def main():
import argparse
parser = argparse.ArgumentParser(
description="imsitu VSRL. Training, evaluation and prediction.")
parser.add_argument("--gpuid",
default=-1,
help="put GPU id > -1 in GPU mode",
type=int)
parser.add_argument('--output_dir',
type=str,
default='./trained_models',
help='Location to output the model')
parser.add_argument('--resume_training',
action='store_true',
help='Resume training from the model [resume_model]')
parser.add_argument('--resume_model',
type=str,
default='',
help='The model we resume')
parser.add_argument('--evaluate',
action='store_true',
help='Only use the testing mode')
parser.add_argument('--evaluate_visualize',
action='store_true',
help='Only use the testing mode to visualize ')
parser.add_argument('--evaluate_rare',
action='store_true',
help='Only use the testing mode')
parser.add_argument('--test',
action='store_true',
help='Only use the testing mode')
parser.add_argument('--dataset_folder',
type=str,
default='./imSitu',
help='Location of annotations')
parser.add_argument('--imgset_dir',
type=str,
default='./resized_256',
help='Location of original images')
parser.add_argument('--train_file',
default="train_freq2000.json",
type=str,
help='trainfile name')
parser.add_argument('--dev_file',
default="dev_freq2000.json",
type=str,
help='dev file name')
parser.add_argument('--test_file',
default="test_freq2000.json",
type=str,
help='test file name')
parser.add_argument('--model_saving_name',
type=str,
help='saving name of the outpul model')
parser.add_argument('--epochs', type=int, default=500)
parser.add_argument('--model', type=str, default='top_down_baseline')
parser.add_argument('--batch_size', type=int, default=64)
parser.add_argument('--seed', type=int, default=1111, help='random seed')
parser.add_argument('--clip_norm', type=float, default=0.25)
parser.add_argument('--num_workers', type=int, default=3)
args = parser.parse_args()
n_epoch = args.epochs
batch_size = args.batch_size
clip_norm = args.clip_norm
n_worker = args.num_workers
dataset_folder = args.dataset_folder
imgset_folder = args.imgset_dir
train_set = json.load(open(dataset_folder + '/' + args.train_file))
encoder = imsitu_encoder.imsitu_encoder(train_set)
train_set = imsitu_loader.imsitu_loader(imgset_folder, train_set, encoder,
'train', encoder.train_transform)
constructor = 'build_%s' % args.model
model = getattr(top_down_baseline, constructor)(encoder.get_num_roles(),
encoder.get_num_verbs(),
encoder.get_num_labels(),
encoder)
train_loader = torch.utils.data.DataLoader(train_set,
batch_size=batch_size,
shuffle=True,
num_workers=n_worker)
dev_set = json.load(open(dataset_folder + '/' + args.dev_file))
dev_set = imsitu_loader.imsitu_loader(imgset_folder, dev_set, encoder,
'val', encoder.dev_transform)
dev_loader = torch.utils.data.DataLoader(dev_set,
batch_size=batch_size,
shuffle=True,
num_workers=n_worker)
test_set = json.load(open(dataset_folder + '/' + args.test_file))
test_set = imsitu_loader.imsitu_loader(imgset_folder, test_set, encoder,
'test', encoder.dev_transform)
test_loader = torch.utils.data.DataLoader(test_set,
batch_size=batch_size,
shuffle=True,
num_workers=n_worker)
if not os.path.exists(args.output_dir):
os.mkdir(args.output_dir)
torch.manual_seed(args.seed)
if args.gpuid >= 0:
model.cuda()
torch.cuda.manual_seed(args.seed)
torch.backends.cudnn.benchmark = True
if args.resume_training:
print('Resume training from: {}'.format(args.resume_model))
args.train_all = True
if len(args.resume_model) == 0:
raise Exception('[pretrained module] not specified')
utils.load_net(args.resume_model, [model])
optimizer = torch.optim.Adamax(model.parameters(), lr=1e-3)
model_name = 'resume_all'
else:
print('Training from the scratch.')
