File size: 4,507 Bytes
f7f604d
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
import os
import sys
import tqdm

import pandas as pd
import numpy as np

from PIL import Image

filepath = os.path.split(os.path.abspath(__file__))[0]
repopath = os.path.split(filepath)[0]
sys.path.append(repopath)

from utils.eval_functions import *
from utils.misc import *

BETA = 1.0

def evaluate(opt, args):
    if os.path.isdir(opt.Eval.result_path) is False:
        os.makedirs(opt.Eval.result_path)
        
    method = os.path.split(opt.Eval.pred_root)[-1]

    if args.verbose is True:
        print('#' * 20, 'Start Evaluation', '#' * 20)
        datasets = tqdm.tqdm(opt.Eval.datasets, desc='Expr - ' + method, total=len(
            opt.Eval.datasets), position=0, bar_format='{desc:<30}{percentage:3.0f}%|{bar:50}{r_bar}')
    else:
        datasets = opt.Eval.datasets

    results = []

    for dataset in datasets:
        pred_root = os.path.join(opt.Eval.pred_root, dataset)
        gt_root = os.path.join(opt.Eval.gt_root, dataset, 'masks')

        preds = os.listdir(pred_root)
        gts = os.listdir(gt_root)
        
        preds = sort(preds)
        gts = sort(gts)
        
        preds = [i for i in preds if i in gts]
        gts = [i for i in gts if i in preds]
        
        FM = Fmeasure()
        WFM = WeightedFmeasure()
        SM = Smeasure()
        EM = Emeasure()
        MAE = Mae()
        MSE = Mse()
        MBA = BoundaryAccuracy()
        IOU = IoU()
        BIOU = BIoU()
        TIOU = TIoU()

        if args.verbose is True:
            samples = tqdm.tqdm(enumerate(zip(preds, gts)), desc=dataset + ' - Evaluation', total=len(
                preds), position=1, leave=False, bar_format='{desc:<30}{percentage:3.0f}%|{bar:50}{r_bar}')
        else:
            samples = enumerate(zip(preds, gts))

        for i, sample in samples:
            pred, gt = sample

            pred_mask = np.array(Image.open(os.path.join(pred_root, pred)).convert('L'))
            gt_mask = np.array(Image.open(os.path.join(gt_root, gt)).convert('L'))

            if len(pred_mask.shape) != 2:
                pred_mask = pred_mask[:, :, 0]
            if len(gt_mask.shape) != 2:
                gt_mask = gt_mask[:, :, 0]

            assert pred_mask.shape == gt_mask.shape, print(pred, 'does not match the size of', gt)
            # print(gt_mask.max())

            FM.step( pred=pred_mask, gt=gt_mask)
            WFM.step(pred=pred_mask, gt=gt_mask)
            SM.step( pred=pred_mask, gt=gt_mask)
            EM.step( pred=pred_mask, gt=gt_mask)
            MAE.step(pred=pred_mask, gt=gt_mask)
            MSE.step(pred=pred_mask, gt=gt_mask)
            MBA.step(pred=pred_mask, gt=gt_mask)
            IOU.step(pred=pred_mask, gt=gt_mask)
            BIOU.step(pred=pred_mask, gt=gt_mask)
            TIOU.step(pred=pred_mask, gt=gt_mask)
            
        result = []

        Sm =  SM.get_results()["sm"]
        wFm = WFM.get_results()["wfm"]
        mae = MAE.get_results()["mae"]
        mse = MSE.get_results()["mse"]
        mBA = MBA.get_results()["mba"]
        
        Fm =  FM.get_results()["fm"]
        Em =  EM.get_results()["em"]
        Iou = IOU.get_results()["iou"]
        BIou = BIOU.get_results()["biou"]
        TIou = TIOU.get_results()["tiou"]
        
        adpEm = Em["adp"]
        avgEm = Em["curve"].mean()
        maxEm = Em["curve"].max()
        adpFm = Fm["adp"]
        avgFm = Fm["curve"].mean()
        maxFm = Fm["curve"].max()
        avgIou = Iou["curve"].mean()
        maxIou = Iou["curve"].max()
        avgBIou = BIou["curve"].mean()
        maxBIou = BIou["curve"].max()
        avgTIou = TIou["curve"].mean()
        maxTIou = TIou["curve"].max()
        
        out = dict()
        for metric in opt.Eval.metrics:
            out[metric] = eval(metric)

        pkl = os.path.join(opt.Eval.result_path, 'result_' + dataset + '.pkl')
        if os.path.isfile(pkl) is True:
            result = pd.read_pickle(pkl)
            result.loc[method] = out
            result.to_pickle(pkl)
        else:
            result = pd.DataFrame(data=out, index=[method])
            result.to_pickle(pkl)
        result.to_csv(os.path.join(opt.Eval.result_path, 'result_' + dataset + '.csv'))
        results.append(result)
        
    if args.verbose is True:
        for dataset, result in zip(datasets, results):
            print('###', dataset, '###', '\n', result.sort_index(), '\n')
    
if __name__ == "__main__":
    args = parse_args()
    opt = load_config(args.config)
    evaluate(opt, args)