute gradient and do SGD step
optimizer.zero_grad()
optimizer_tl.zero_grad()
loss.backward()
optimizer.step()
optimizer_tl.step()
return losses.avg
m = 1
if m == 0:
road_2d_matrix[1][local + 1] = road_2d_matrix[way][local]
road_2d_matrix[way][local] = 0
leng[way] = leng[way] - 1
leng[1] = leng[1] + 1
cell2[1][local + 1] = cell2[way][local]
cell2[way][local] = 0
if m == 0:
return 0
else:
return 1
if __name__ == "__main__":
show_img("resources/i1geographical_urban.jpg")
time.sleep(1)
show_simplify_to_path()
length = 3
width = 30
d = 0
cell = np.zeros((length, width), int)
road_2d_matrix = copy.deepcopy(cell)
cell2 = copy.deepcopy(cell)
for i in range(0, length):
for j in range(0, width):
road_2d_matrix[i][j] = 0