def main():
# ------------------------------------------------ Training Phase ------------------------------------------------
# image_files = random.sample(glob.glob('E:\\work\\pedestrian_crop_python_process\\Pedestrain_cropDB\\train\\0\\*.bmp'), 10)
# image_files = random.sample(glob.glob('data/0.normal/*.bmp'), 10)
# data_in = data_read(image_files)
opt = Options().parse()
opt.iwidth = map_x_size
opt.iheight = map_y_size
#---new--- depth for size
ctinit = map_x_size
while ctinit > 4:
ctinit = ctinit / 2
opt.ctinit = int(ctinit)
#---new---
opt.batchsize = 64
opt.epochs = 1000
opt.mask = 0 # 1: masking for simulation map
opt.time = datetime.now()
train_dataloader = load_data(
'./data/unsupervised/train/') # path to trainset
result_path = './results/{0}/'.format(
opt.time) # reconstructions durnig the training
if not os.path.isdir(result_path):
os.mkdir(result_path)
# dataloader = load_data(opt, data_in)
model = AAE_basic(opt, train_dataloader)
model.train()
map_x_size = 64
map_y_size = 64
map_layer_num = 3
opt = Options().parse()
opt.iwidth = map_x_size
opt.iheight = map_y_size
opt.batchsize = 1
opt.ngpu = 0
opt.gpu_ids = -1
# ---new---
ctinit = map_x_size
while ctinit > 4:
ctinit = ctinit / 2
opt.ctinit = int(ctinit)
# ---new---
# opt.mask = 1
model_saved = False
d_loss = None
g_loss = None
recon_loss = None
z_loss = None
N = 1000
fake = None
P = None
Q = None
D = None