Pytorch-UNet/predict_simple_batch.py at master · Zimmer-lab/Pytorch-UNet · 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
import argparse
import logging
import os

import numpy as np
import torch
import torch.nn.functional as F
from PIL import Image

from utils.data_loading import BasicDataset
from unet import UNet
from utils.utils import plot_img_and_mask


def predict_img(net, full_img, device, scale_factor=1, out_threshold=0.5):
    net.eval()
    img = torch.from_numpy(BasicDataset.preprocess(None, full_img, scale_factor, is_mask=False))
    img = img.unsqueeze(0)
    img = img.to(device=device, dtype=torch.float32)

    with torch.no_grad():
        output = net(img).cpu()
        output = F.interpolate(output, (full_img.size[1], full_img.size[0]), mode='bilinear')
        if net.n_classes > 1:
            mask = output.argmax(dim=1)
        else:
            mask = torch.sigmoid(output) > out_threshold

    return mask[0].long().squeeze().numpy()


def get_args():
    parser = argparse.ArgumentParser(description='Predict masks from input images')
    parser.add_argument('--model', '-m', default='MODEL.pth', metavar='FILE',
                        help='Specify the file in which the model is stored')
    parser.add_argument('--input-folder', '-i', required=True, help='Folder of input images')
    parser.add_argument('--output-folder', '-o', required=True, help='Folder to save output images')
    parser.add_argument('--viz', '-v', action='store_true',
                        help='Visualize the images as they are processed')
    parser.add_argument('--no-save', '-n', action='store_true', help='Do not save the output masks')
    parser.add_argument('--mask-threshold', '-t', type=float, default=0.5,
                        help='Minimum probability value to consider a mask pixel white')
    parser.add_argument('--scale', '-s', type=float, default=0.5,
                        help='Scale factor for the input images')
    parser.add_argument('--bilinear', action='store_true', default=False, help='Use bilinear upsampling')
    parser.add_argument('--classes', '-c', type=int, default=2, help='Number of classes')

    return parser.parse_args()


def get_output_filenames(input_folder, output_folder, input_files):
    return [os.path.join(output_folder, os.path.splitext(os.path.basename(fn))[0] + '_OUT.png') for fn in input_files]


def mask_to_image(mask: np.ndarray, mask_values):
    if isinstance(mask_values[0], list):
        out = np.zeros((mask.shape[-2], mask.shape[-1], len(mask_values[0])), dtype=np.uint8)
    elif mask_values == [0, 1]:
        out = np.zeros((mask.shape[-2], mask.shape[-1]), dtype=bool)
    else:
        out = np.zeros((mask.shape[-2], mask.shape[-1]), dtype=np.uint8)

    if mask.ndim == 3:
        mask = np.argmax(mask, axis=0)

    for i, v in enumerate(mask_values):
        out[mask == i] = v

    return Image.fromarray(out)


if __name__ == '__main__':
    args = get_args()
    logging.basicConfig(level=logging.INFO, format='%(levelname)s: %(message)s')

    input_folder = args.input_folder
    output_folder = args.output_folder
    os.makedirs(output_folder, exist_ok=True)

    in_files = [os.path.join(input_folder, f) for f in os.listdir(input_folder) if
                os.path.isfile(os.path.join(input_folder, f))]
    out_files = get_output_filenames(input_folder, output_folder, in_files)

    net = UNet(n_channels=3, n_classes=args.classes, bilinear=args.bilinear)

    device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
    logging.info(f'Loading model {args.model}')
    logging.info(f'Using device {device}')

    net.to(device=device)
    state_dict = torch.load(args.model, map_location=device)
    mask_values = state_dict.pop('mask_values', [0, 1])
    net.load_state_dict(state_dict)

    logging.info('Model loaded!')

    for i, filename in enumerate(in_files):
        logging.info(f'Predicting image {filename} ...')
        img = Image.open(filename)

        mask = predict_img(net=net,
                           full_img=img,
                           scale_factor=args.scale,
                           out_threshold=args.mask_threshold,
                           device=device)

        if not args.no_save:
            out_filename = out_files[i]
            result = mask_to_image(mask, mask_values)
            result.save(out_filename)
            logging.info(f'Mask saved to {out_filename}')

        if args.viz:
            logging.info(f'Visualizing results for image {filename}, close to continue...')
            plot_img_and_mask(img, mask)