File size: 5,093 Bytes
017c046
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
"""
Faster R-CNN ๋ฐ‘๋ฐ”๋‹ฅ ๊ตฌํ˜„ โ€” ์ถ”๋ก (inference) ์Šคํฌ๋ฆฝํŠธ
=====================================================
ํ•™์Šต๋œ frcnn.pth ๋กœ ์ž„์˜์˜ ์ด๋ฏธ์ง€์—์„œ ๊ฐ์ฒด๋ฅผ ํƒ์ง€ํ•˜๊ณ ,
๋ฐ•์Šค + ํด๋ž˜์Šค๋ช… + ์ ์ˆ˜๋ฅผ ๊ทธ๋ ค์„œ ์ €์žฅํ•œ๋‹ค.

์‹คํ–‰ ์˜ˆ:
  # ์ด๋ฏธ์ง€ ํ•œ ์žฅ
  python infer.py --ckpt frcnn.pth --image test.jpg

  # ํด๋” ์•ˆ ๋ชจ๋“  ์ด๋ฏธ์ง€
  python infer.py --ckpt frcnn.pth --image_dir ./samples --out_dir ./results

  # ์ ์ˆ˜ ์ž„๊ณ„๊ฐ’ ์กฐ์ •(๊ธฐ๋ณธ 0.5)
  python infer.py --ckpt frcnn.pth --image test.jpg --score_thresh 0.7

์ฃผ์˜:
  - train.py, model.py ๋“ฑ๊ณผ ๊ฐ™์€ ํด๋”์—์„œ ์‹คํ–‰ํ•  ๊ฒƒ.
  - ํ•™์Šต๊ณผ ๋™์ผํ•œ ๋ฆฌ์‚ฌ์ด์ฆˆ/์ •๊ทœํ™”๋ฅผ ์ ์šฉํ•ด์•ผ ๊ฒฐ๊ณผ๊ฐ€ ์ •์ƒ.
"""

import os
import argparse

import torch
from PIL import Image, ImageDraw, ImageFont
import torchvision.transforms.functional as F

from model import FasterRCNN
from dataset import NUM_CLASSES, VOC_CLASSES


# ํด๋ž˜์Šค๋ณ„ ์ƒ‰์ƒ(20๊ฐœ) โ€” ์‹œ๊ฐ์ ์œผ๋กœ ๊ตฌ๋ถ„๋˜๋„๋ก HSV ๋ถ„ํ• 
def _class_colors():
    import colorsys
    colors = []
    for i in range(len(VOC_CLASSES)):
        h = i / len(VOC_CLASSES)
        r, g, b = colorsys.hsv_to_rgb(h, 0.75, 0.95)
        colors.append((int(r * 255), int(g * 255), int(b * 255)))
    return colors

CLASS_COLORS = _class_colors()


def preprocess(pil_img, min_size=600, max_size=1000):
    """ํ•™์Šต๊ณผ ๋™์ผํ•œ ๋ฆฌ์‚ฌ์ด์ฆˆ + ์ •๊ทœํ™”. ์›๋ณธ ๋ณต์›์šฉ scale๋„ ๋ฐ˜ํ™˜."""
    w, h = pil_img.size
    short, long = min(w, h), max(w, h)
    scale = min_size / short
    if long * scale > max_size:
        scale = max_size / long
    new_w, new_h = int(round(w * scale)), int(round(h * scale))

    resized = pil_img.resize((new_w, new_h), Image.BILINEAR)
    t = F.to_tensor(resized)
    t = F.normalize(t, mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
    return t, scale


def draw_detections(pil_img, boxes, labels, scores, scale):
    """ํƒ์ง€ ๊ฒฐ๊ณผ๋ฅผ ์›๋ณธ ์ด๋ฏธ์ง€ ์ขŒํ‘œ๋กœ ๋˜๋Œ๋ ค ๋ฐ•์Šค์™€ ๋ผ๋ฒจ์„ ๊ทธ๋ฆฐ๋‹ค."""
    draw = ImageDraw.Draw(pil_img)
    try:
        font = ImageFont.truetype("arial.ttf", 16)
    except Exception:
        font = ImageFont.load_default()

