def run(dataset, data_dir, result_dir, config_id, num_gpus, total_kimg, gamma,
mirror_augment, metrics, dlatent_size, lr, batch_size, decay_step,
decay_rate, stair, tick_kimg):
train = EasyDict(run_func_name='training.vae_training_loop.training_loop'
) # Options for training loop.
G = EasyDict(func_name='training.vae_dcgan.Decoder_main'
) # Options for generator network.
D = EasyDict(func_name='training.vae_dcgan.Encoder'
) # Options for discriminator network.
G_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for generator optimizer.
D_opt = EasyDict(beta1=0.0, beta2=0.99,
epsilon=1e-8) # Options for discriminator optimizer.
G_loss = EasyDict(func_name='training.loss.G_logistic_ns_pathreg'
) # Options for generator loss.
D_loss = EasyDict(
func_name='training.loss.vae_loss') # Options for discriminator loss.
sched = EasyDict() # Options for TrainingSchedule.
grid = EasyDict(
size='8k', layout='random') # Options for setup_snapshot_image_grid().
sc = dnnlib.SubmitConfig() # Options for dnnlib.submit_run().
tf_config = {'rnd.np_random_seed': 1000} # Options for tflib.init_tf().
train.data_dir = data_dir
train.total_kimg = total_kimg
train.mirror_augment = mirror_augment
train.image_snapshot_ticks = train.network_snapshot_ticks = 10
sched.batch_size = batch_size
sched.lr = lr
sched.decay_step = decay_step
sched.decay_rate = decay_rate
sched.stair = stair
sched.tick_kimg = tick_kimg
D_loss.gamma = 10
metrics = [metric_defaults[x] for x in metrics]
desc = 'vae_dcgan'
G.dlatent_size = dlatent_size
D.dlatent_size = dlatent_size
G.num_units = D.num_units = 1024
G.act = D.act = 'relu'
desc += '-' + dataset
dataset_args = EasyDict(tfrecord_dir=dataset)
assert num_gpus in [1, 2, 4, 8]
sc.num_gpus = num_gpus
desc += '-%dgpu' % num_gpus
assert config_id in _valid_configs
desc += '-' + config_id
if gamma is not None:
D_loss.gamma = gamma
sc.submit_target = dnnlib.SubmitTarget.LOCAL
sc.local.do_not_copy_source_files = True
kwargs = EasyDict(train)
kwargs.update(G_args=G,
D_args=D,
G_opt_args=G_opt,
D_opt_args=D_opt,
G_loss_args=G_loss,
D_loss_args=D_loss)
kwargs.update(dataset_args=dataset_args,
sched_args=sched,
grid_args=grid,
metric_arg_list=metrics,
tf_config=tf_config)
kwargs.submit_config = copy.deepcopy(sc)
kwargs.submit_config.run_dir_root = result_dir
kwargs.submit_config.run_desc = desc
dnnlib.submit_run(**kwargs)
