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.model_dir = os.path.join(exp_const.exp_dir, 'models')
exp_const.seed = 0
exp_const.contextualize = not kwargs['no_context']
exp_const.random_lang = kwargs['random_lang']
data_const = FlickrDatasetConstants(kwargs['subset'])
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']
if model_const.model_num == -100:
filename = os.path.join(exp_const.exp_dir, f'results_val_best.json')
results = io.load_json_object(filename)
model_const.model_num = results['model_num']
print('Selected model num:', model_const.model_num)
model_const.object_encoder_path = os.path.join(
exp_const.model_dir, f'object_encoder_{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}')
if exp_const.random_lang is True:
model_const.cap_encoder_path = os.path.join(
exp_const.model_dir, f'cap_encoder_{model_const.model_num}')
eval_flickr_phrase_loc.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_base_dir = coco_paths['exp_dir']
if kwargs['train_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.train_dataset = kwargs['train_dataset']
exp_const.vis_dataset = kwargs['vis_dataset']
exp_const.vis_dir = os.path.join(exp_const.exp_dir,
f'vis/attention_{exp_const.vis_dataset}')
exp_const.num_vis_samples = 50
exp_const.seed = 0
exp_const.contextualize = not kwargs['no_context']
DatasetConstants = CocoDatasetConstants
if exp_const.vis_dataset == 'flickr':
DatasetConstants = FlickrDatasetConstants
data_const = DatasetConstants('val')
if exp_const.vis_dataset == 'coco':
data_const.image_dir = os.path.join(coco_paths['image_dir'],
data_const.subset_image_dirname)
data_const.read_neg_samples = False
data_const.read_noun_adj_tokens = False
model_const = Constants()
model_const.model_num = kwargs['model_num']
model_const.object_encoder = ObjectEncoderConstants()
model_const.object_encoder.object_feature_dim = 2048
model_const.cap_encoder = CapEncoderConstants()
if model_const.model_num == -100:
model_const.object_encoder_path = os.path.join(exp_const.model_dir,
f'best_object_encoder')
model_const.lang_sup_criterion_path = os.path.join(
exp_const.model_dir, f'best_lang_sup_criterion')
else:
model_const.object_encoder_path = os.path.join(
exp_const.model_dir, f'object_encoder_{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}')
if exp_const.vis_dataset == 'coco':
vis_att(exp_const, data_const, model_const)
else:
vis_att_flickr(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.model_dir = os.path.join(exp_const.exp_dir, 'models')
exp_const.seed = 0
exp_const.contextualize = not kwargs['no_context']
exp_const.random_lang = kwargs['random_lang']
data_const = FlickrDatasetConstants(kwargs['subset'])
model_const = Constants()
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_nums = find_all_model_numbers(exp_const.model_dir)
for num in model_nums:
continue
if num <= 3000:
continue
model_const.model_num = num
model_const.object_encoder_path = os.path.join(
exp_const.model_dir, f'object_encoder_{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}')
if exp_const.random_lang is True:
model_const.cap_encoder_path = os.path.join(
exp_const.model_dir, f'cap_encoder_{model_const.model_num}')
filename = os.path.join(exp_const.exp_dir,
f'results_{data_const.subset}_{num}.json')
if os.path.exists(filename):
print(io.load_json_object(filename))
continue
eval_flickr_phrase_loc.main(exp_const, data_const, model_const)
best_model_num = -1
best_pt_recall = 0
best_results = None
for num in model_nums:
filename = os.path.join(exp_const.exp_dir,
f'results_{data_const.subset}_{num}.json')
if not os.path.exists(filename):
continue
results = io.load_json_object(filename)
results['model_num'] = num
print(results)
if results['pt_recall'] >= best_pt_recall:
best_results = results
best_pt_recall = results['pt_recall']
best_model_num = num
print('-' * 80)
best_results['model_num'] = best_model_num
print(best_results)
filename = os.path.join(exp_const.exp_dir,
f'results_{data_const.subset}_best.json')
io.dump_json_object(best_results, filename)
