def load_net(self, net_name, set_net_version=None):
net_path = os.path.join(self.trained_nets_path, net_name, 'model_dir', 'dynamic_net.pth')
temp_opt = config.get_configurations()
opt_path = os.path.join(self.trained_nets_path, net_name, 'config.txt')
if os.path.exists(opt_path):
opt = utils.read_config_and_arrange_opt(opt_path, temp_opt)
else:
opt = temp_opt
self.main_widget.dynamic_model = InferenceModel(opt, set_net_version=set_net_version)
self.main_widget.dynamic_model.load_network(net_path)
def setup(opts):
ckpt = opts["style_dir"]
model_path = ckpt + "/" + "model_dir/dynamic_net.pth"
config_path = ckpt + "/" + "config.json"
conf = json.load(open(config_path))
set_net_version = conf["network_type"]
opt = config.get_configurations()
dynamic_model = InferenceModel(opt, set_net_version=set_net_version)
dynamic_model.load_network(model_path)
return {"dynamic_model" : dynamic_model,
"network_type" : set_net_version }
parser = argparse.ArgumentParser()
parser.add_argument('--network_name', default=network_name)
parser.add_argument('--num_of_images', default=num_of_images, type=int)
inference_opt = parser.parse_args()
network_name = inference_opt.network_name
num_of_images = inference_opt.num_of_images
networks_path = os.path.join('trained_nets', network_name)
model_path = os.path.join(networks_path, 'model_dir', 'dynamic_net.pth')
config_path = os.path.join(networks_path, 'config.txt')
save_path = os.path.join('results', 'inference_results')
if not os.path.exists(save_path):
utils.make_dirs(save_path)
opt = config.get_configurations(parser=parser)
if os.path.exists(config_path):
utils.read_config_and_arrange_opt(config_path, opt)
dynamic_model = InferenceModel(opt)
dynamic_model.load_network(model_path)
dynamic_model.net.train()
to_tensor = transforms.ToTensor()
to_pil_image = transforms.ToPILImage()
first_image = True
input_tensor = torch.randn((128, dynamic_model.opt.z_size)).view(-1, dynamic_model.opt.z_size, 1, 1).to(dynamic_model.device)
for alpha in tqdm(alphas):
output_tensor = dynamic_model.forward_and_recover(input_tensor.requires_grad_(False), alpha=alpha)
#!/usr/bin/env python
import os
#BA modules
import log
import git
#import render
import config
#import template
import cli
import run
import notifications
if __name__ == '__main__':
# Brief sketch follows
args = cli.parse_cli()
configs = config.get_configurations(os.getcwd())
run.run_process(args, configs)
import config
from models.bank_model import BankModel
opt = config.get_configurations()
if __name__ == "__main__":
model = BankModel(opt)
model.init_paths()
model.write_config()
if opt.training_scheme == 'all':
model.train(main_training=True)
print('Trained main network')
model.net.loop_count = 2
model.train(main_training=False)
print('Trained bank network')
elif opt.training_scheme == 'bank':
model.net.loop_count = 2
model.load_pre_trained()
model.train(main_training=False)
print('Trained bank network')
elif opt.training_scheme == 'main':
model.train(main_training=True)
print('Trained main network')