File size: 4,727 Bytes
625a17f
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
import argparse
import json
import tqdm
import cv2
import os
import numpy as np
import random
from pycocotools.mask import encode, decode, frPyObjects

EVALMODE = "test"


def fuse_mask(mask_list):
    fused_mask = np.zeros_like(mask_list[0])
    for mask in mask_list:
        fused_mask[mask == 1] = 1
    return fused_mask


def blend_mask(input_img, binary_mask, alpha=0.5, color="g"):
    if input_img.ndim == 2:
        return input_img
    mask_image = np.zeros(input_img.shape, np.uint8)
    if color == "r":
        mask_image[:, :, 0] = 255
    if color == "g":
        mask_image[:, :, 1] = 255
    if color == "b":
        mask_image[:, :, 2] = 255
    if color == "o":
        mask_image[:, :, 0] = 255
        mask_image[:, :, 1] = 165
        mask_image[:, :, 2] = 0
    if color == "c":
        mask_image[:, :, 0] = 0
        mask_image[:, :, 1] = 255
        mask_image[:, :, 2] = 255
    if color == "p":
        mask_image[:, :, 0] = 128
        mask_image[:, :, 1] = 0
        mask_image[:, :, 2] = 128


    mask_image = mask_image * np.repeat(binary_mask[:, :, np.newaxis], 3, axis=2)
    blend_image = input_img[:, :, :].copy()
    pos_idx = binary_mask > 0
    for ind in range(input_img.ndim):
        ch_img1 = input_img[:, :, ind]
        ch_img2 = mask_image[:, :, ind]
        ch_img3 = blend_image[:, :, ind]
        ch_img3[pos_idx] = alpha * ch_img1[pos_idx] + (1 - alpha) * ch_img2[pos_idx]
        blend_image[:, :, ind] = ch_img3
    return blend_image


def upsample_mask(mask, frame):
    H, W = frame.shape[:2]
    mH, mW = mask.shape[:2]

    if W > H:
        ratio = mW / W
        h = H * ratio
        diff = int((mH - h) // 2)
        if diff == 0:
            mask = mask
        else:
            mask = mask[diff:-diff]
    else:
        ratio = mH / H
        w = W * ratio
        diff = int((mW - w) // 2)
        if diff == 0:
            mask = mask
        else:
            mask = mask[:, diff:-diff]

    mask = cv2.resize(mask, (W, H))
    return mask


def downsample(mask, frame):
    H, W = frame.shape[:2]
    mH, mW = mask.shape[:2]

    mask = cv2.resize(mask, (W, H))
    return mask


if __name__ == "__main__":
   

    color = ['g', 'r', 'b', 'o', 'c', 'p']
    data_path = "/data/work-gcp-europe-west4-a/yuqian_fu/datasets/HANDAL"
    json_path = "/data/work-gcp-europe-west4-a/yuqian_fu/datasets/HANDAL_results/xmem_handal.json" #debug
    output_path = "/data/work-gcp-europe-west4-a/yuqian_fu/datasets/HANDAL/vis_rondom_check/xmem"
    

    with open(json_path, "r") as fp:
        datas = json.load(fp)

    # datas = random.sample(datas, 10)
    
    
    for data in datas:
        video_name = data["image"].split("/")[0]
        name = data["image"].split("/")[-1]
        frame_idx = name.split(".")[0]
        #target gt
        frame_target = cv2.imread(
                        f"{data_path}/{data['image']}"
                    )


        # for check xmem predicted result
        mask = decode(data["pred_mask"])
        mask = downsample(mask, frame_target)
        out = blend_mask(frame_target, mask, color=color[0])
        os.makedirs(
                        f"{output_path}/xmem", #debug
                        exist_ok=True,
                    )
        cv2.imwrite(
                        f"{output_path}/xmem/{frame_idx}.jpg",  #debug
                        out,
                    )






        # for check handal original json
        # for i,ann in enumerate(data["anns"]):
        #     mask = decode(ann["segmentation"])
        #     mask = downsample(mask, frame_target)
        #     out = blend_mask(frame_target, mask, color=color[0])
        #     os.makedirs(
        #                 f"{output_path}/{video_name}/target_gt", #debug
        #                 exist_ok=True,
        #             )
        #     cv2.imwrite(
        #                 f"{output_path}/{video_name}/target_gt/{frame_idx}.jpg",  #debug
        #                 out,
        #             )
    
        
        # #query gt
        # frame_query = cv2.imread(
        #                 f"{data_path}/{data['first_frame_image']}"
        #             )


        # for i,ann in enumerate(data["first_frame_anns"]):
        #     mask = decode(ann["segmentation"])
        #     mask = downsample(mask, frame_query)
        #     out = blend_mask(frame_query, mask, color=color[0])
        #     os.makedirs(
        #                 f"{output_path}/{video_name}/query_gt",  #debug
        #                 exist_ok=True,
        #             )
        #     cv2.imwrite(
        #                 f"{output_path}/{video_name}/query_gt/{frame_idx}.jpg",  #debug
        #                 out,
        #             )