fig = utility.plot(fake_image)
plt.savefig(os.path.join(args.output, 'fake_cgan.png'),
bbox_inches='tight')
plt.close(fig)
elif args.model_net == 'DCGAN':
noise_data = np.random.uniform(low=-1.0,
high=1.0,
size=[args.n_samples, args.noise_size
]).astype('float32')
noise_tensor = fluid.LoDTensor()
noise_tensor.set(noise_data, place)
fake_temp = exe.run(fetch_list=[fake.name],
feed={"noise": noise_tensor})[0]
fake_image = np.reshape(fake_temp, (args.n_samples, -1))
fig = utility.plot(fake_image)
plt.savefig(os.path.join(args.output, 'fake_dcgan.png'),
bbox_inches='tight')
plt.close(fig)
else:
raise NotImplementedError("model_net {} is not support".format(
args.model_net))
if __name__ == "__main__":
args = parser.parse_args()
print_arguments(args)
check_gpu(args.use_gpu)
infer(args)
raise NotImplementedError('CGAN only support mnist now!')
model = CGAN(cfg, train_reader)
elif cfg.model_net == 'DCGAN':
from trainer.DCGAN import DCGAN
if cfg.dataset != 'mnist':
raise NotImplementedError('DCGAN only support mnist now!')
model = DCGAN(cfg, train_reader)
elif cfg.model_net == 'CycleGAN':
from trainer.CycleGAN import CycleGAN
model = CycleGAN(cfg, a_reader, b_reader, a_reader_test, b_reader_test,
batch_num)
else:
pass
model.build_model()
if __name__ == "__main__":
cfg = config.parse_args()
config.print_arguments(cfg)
assert cfg.load_size >= cfg.crop_size, "Load Size CANNOT less than Crop Size!"
if cfg.profile:
if cfg.use_gpu:
with profiler.profiler('All', 'total', '/tmp/profile') as prof:
train(cfg)
else:
with profiler.profiler("CPU", sorted_key='total') as cpuprof:
train(cfg)
else:
train(cfg)
