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("--command", choices = ["train", "eval", "resume", 'predict'], required = True) 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('--verb_module', type=str, default='', help='pretrained verb module') parser.add_argument('--train_role', action='store_true', help='cnn fix, verb fix, role train from the scratch') parser.add_argument( '--finetune_verb', action='store_true', help='cnn fix, verb finetune, role train from the scratch') parser.add_argument( '--finetune_cnn', action='store_true', help='cnn finetune, verb finetune, role train from the scratch') parser.add_argument('--output_dir', type=str, default='./trained_models', help='Location to output the model') parser.add_argument('--evaluate', 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('--frcnn_feat_dir', type=str, help='Location of output from detectron') #todo: train role module separately with gt verbs args = parser.parse_args() batch_size = 640 #lr = 5e-6 lr = 0.0001 lr_max = 5e-4 lr_gamma = 0.1 lr_step = 25 clip_norm = 50 weight_decay = 1e-4 n_epoch = 500 n_worker = 3 #dataset_folder = 'imSitu' #imgset_folder = 'resized_256' dataset_folder = args.dataset_folder imgset_folder = args.imgset_dir print('model spec :, top down att with role q ') train_set = json.load(open(dataset_folder + "/train.json")) imsitu_roleq = json.load(open("imsitu_data/imsitu_questions.json")) encoder = imsitu_encoder(train_set, imsitu_roleq) model = model_role_noun.BaseModel(encoder, args.gpuid) # To group up the features cnn_features, role_features = utils.group_features_noun(model) train_set = imsitu_loader_roleq(imgset_folder, train_set, encoder, model.train_preprocess()) train_loader = torch.utils.data.DataLoader(train_set, batch_size=64, shuffle=True, num_workers=n_worker) dev_set = json.load(open(dataset_folder + "/dev.json")) dev_set = imsitu_loader_roleq(imgset_folder, dev_set, encoder, model.dev_preprocess()) dev_loader = torch.utils.data.DataLoader(dev_set, batch_size=64, shuffle=True, num_workers=n_worker) test_set = json.load(open(dataset_folder + "/test.json")) test_set = imsitu_loader_roleq(imgset_folder, test_set, encoder, model.dev_preprocess()) test_loader = torch.utils.data.DataLoader(test_set, batch_size=64, shuffle=True, num_workers=n_worker) traindev_set = json.load(open(dataset_folder + "/dev.json")) traindev_set = imsitu_loader_roleq(imgset_folder, traindev_set, encoder, model.dev_preprocess()) traindev_loader = torch.utils.data.DataLoader(traindev_set, batch_size=8, shuffle=True, num_workers=n_worker) utils.set_trainable(model, False) if args.train_role: print('CNN fix, Verb fix, train role from the scratch from: {}'.format( args.verb_module)) args.train_all = False if len(args.verb_module) == 0: raise Exception('[pretrained verb module] not specified') utils.load_net(args.verb_module, [model.conv, model.verb], ['conv', 'verb']) optimizer_select = 1 model_name = 'cfx_vfx_rtrain' elif args.finetune_verb: print('CNN fix, Verb finetune, train role from the scratch from: {}'. format(args.verb_module)) args.train_all = True if len(args.verb_module) == 0: raise Exception('[pretrained verb module] not specified') utils.load_net(args.verb_module, [model.conv, model.verb], ['conv', 'verb']) optimizer_select = 2 model_name = 'cfx_vft_rtrain' elif args.finetune_cnn: print( 'CNN finetune, Verb finetune, train role from the scratch from: {}' .format(args.verb_module)) args.train_all = True if len(args.verb_module) == 0: raise Exception('[pretrained verb module] not specified') utils.load_net(args.verb_module, [model.conv, model.verb], ['conv', 'verb']) optimizer_select = 3 model_name = 'cft_vft_rtrain' elif args.resume_training: print('Resume training from: {}'.format(args.resume_model)) args.train_all = True if len(args.resume_model) == 0: raise Exception('[pretrained verb module] not specified') utils.load_net(args.resume_model, [model]) optimizer_select = 0 model_name = 'resume_all' else: print('Training from the scratch.') optimizer_select = 0 args.train_all = True model_name = 'train_full' optimizer = utils.get_optimizer_noun(lr, weight_decay, optimizer_select, cnn_features, role_features) if not os.path.exists(args.output_dir): os.mkdir(args.output_dir) torch.manual_seed(1234) if args.gpuid >= 0: #print('GPU enabled') model.cuda() torch.cuda.manual_seed(1234) torch.backends.cudnn.deterministic = True optimizer = torch.optim.Adamax([{ 'params': cnn_features, 'lr': 5e-5 }, { 'params': role_features }], lr=1e-3) #optimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=weight_decay) #scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=lr_step, gamma=lr_gamma) #gradient