def exp_train(): exp_name = 'EXP_NAME' out_base_dir = os.path.join(os.getcwd(), 'symlinks/exp/EXP_GROUP') exp_const = ExpConstants(exp_name, out_base_dir) exp_const.model_dir = os.path.join(exp_const.exp_dir, 'models') exp_const.log_dir = os.path.join(exp_const.exp_dir, 'log') exp_const.vis_dir = os.path.join(exp_const.exp_dir, 'vis') exp_const.log_step = 10 exp_const.model_save_step = 1000 exp_const.val_step = 1000 exp_const.num_val_samples = 1000 exp_const.batch_size = 32 exp_const.num_epochs = 1000 exp_const.lr = 0.01 exp_const.momentum = 0.9 exp_const.num_workers = 5 exp_const.optimizer = 'SGD' exp_const.subset = {'training': 'train', 'validation': 'val'} data_const = DATASET_CONSTANTS() model_const = Constants() model_const.model_num = None model_const.net = NET_CONSTANTS() model_const.net_path = os.path.join(exp_const.model_dir, f'net_{model_const.model_num}') train.main(exp_const, data_const, model_const)
def main(**kwargs): exp_base_dir = coco_paths['exp_dir'] if kwargs['dataset'] == 'flickr': exp_base_dir = flickr_paths['exp_dir'] exp_const = ExpConstants(kwargs['exp_name'], exp_base_dir) exp_const.log_dir = os.path.join(exp_const.exp_dir, 'logs') exp_const.model_dir = os.path.join(exp_const.exp_dir, 'models') exp_const.vis_dir = os.path.join(exp_const.exp_dir, 'vis') exp_const.dataset = kwargs['dataset'] exp_const.optimizer = 'Adam' exp_const.lr = kwargs['lr'] exp_const.momentum = None exp_const.num_epochs = 10 exp_const.log_step = 20 # Save models approx. twice every epoch exp_const.model_save_step = 400000 // (2 * kwargs['train_batch_size'] ) # 4000=400000/(2*50) if exp_const.dataset == 'flickr': exp_const.model_save_step = 150000 // (2 * kwargs['train_batch_size']) val_freq_factor = 2 if kwargs['val_frequently'] is True: val_freq_factor = 1 exp_const.val_step = val_freq_factor * exp_const.model_save_step # set to 1*model_save_step for plotting mi vs perf exp_const.num_val_samples = None exp_const.train_batch_size = kwargs['train_batch_size'] exp_const.val_batch_size = 20 exp_const.num_workers = 10 exp_const.seed = 0 exp_const.neg_noun_loss_wt = kwargs['neg_noun_loss_wt'] exp_const.self_sup_loss_wt = kwargs['self_sup_loss_wt'] exp_const.lang_sup_loss_wt = kwargs['lang_sup_loss_wt'] exp_const.contextualize = not kwargs['no_context'] exp_const.random_lang = kwargs['random_lang'] DatasetConstants = CocoDatasetConstants if exp_const.dataset == 'flickr': DatasetConstants = FlickrDatasetConstants data_const = { 'train': DatasetConstants('train'), 'val': DatasetConstants('val'), } model_const = Constants() model_const.model_num = kwargs['model_num'] model_const.object_encoder = ObjectEncoderConstants() model_const.object_encoder.context_layer.output_attentions = True model_const.object_encoder.object_feature_dim = 2048 model_const.cap_encoder = CapEncoderConstants() model_const.cap_encoder.output_attentions = True model_const.cap_info_nce_layers = kwargs['cap_info_nce_layers'] model_const.object_encoder_path = os.path.join( exp_const.model_dir, f'object_encoder_{model_const.model_num}') model_const.self_sup_criterion_path = os.path.join( exp_const.model_dir, f'self_sup_criterion_{model_const.model_num}') model_const.lang_sup_criterion_path = os.path.join( exp_const.model_dir, f'lang_sup_criterion_{model_const.model_num}') train(exp_const, data_const, model_const)
def main(**kwargs): exp_const = ExpConstants(kwargs['exp_name'], kwargs['exp_base_dir']) exp_const.log_dir = os.path.join(exp_const.exp_dir, 'logs') exp_const.model_dir = os.path.join(exp_const.exp_dir, 'models') exp_const.vis_dir = os.path.join(exp_const.exp_dir, 'vis') exp_const.optimizer = 'Adam' exp_const.lr = 1e-3 exp_const.momentum = None exp_const.num_epochs = 100 exp_const.log_step = 100 exp_const.model_save_step = 1000 exp_const.val_step = 1000 exp_const.num_val_samples = None data_const = {'train': Constants(), 'val': Constants()} model_const = Constants() model_const.model_num = kwargs['model_num'] model_const.net = Constants() model_const.net_path = os.path.join(exp_const.model_dir, f'net_{model_const.model_num}')