def load_models(directory):
generator = model.GlobalGenerator(n_downsampling=2, n_blocks=6)
gen_name = os.path.join(directory, 'final_generator.pth')
if os.path.isfile(gen_name):
gen_dict = torch.load(gen_name)
generator.load_state_dict(gen_dict)
return generator.to(device)
def load_models(directory, batch_num):
generator = model.GlobalGenerator()
discriminator = model.NLayerDiscriminator(input_nc=3)
gen_name = os.path.join(directory, '%05d_generator.pth' % batch_num)
dis_name = os.path.join(directory, '%05d_discriminator.pth' % batch_num)
if os.path.isfile(gen_name) and os.path.isfile(dis_name):
gen_dict = torch.load(gen_name)
dis_dict = torch.load(dis_name)
generator.load_state_dict(gen_dict)
discriminator.load_state_dict(dis_dict)
print('Models loaded, resume training from batch %05d...' % batch_num)
else:
print('Cannot find saved models, start training from scratch...')
batch_num = 0
return generator, discriminator, batch_num
def load_models(directory, batch_num):
# 20180924: smaller network.
generator = model.GlobalGenerator(n_downsampling=2, n_blocks=6)
discriminator = model.NLayerDiscriminator(input_nc=3, n_layers=3) # 48 input
gen_name = os.path.join(directory, '%05d_generator.pth' % batch_num)
dis_name = os.path.join(directory, '%05d_discriminator.pth' % batch_num)
if os.path.isfile(gen_name) and os.path.isfile(dis_name):
gen_dict = torch.load(gen_name)
dis_dict = torch.load(dis_name)
generator.load_state_dict(gen_dict)
discriminator.load_state_dict(dis_dict)
print('Models loaded, resume training from batch %05d...' % batch_num)
else:
print('Cannot find saved models, start training from scratch...')
batch_num = 0
return generator, discriminator, batch_num