    for box, label, score in zip(boxes, labels, scores):
        # ๋ชจ๋ธ์€ ๋ฆฌ์‚ฌ์ด์ฆˆ๋œ ์ขŒํ‘œ๋ฅผ ์ถœ๋ ฅ โ†’ ์›๋ณธ ํฌ๊ธฐ๋กœ ๋˜๋Œ๋ฆผ(รทscale)
        x1, y1, x2, y2 = (box / scale).tolist()
        cls_idx = int(label) - 1  # 0=๋ฐฐ๊ฒฝ ์ œ์™ธ
        if cls_idx < 0 or cls_idx >= len(VOC_CLASSES):
            continue
        name = VOC_CLASSES[cls_idx]
        color = CLASS_COLORS[cls_idx]

        # ๋ฐ•์Šค
        draw.rectangle([x1, y1, x2, y2], outline=color, width=3)

        # ๋ผ๋ฒจ ๋ฐฐ๊ฒฝ + ํ…์ŠคํŠธ
        text = f"{name} {score:.2f}"
        tb = draw.textbbox((x1, y1), text, font=font)
        draw.rectangle([tb[0], tb[1], tb[2], tb[3]], fill=color)
        draw.text((x1, y1), text, fill="white", font=font)

    return pil_img


@torch.no_grad()
def infer_image(model, img_path, device, score_thresh):
    pil = Image.open(img_path).convert("RGB")
    tensor, scale = preprocess(pil)
    tensor = tensor.to(device).unsqueeze(0)

    det = model(tensor)  # eval ๋ชจ๋“œ โ†’ {boxes, labels, scores}
    keep = det["scores"] >= score_thresh
    boxes = det["boxes"][keep].cpu()
    labels = det["labels"][keep].cpu()
    scores = det["scores"][keep].cpu()

    result = draw_detections(pil, boxes, labels, scores, scale)
    return result, len(boxes)


def main():
    ap = argparse.ArgumentParser()
    ap.add_argument("--ckpt", required=True, help="ํ•™์Šต๋œ ๊ฐ€์ค‘์น˜ (frcnn.pth)")
    ap.add_argument("--image", help="๋‹จ์ผ ์ด๋ฏธ์ง€ ๊ฒฝ๋กœ")
    ap.add_argument("--image_dir", help="์ด๋ฏธ์ง€ ํด๋” ๊ฒฝ๋กœ")
    ap.add_argument("--out_dir", default="./results", help="๊ฒฐ๊ณผ ์ €์žฅ ํด๋”")
    ap.add_argument("--score_thresh", type=float, default=0.5,
                    help="์ด ์ ์ˆ˜ ์ด์ƒ๋งŒ ํ‘œ์‹œ")
    args = ap.parse_args()

    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
    print("device:", device)

    model = FasterRCNN(NUM_CLASSES).to(device)
    model.load_state_dict(torch.load(args.ckpt, map_location=device))
    model.eval()
    print(f"๋ชจ๋ธ ๋กœ๋“œ ์™„๋ฃŒ: {args.ckpt}")

    os.makedirs(args.out_dir, exist_ok=True)

    # ์ฒ˜๋ฆฌํ•  ์ด๋ฏธ์ง€ ๋ชฉ๋ก ๊ตฌ์„ฑ
    targets = []
    if args.image:
        targets.append(args.image)
    if args.image_dir:
        for fn in os.listdir(args.image_dir):
            if fn.lower().endswith((".jpg", ".jpeg", ".png", ".bmp")):
                targets.append(os.path.join(args.image_dir, fn))

    if not targets:
        print("์ด๋ฏธ์ง€๋ฅผ ์ง€์ •ํ•˜์„ธ์š”: --image ๋˜๋Š” --image_dir")
        return

    for path in targets:
        result, n = infer_image(model, path, device, args.score_thresh)
        out_path = os.path.join(args.out_dir, "det_" + os.path.basename(path))
        result.save(out_path)
        print(f"  {os.path.basename(path)}: {n}๊ฐœ ํƒ์ง€ โ†’ {out_path}")

    print(f"์™„๋ฃŒ. ๊ฒฐ๊ณผ๋Š” {args.out_dir} ํด๋”์— ์ €์žฅ๋จ.")


if __name__ == "__main__":
    main()