def main(exp_const, data_const, model_const):
np.random.seed(exp_const.seed)
torch.manual_seed(exp_const.seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
print('Creating network ...')
model = Constants()
model.const = model_const
model.object_encoder = ObjectEncoder(model.const.object_encoder)
model.cap_encoder = CapEncoder(model.const.cap_encoder)
o_dim = model.object_encoder.const.object_feature_dim
if exp_const.contextualize == True:
o_dim = model.object_encoder.const.context_layer.hidden_size
model.lang_sup_criterion = create_cap_info_nce_criterion(
o_dim, model.object_encoder.const.object_feature_dim,
model.cap_encoder.model.config.hidden_size,
model.cap_encoder.model.config.hidden_size // 2,
model.const.cap_info_nce_layers)
if model.const.model_num != -1:
loaded_object_encoder = torch.load(model.const.object_encoder_path)
print('Loaded model number:', loaded_object_encoder['step'])
model.object_encoder.load_state_dict(
loaded_object_encoder['state_dict'])
model.lang_sup_criterion.load_state_dict(
torch.load(model.const.lang_sup_criterion_path)['state_dict'])
if exp_const.random_lang is True:
model.cap_encoder.load_state_dict(
torch.load(model.const.cap_encoder_path)['state_dict'])
model.object_encoder.cuda()
model.cap_encoder.cuda()
model.lang_sup_criterion.cuda()
print('Creating dataloader ...')
dataset = FlickrDataset(data_const)
with torch.no_grad():
results = eval_model(model, dataset, exp_const)
filename = os.path.join(
exp_const.exp_dir,
f'results_{data_const.subset}_{model_const.model_num}.json')
io.dump_json_object(results, filename)
def main(exp_const, data_const, model_const):
np.random.seed(exp_const.seed)
torch.manual_seed(exp_const.seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
io.mkdir_if_not_exists(exp_const.exp_dir, recursive=True)
io.mkdir_if_not_exists(exp_const.log_dir)
io.mkdir_if_not_exists(exp_const.model_dir)
io.mkdir_if_not_exists(exp_const.vis_dir)
print('Creating network ...')
model = Constants()
model.const = model_const
model.object_encoder = ObjectEncoder(model.const.object_encoder)
model.cap_encoder = CapEncoder(model.const.cap_encoder)
o_dim = model.object_encoder.const.object_feature_dim
if exp_const.contextualize == True:
o_dim = model.object_encoder.const.context_layer.hidden_size
model.lang_sup_criterion = create_cap_info_nce_criterion(
o_dim, model.object_encoder.const.object_feature_dim,
model.cap_encoder.model.config.hidden_size,
model.cap_encoder.model.config.hidden_size // 2)
if model.const.model_num != -1:
print('Loading model num', model.const.model_num, '...')
loaded_object_encoder = torch.load(model.const.object_encoder_path)
print(loaded_object_encoder['step'])
model.object_encoder.load_state_dict(
loaded_object_encoder['state_dict'])
model.lang_sup_criterion.load_state_dict(
torch.load(model.const.lang_sup_criterion_path)['state_dict'])
model.object_encoder.cuda()
model.cap_encoder.cuda()
model.lang_sup_criterion.cuda()
print('Creating dataloader ...')
dataset = CocoDataset(data_const)
dataloader = DataLoader(dataset, batch_size=1, shuffle=True, num_workers=1)
eval_model(model, dataloader, exp_const)
def main(exp_const,data_const,model_const):
np.random.seed(exp_const.seed)
torch.manual_seed(exp_const.seed)
torch.backends.cudnn.deterministic = True
torch.backends.cudnn.benchmark = False
io.mkdir_if_not_exists(exp_const.exp_dir,recursive=True)
io.mkdir_if_not_exists(exp_const.log_dir)
io.mkdir_if_not_exists(exp_const.model_dir)
io.mkdir_if_not_exists(exp_const.vis_dir)
tb_writer = SummaryWriter(log_dir=exp_const.log_dir)
model_num = model_const.model_num
save_constants({
f'exp_{model_num}': exp_const,
f'data_train_{model_num}': data_const['train'],
f'data_val_{model_num}': data_const['val'],
f'model_{model_num}': model_const},
exp_const.exp_dir)
print('Creating network ...')
model = Constants()
model.const = model_const
model.object_encoder = ObjectEncoder(model.const.object_encoder)
model.cap_encoder = CapEncoder(model.const.cap_encoder)
if exp_const.random_lang is True:
model.cap_encoder.random_init()
c_dim = model.object_encoder.const.object_feature_dim
if exp_const.contextualize==True:
c_dim = model.object_encoder.const.context_layer.hidden_size
model.self_sup_criterion = create_info_nce_criterion(
model.object_encoder.const.object_feature_dim,
c_dim,
model.object_encoder.const.context_layer.hidden_size)
o_dim = model.object_encoder.const.object_feature_dim
if exp_const.contextualize==True:
o_dim = model.object_encoder.const.context_layer.hidden_size
model.lang_sup_criterion = create_cap_info_nce_criterion(
o_dim,
model.object_encoder.const.object_feature_dim,
model.cap_encoder.model.config.hidden_size,
model.cap_encoder.model.config.hidden_size//2,
model.const.cap_info_nce_layers)
if model.const.model_num != -1:
model.object_encoder.load_state_dict(
torch.load(model.const.object_encoder_path)['state_dict'])
model.self_sup_criterion.load_state_dict(
torch.load(model.const.self_sup_criterion_path)['state_dict'])
model.lang_sup_criterion.load_state_dict(
torch.load(model.const.lang_sup_criterion_path)['state_dict'])
model.object_encoder.cuda()
model.cap_encoder.cuda()
model.self_sup_criterion.cuda()
model.lang_sup_criterion.cuda()
model.object_encoder.to_file(
os.path.join(exp_const.exp_dir,'object_encoder.txt'))
model.self_sup_criterion.to_file(
os.path.join(exp_const.exp_dir,'self_supervised_criterion.txt'))
model.lang_sup_criterion.to_file(
os.path.join(exp_const.exp_dir,'lang_supervised_criterion.txt'))
print('Creating dataloader ...')
dataloaders = {}
if exp_const.dataset=='coco':
Dataset = CocoDataset
elif exp_const.dataset=='flickr':
Dataset = FlickrDataset
else:
msg = f'{exp_const.dataset} not implemented'
raise NotImplementedError(msg)
for mode, const in data_const.items():
dataset = Dataset(const)
if mode=='train':
shuffle=True
batch_size=exp_const.train_batch_size
else:
shuffle=True
batch_size=exp_const.val_batch_size
dataloaders[mode] = DataLoader(
dataset,
batch_size=batch_size,
shuffle=shuffle,
num_workers=exp_const.num_workers)
train_model(model,dataloaders,exp_const,tb_writer)