model_name = 'train_full'
utils.set_trainable(model, True)
optimizer = torch.optim.Adamax(
[{
'params': model.convnet.parameters(),
'lr': 5e-5
}, {
'params': model.role_emb.parameters()
}, {
'params': model.verb_emb.parameters()
}, {
'params': model.query_composer.parameters()
}, {
'params': model.v_att.parameters()
}, {
'params': model.q_net.parameters()
}, {
'params': model.v_net.parameters()
}, {
'params': model.classifier.parameters()
}],
lr=1e-3)
scheduler = torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma=0.9)
if args.evaluate:
top1, top5, val_loss = eval(model, dev_loader, encoder, args.gpuid)
top1_avg = top1.get_average_results_nouns()
top5_avg = top5.get_average_results_nouns()
avg_score = top1_avg["verb"] + top1_avg["value"] + top1_avg["value-all"] + top5_avg["verb"] + \
top5_avg["value"] + top5_avg["value-all"] + top5_avg["value*"] + top5_avg["value-all*"]
avg_score /= 8
print('Dev average :{:.2f} {} {}'.format(
avg_score * 100, utils.format_dict(top1_avg, '{:.2f}', '1-'),
utils.format_dict(top5_avg, '{:.2f}', '5-')))
elif args.test:
top1, top5, val_loss = eval(model, test_loader, encoder, args.gpuid)
top1_avg = top1.get_average_results_nouns()
top5_avg = top5.get_average_results_nouns()
avg_score = top1_avg["verb"] + top1_avg["value"] + top1_avg["value-all"] + top5_avg["verb"] + \
top5_avg["value"] + top5_avg["value-all"] + top5_avg["value*"] + top5_avg["value-all*"]
avg_score /= 8
print('Test average :{:.2f} {} {}'.format(
avg_score * 100, utils.format_dict(top1_avg, '{:.2f}', '1-'),
utils.format_dict(top5_avg, '{:.2f}', '5-')))
else:
print('Model training started!')
train(
model,
train_loader,
dev_loader,
optimizer,
scheduler,
n_epoch,
args.output_dir,
encoder,
args.gpuid,
clip_norm,
model_name,
args.model_saving_name,
)
def main():
import argparse
parser = argparse.ArgumentParser(
description="imsitu VSRL. Training, evaluation and prediction.")
parser.add_argument("--gpuid",
default=-1,
help="put GPU id > -1 in GPU mode",
type=int)
parser.add_argument('--output_dir',
type=str,
default='./trained_models',
help='Location to output the model')
parser.add_argument('--resume_training',
action='store_true',
help='Resume training from the model [resume_model]')
parser.add_argument('--resume_model',
type=str,
default='',
help='The model we resume')
parser.add_argument('--evaluate',
action='store_true',
help='Only use the testing mode')
parser.add_argument('--evaluate_rare',
action='store_true',
help='Only use the testing mode')
parser.add_argument('--test',
action='store_true',
help='Only use the testing mode')
parser.add_argument('--dataset_folder',
type=str,
default='./imSitu',
help='Location of annotations')
parser.add_argument('--imgset_dir',
type=str,
default='./resized_256',
help='Location of original images')
parser.add_argument('--train_file',
default="train_freq2000.json",
type=str,
help='trainfile name')
parser.add_argument('--dev_file',
default="dev_freq2000.json",
type=str,
help='dev file name')
parser.add_argument('--test_file',
default="test_freq2000.json",
type=str,
help='test file name')
parser.add_argument('--model_saving_name',
type=str,
help='saving name of the outpul model')
parser.add_argument('--epochs', type=int, default=500)
parser.add_argument('--model', type=str, default='vgg_caq_joint')
parser.add_argument('--batch_size', type=int, default=64)
parser.add_argument('--seed', type=int, default=1111, help='random seed')
parser.add_argument('--clip_norm', type=float, default=0.25)
parser.add_argument('--num_workers', type=int, default=3)
parser.add_argument('--vgg_verb_model',
type=str,
default='',
help='Pretrained vgg verb model')
parser.add_argument('--tda_verb_model',
type=str,
default='',
help='Pretrained topdown verb model')
parser.add_argument('--caq_model',
type=str,
default='',
help='Pretrained CAQ model')
args = parser.parse_args()
n_epoch = args.epochs
batch_size = args.batch_size
clip_norm = args.clip_norm
n_worker = args.num_workers
dataset_folder = args.dataset_folder
imgset_folder = args.imgset_dir
train_set = json.load(open(dataset_folder + '/' + args.train_file))
encoder = imsitu_encoder.imsitu_encoder(train_set)
train_set = imsitu_loader.imsitu_loader(imgset_folder, train_set, encoder,
'train', encoder.train_transform)
