config.restart = True
# copy over new num_epochs and lr schedule
config.num_epochs = given_config.num_epochs
config.lr_schedule = given_config.lr_schedule
config.save_progression = given_config.save_progression
if not hasattr(config, "batchnorm_track"):
config.batchnorm_track = True # before we added in false option
if not hasattr(config, "lamb_A"):
config.lamb_A = config.lamb
config.lamb_B = config.lamb
else:
print("Config: %s" % config_to_str(config))
# Model ------------------------------------------------------------------------
def train(render_count=-1):
dataloaders_head_A, dataloaders_head_B, \
mapping_assignment_dataloader, mapping_test_dataloader = \
cluster_twohead_create_dataloaders(config)
net = archs.__dict__[config.arch](config)
if config.restart:
model_path = os.path.join(config.out_dir, net_name)
net.load_state_dict(
torch.load(model_path, map_location=lambda storage, loc: storage))
net.cuda()
config_name = "config.pickle"
dict_name = "latest.pytorch"
given_config = config
reloaded_config_path = os.path.join(given_config.out_dir, config_name)
print("Loading restarting config from: %s" % reloaded_config_path)
with open(reloaded_config_path, "rb") as config_f:
config = pickle.load(config_f)
assert (config.model_ind == given_config.model_ind)
config.restart = True
# copy over new num_epochs and lr schedule
config.num_epochs = given_config.num_epochs
config.lr_schedule = given_config.lr_schedule
else:
print("Given config: %s" % config_to_str(config))
# Model ------------------------------------------------------
def train():
print("inside train")
exit()
dataloaders_head_A, mapping_assignment_dataloader, mapping_test_dataloader = \
segmentation_create_dataloaders(config)
dataloaders_head_B = dataloaders_head_A # unlike for clustering datasets
net = archs.__dict__[config.arch](config)
if config.restart:
dict = torch.load(os.path.join(config.out_dir, dict_name),
map_location=lambda storage, loc: storage)
