diffeye/main.py at main · RehgLab/diffeye · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
import os
import torch
import torch.optim.adam
from tools.utils import parse_args, load_yaml_config, merge_opts_to_config, \
    instantiate_from_config, seed_everything, create_mlab_eng, Logger
from pprint import pprint

def main():
    args = parse_args()

    config = load_yaml_config(args.config_file)
    config = merge_opts_to_config(config, args.opts)
    logger = Logger(args)
    logger.save_config(config, name='config.yaml')

    config['train_dataset']['params']['root'] = os.path.join(
        args.root_dir,
        config['train_dataset']['params']['root']
    )
    config['train_dataset']['params']['stim_to_sub_pth'] = os.path.join(
        config['train_dataset']['params']['root'],
        config['train_dataset']['params']['stim_to_sub_pth']
    )

    config['val_dataset']['params']['root'] = os.path.join(
        args.root_dir,
        config['val_dataset']['params']['root']
    )
    config['val_dataset']['params']['stim_to_sub_pth'] = os.path.join(
        config['val_dataset']['params']['root'],
        config['val_dataset']['params']['stim_to_sub_pth']
    )

    config['trainer']['params']['ground_truth_dir'] = os.path.join(
        config['train_dataset']['params']['root'],
        config['trainer']['params']['ground_truth_dir']
    )

    print(config)


    logger.save_config(config, name='config_w_abs_paths.yaml')

    logger.save_git_commit()

    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    print(f'Using device: {device}')

    seed_everything(args.seed)

    model = instantiate_from_config(config['model']).to(device)

    # print trainable parameters number
    print(f'Trainable parameters: {sum(p.numel() for p in model.parameters() if p.requires_grad)}')
    optimizer = instantiate_from_config(
        config['optimizer'],
        params=model.parameters()
    )

    ckpt_pth = args.ckpt_pth
    if ckpt_pth is not None:
        print(f'Loading checkpoint from {ckpt_pth}')
        checkpoint = torch.load(ckpt_pth, map_location='cpu')
        model.load_state_dict(checkpoint['model_state_dict'])
        optimizer.load_state_dict(checkpoint['optimizer_state_dict'])

    train_scheduler = instantiate_from_config(config['diff_train_scheduler'])

    train_dataset = instantiate_from_config(config['train_dataset'])
    train_loader = instantiate_from_config(
        config['train_loader'],
        dataset=train_dataset
    )


    criterion = instantiate_from_config(config['criterion'])

    if config['trainer']['params']['should_evaluate'] == True:
        val_scheduler = instantiate_from_config(config['diff_val_scheduler'])
        if config['diff_val_scheduler']['target'] == 'diffusers.schedulers.DDIMScheduler':
            val_scheduler.set_timesteps(config['diff_val_scheduler']['num_inference_steps'])
        val_dataset = instantiate_from_config(config['val_dataset'])
        val_loader = instantiate_from_config(
            config['val_loader'],
            dataset=val_dataset
        )

        matlab_eng = create_mlab_eng(
            os.path.join(config['train_dataset']['params']['root'], 'DatabaseCode'),
        )
    else:
        matlab_eng = None
        val_loader = None
        val_scheduler = None


    trainer = instantiate_from_config(
        config=config['trainer'],
        cfg=config,
        args=args,
        model=model,
        train_scheduler=train_scheduler,
        val_scheduler=val_scheduler,
        train_loader=train_loader,
        val_loader=val_loader,
        optimizer=optimizer,
        criterion=criterion,
        matlab_eng=matlab_eng,
        device=device,
        logger=logger,
    )

    trainer.train()

if __name__ == "__main__":
    main()