constructor = 'build_vgg_verb_classifier'
vgg_verb_model = getattr(vgg_verb_classifier,
constructor)(len(encoder.verb_list))
constructor = 'build_top_down_baseline'
role_module = getattr(top_down_baseline_addemb,
constructor)(encoder.get_num_roles(),
encoder.get_num_verbs(),
encoder.get_num_labels(), encoder)
constructor = 'build_top_down_verb'
tda_verb_model = getattr(top_down_verb,
constructor)(encoder.get_num_labels(),
encoder.get_num_verbs(), role_module)
constructor = 'build_top_down_baseline'
tda_role_module = getattr(top_down_baseline,
constructor)(encoder.get_num_roles(),
encoder.get_num_verbs(),
encoder.get_num_labels(), encoder)
constructor = 'build_top_down_query_context'
caq_model = getattr(top_down_query_context,
constructor)(encoder.get_num_roles(),
encoder.get_num_verbs(),
encoder.get_num_labels(), encoder,
tda_role_module)
constructor = 'build_%s' % args.model
model = getattr(revgg_caq_joint_eval,
constructor)(vgg_verb_model, tda_verb_model, caq_model)
train_loader = torch.utils.data.DataLoader(train_set,
batch_size=batch_size,
shuffle=True,
num_workers=n_worker)
dev_set = json.load(open(dataset_folder + '/' + args.dev_file))
dev_set = imsitu_loader.imsitu_loader(imgset_folder, dev_set, encoder,
'val', encoder.dev_transform)
dev_loader = torch.utils.data.DataLoader(dev_set,
batch_size=batch_size,
shuffle=True,
num_workers=n_worker)
test_set = json.load(open(dataset_folder + '/' + args.test_file))
test_set = imsitu_loader.imsitu_loader(imgset_folder, test_set, encoder,
'test', encoder.dev_transform)
test_loader = torch.utils.data.DataLoader(test_set,
batch_size=batch_size,
shuffle=True,
num_workers=n_worker)
if not os.path.exists(args.output_dir):
os.mkdir(args.output_dir)
torch.manual_seed(args.seed)
if args.gpuid >= 0:
model.cuda()
torch.cuda.manual_seed(args.seed)
torch.backends.cudnn.benchmark = True
#load models
utils.load_net(args.vgg_verb_model, [model.vgg_model])
print('successfully loaded vgg_verb_model!')
utils.load_net(args.tda_verb_model, [model.tda_model])
print('successfully loaded tda_verb_model!')
utils.load_net(args.caq_model, [model.caq_model])
print('successfully loaded caq_model!')
if args.evaluate:
top1, top5, val_loss = eval(model,
dev_loader,
encoder,
args.gpuid,
write_to_file=True)
top1_avg = top1.get_average_results()
top5_avg = top5.get_average_results()
avg_score = top1_avg["verb"] + top1_avg["value"] + top1_avg["value-all"] + top5_avg["verb"] + \
top5_avg["value"] + top5_avg["value-all"] + top5_avg["value*"] + top5_avg["value-all*"]
avg_score /= 8
print('Dev average :{:.2f} {} {}'.format(
avg_score * 100, utils.format_dict(top1_avg, '{:.2f}', '1-'),
utils.format_dict(top5_avg, '{:.2f}', '5-')))
elif args.test:
top1, top5, val_loss = eval(model,
test_loader,
encoder,
args.gpuid,
write_to_file=True)
top1_avg = top1.get_average_results()
top5_avg = top5.get_average_results()
avg_score = top1_avg["verb"] + top1_avg["value"] + top1_avg["value-all"] + top5_avg["verb"] + \
top5_avg["value"] + top5_avg["value-all"] + top5_avg["value*"] + top5_avg["value-all*"]
avg_score /= 8
print('Test average :{:.2f} {} {}'.format(
avg_score * 100, utils.format_dict(top1_avg, '{:.2f}', '1-'),
utils.format_dict(top5_avg, '{:.2f}', '5-')))
#open train, dev, test json
with open(pjoin(args.dataset_folder, 'train.json'), 'r') as f:
encoder_json = jload(f) #encoder json is always train.json
with open(pjoin(args.dataset_folder, args.train_file), 'r') as f:
train_json = jload(f)
with open(pjoin(args.dataset_folder, args.dev_file), 'r') as f:
dev_json = jload(f)
with open(pjoin(args.dataset_folder, args.test_file), 'r') as f:
test_json = jload(f)
# if encoder exists dont create again (time saver)
if not pisfile(pjoin(args.saving_folder, 'encoder')):
encoder = imsitu_encoder.imsitu_encoder(encoder_json)
torch.save(encoder, pjoin(args.saving_folder, 'encoder'))
else:
print("Loading encoder file")
encoder = torch.load(pjoin(args.saving_folder, 'encoder'))
# create dataloader
train_set = imsitu_loader.imsitu_loader(args.imgset_dir, train_json,
encoder, encoder.train_transform)
train_loader = torch.utils.data.DataLoader(train_set,
pin_memory=True,
batch_size=args.batch_size,
shuffle=True,
num_workers=args.num_workers)
dev_set = imsitu_loader.imsitu_loader(args.imgset_dir, dev_json, encoder,