File size: 5,944 Bytes
8274714
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
171
172
173
174
175
176
177
178
179
# Copyright (C) 2020 * Ltd. All rights reserved.
# author : Sanghyeon Jo <josanghyeokn@gmail.com>

import gradio as gr

import os
import sys
import copy
import shutil
import random
import argparse
import numpy as np

import imageio

import torch
import torch.nn as nn
import torch.nn.functional as F

from torchvision import transforms
from torch.utils.tensorboard import SummaryWriter

from torch.utils.data import DataLoader

from core.puzzle_utils import *
from core.networks import *
from core.datasets import *

from tools.general.io_utils import *
from tools.general.time_utils import *
from tools.general.json_utils import *

from tools.ai.log_utils import *
from tools.ai.demo_utils import *
from tools.ai.optim_utils import *
from tools.ai.torch_utils import *
from tools.ai.evaluate_utils import *

from tools.ai.augment_utils import *
from tools.ai.randaugment import *

parser = argparse.ArgumentParser()

###############################################################################
# Dataset
###############################################################################
parser.add_argument('--seed', default=2606, type=int)
parser.add_argument('--num_workers', default=4, type=int)
parser.add_argument('--data_dir', default='../VOCtrainval_11-May-2012/', type=str)

###############################################################################
# Network
###############################################################################
parser.add_argument('--architecture', default='DeepLabv3+', type=str)
parser.add_argument('--backbone', default='resnet50', type=str)
parser.add_argument('--mode', default='fix', type=str)
parser.add_argument('--use_gn', default=True, type=str2bool)

###############################################################################
# Inference parameters
###############################################################################
parser.add_argument('--tag', default='', type=str)

parser.add_argument('--domain', default='val', type=str)

parser.add_argument('--scales', default='0.5,1.0,1.5,2.0', type=str)
parser.add_argument('--iteration', default=10, type=int)

if __name__ == '__main__':
    ###################################################################################
    # Arguments
    ###################################################################################
    args = parser.parse_args()

    model_dir = create_directory('./experiments/models/')
    model_path = model_dir + f'DeepLabv3+@ResNet-50@Fix@GN.pth'

    if 'train' in args.domain:
        args.tag += '@train'
    else:
        args.tag += '@' + args.domain

    args.tag += '@scale=%s' % args.scales
    args.tag += '@iteration=%d' % args.iteration

    set_seed(args.seed)
    log_func = lambda string='': print(string)

    ###################################################################################
    # Transform, Dataset, DataLoader
    ###################################################################################
    imagenet_mean = [0.485, 0.456, 0.406]
    imagenet_std = [0.229, 0.224, 0.225]

    normalize_fn = Normalize(imagenet_mean, imagenet_std)

    # for mIoU
    meta_dic = read_json('./data/VOC_2012.json')

    ###################################################################################
    # Network
    ###################################################################################
    if args.architecture == 'DeepLabv3+':
        model = DeepLabv3_Plus(args.backbone, num_classes=meta_dic['classes'] + 1, mode=args.mode,
                               use_group_norm=args.use_gn)
    elif args.architecture == 'Seg_Model':
        model = Seg_Model(args.backbone, num_classes=meta_dic['classes'] + 1)
    elif args.architecture == 'CSeg_Model':
        model = CSeg_Model(args.backbone, num_classes=meta_dic['classes'] + 1)

    model = model.cuda()
    model.eval()

    log_func('[i] Architecture is {}'.format(args.architecture))
    log_func('[i] Total Params: %.2fM' % (calculate_parameters(model)))
    log_func()

    load_model(model, model_path, parallel=False)

    #################################################################################################
    # Evaluation
    #################################################################################################
    eval_timer = Timer()
    scales = [float(scale) for scale in args.scales.split(',')]

    model.eval()
    eval_timer.tik()


    def inference(images, image_size):
        images = images.cuda()

        logits = model(images)
        logits = resize_for_tensors(logits, image_size)

        logits = logits[0] + logits[1].flip(-1)
        logits = get_numpy_from_tensor(logits).transpose((1, 2, 0))
        return logits


    def predict_image(ori_image):
        with torch.no_grad():
            ori_w, ori_h = ori_image.size

            cams_list = []

            for scale in scales:
                image = copy.deepcopy(ori_image)
                image = image.resize((round(ori_w * scale), round(ori_h * scale)), resample=PIL.Image.BICUBIC)

                image = normalize_fn(image)
                image = image.transpose((2, 0, 1))

                image = torch.from_numpy(image)
                flipped_image = image.flip(-1)

                images = torch.stack([image, flipped_image])

                cams = inference(images, (ori_h, ori_w))
                cams_list.append(cams)

            preds = np.sum(cams_list, axis=0)
            preds = F.softmax(torch.from_numpy(preds), dim=-1).numpy()

            if args.iteration > 0:
                preds = crf_inference(np.asarray(ori_image), preds.transpose((2, 0, 1)), t=args.iteration)
                pred_mask = np.argmax(preds, axis=0)
            else:
                pred_mask = np.argmax(preds, axis=-1)

            return pred_mask.astype(np.uint8)


    demo = gr.Interface(
        fn=predict_image,
        inputs="image",
        outputs="image"
    )