Hugging Face's logo

Spaces:
Salesforce
/
BLIP
Build error

App Files Community
4
BLIP
File size: 4,249 Bytes 
794924b
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
118
 
'''
 * Copyright (c) 2022, salesforce.com, inc.
 * All rights reserved.
 * SPDX-License-Identifier: BSD-3-Clause
 * For full license text, see LICENSE.txt file in the repo root or https://opensource.org/licenses/BSD-3-Clause
 * By Junnan Li
'''
import argparse
import os
import ruamel_yaml as yaml
import numpy as np
import random
import time
import datetime
import json
from pathlib import Path

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.backends.cudnn as cudnn
import torch.distributed as dist
from torch.utils.data import DataLoader

from models.blip import blip_decoder
import utils
from data import create_dataset, create_sampler, create_loader
from data.utils import save_result

@torch.no_grad()
def evaluate(model, data_loader, device, config):
    # evaluate
    model.eval() 
    
    metric_logger = utils.MetricLogger(delimiter="  ")
    header = 'Evaluation:'
    print_freq = 10

    result = []
    for image, image_id in metric_logger.log_every(data_loader, print_freq, header): 
        
        image = image.to(device)       
        
        captions = model.generate(image, sample=False, num_beams=config['num_beams'], max_length=config['max_length'], 
                                  min_length=config['min_length'], repetition_penalty=1.1)
        
        for caption, img_id in zip(captions, image_id):
            result.append({"image_id": img_id.item(), "caption": caption})
  
    return result


def main(args, config):
    utils.init_distributed_mode(args)    
    
    device = torch.device(args.device)

    # fix the seed for reproducibility
    seed = args.seed + utils.get_rank()
    torch.manual_seed(seed)
    np.random.seed(seed)
    random.seed(seed)
    cudnn.benchmark = True

    #### Dataset #### 
    print("Creating captioning dataset")
    val_dataset, test_dataset = create_dataset('nocaps', config)  

    if args.distributed:
        num_tasks = utils.get_world_size()
        global_rank = utils.get_rank()            
        samplers = create_sampler([val_dataset,test_dataset], [False,False], num_tasks, global_rank)         
    else:
        samplers = [None,None]
    
    val_loader, test_loader = create_loader([val_dataset, test_dataset],samplers, 
                                            batch_size=[config['batch_size']]*2,num_workers=[4,4],
                                            is_trains=[False, False], collate_fns=[None,None])        

    #### Model #### 
    print("Creating model")
    model = blip_decoder(pretrained=config['pretrained'], image_size=config['image_size'], vit=config['vit'], 
                           prompt=config['prompt'])

    model = model.to(device)   
    
    model_without_ddp = model
    if args.distributed:
        model = torch.nn.parallel.DistributedDataParallel(model, device_ids=[args.gpu])
        model_without_ddp = model.module    
    
    val_result = evaluate(model_without_ddp, val_loader, device, config)  
    val_result_file = save_result(val_result, args.result_dir, 'val', remove_duplicate='image_id')   
    test_result = evaluate(model_without_ddp, test_loader, device, config)  
    test_result_file = save_result(test_result, args.result_dir, 'test', remove_duplicate='image_id') 


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('--config', default='./configs/nocaps.yaml')
    parser.add_argument('--output_dir', default='output/NoCaps')        
    parser.add_argument('--device', default='cuda')
    parser.add_argument('--seed', default=42, type=int)
    parser.add_argument('--world_size', default=1, type=int, help='number of distributed processes')    
    parser.add_argument('--dist_url', default='env://', help='url used to set up distributed training')
    parser.add_argument('--distributed', default=True, type=bool)
    args = parser.parse_args()

    config = yaml.load(open(args.config, 'r'), Loader=yaml.Loader)

    args.result_dir = os.path.join(args.output_dir, 'result')

    Path(args.output_dir).mkdir(parents=True, exist_ok=True)
    Path(args.result_dir).mkdir(parents=True, exist_ok=True)
        
    yaml.dump(config, open(os.path.join(args.output_dir, 'config.yaml'), 'w'))    
    
    main(args, config)