clipping, grad check scheduler = torch.optim.lr_scheduler.ExponentialLR(optimizer, gamma=0.9) if args.evaluate: top1, top5, val_loss = eval(model, dev_loader, encoder, args.gpuid, write_to_file=True) 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-'))) #write results to csv file role_dict = top1.role_dict fail_val_all = top1.value_all_dict pass_val_dict = top1.vall_all_correct fail_role = top1.fail_verb_role all_role = top1.all_verb_role with open('role_pred_data.json', 'w') as fp: json.dump(role_dict, fp, indent=4) with open('fail_val_all.json', 'w') as fp: json.dump(fail_val_all, fp, indent=4) with open('pass_val_all.json', 'w') as fp: json.dump(pass_val_dict, fp, indent=4) with open('fail_role.json', 'w') as fp: json.dump(fail_role, fp, indent=4) with open('all_role.json', 'w') as fp: json.dump(all_role, fp, indent=4) print('Writing predictions to file completed !') elif args.test: top1, top5, val_loss = eval(model, test_loader, encoder, args.gpuid, write_to_file=True) 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, traindev_loader, optimizer, scheduler, n_epoch, args.output_dir, encoder, args.gpuid, clip_norm, lr_max, model_name, args)
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("--command", choices = ["train", "eval", "resume", 'predict'], required = True) 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('--verb_module', type=str, default='', help='pretrained verb module') parser.add_argument('--role_module', type=str, default='', help='pretrained role module') parser.add_argument('--train_role', action='store_true', help='cnn fix, verb fix, role train from the scratch') parser.add_argument( '--finetune_verb', action='store_true', help='cnn fix, verb finetune, role train from the scratch') parser.add_argument( '--finetune_cnn', action='store_true', help='cnn finetune, verb finetune, role train from the scratch') parser.add_argument('--output_dir', type=str, default='./trained_models', help='Location to output the model') parser.add_argument('--evaluate', 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('--frcnn_feat_dir', type=str, help='Location of output from detectron') #todo: train role module separately with gt verbs args = parser.parse_args() batch_size = 640 #lr = 5e-6 lr = 0.0001 lr_max = 5e-4 lr_gamma = 0.1 lr_step = 25 clip_norm = 50 weight_decay = 1e-4 n_epoch = 500 n_worker = 3 #dataset_folder = 'imSitu' #imgset_folder = 'resized_256' dataset_folder = args.dataset_folder imgset_folder = args.imgset_dir print('model spec :, verb role with context ') train_set = json.load(open(dataset_folder + "/train.json")) imsitu_roleq = json.load(open("imsitu_data/imsitu_questions_prev.json")) encoder = imsitu_encoder(train_set, imsitu_roleq) model = model_verbmlp_roletd_new.BaseModel(encoder, args.gpuid) # To group up the features #all verb and role feat are under role as it's a single unit train_set = imsitu_loader_roleq(imgset_folder, train_set, encoder, model.train_preprocess()) train_loader = torch.utils.data.DataLoader(train_set, batch_size=64, shuffle=True, num_workers=n_worker) dev_set = json.load(open(dataset_folder + "/dev.json")) dev_set = imsitu_loader_roleq(imgset_folder, dev_set, encoder, model.dev_preprocess()) dev_loader = torch.utils.data.DataLoader(dev_set, batch_size=64, shuffle=True, num_workers=n_worker) test_set = json.load(open(dataset_folder + "/test.json")) test_set = imsitu_loader_roleq(imgset_folder, test_set, encoder, model.dev_preprocess()) test_loader = torch.utils.data.DataLoader(test_set, batch_size=64, shuffle=True, num_workers=n_worker) traindev_set = json.load(open(dataset_folder + "/dev.json")) traindev_set = imsitu_loader_roleq(imgset_folder, traindev_set, encoder, model.dev_preprocess()) traindev_loader = torch.utils.data.DataLoader(traindev_set, batch_size=8, shuffle=True, num_workers=n_worker) utils.set_trainable(model, False) utils.load_net(args.verb_module, [model.verb]) utils.load_net(args.role_module, [model.roles]) if not os.path.exists(args.output_dir): os.mkdir(args.output_dir) torch.manual_seed(1234) if args.gpuid >= 0: #print('GPU enabled') model.cuda() torch.cuda.manual_seed(1234) torch.backends.cudnn.deterministic = True top1, top5, val_loss = eval(model, dev_loader, encoder, args.gpuid, write_to_file=True) top1_avg = top1.get_average_results() avg_score = top1_avg["verb"] + top1_avg["value"] + top1_avg["value-all"] avg_score /= 3 print('Dev average :{:.2f} {} '.format( avg_score * 100, utils.format_dict(top1_avg, '{:.2f}', '1-')))