File size: 10,228 Bytes
1e84a23
 
3b57cb5
15a1060
3b57cb5
d5b6416
 
f542926
3b57cb5
 
f542926
 
1e84a23
 
1fca7a7
b5659d1
1fca7a7
 
 
b5659d1
 
ff02ae0
 
1e84a23
 
 
ff02ae0
 
b5659d1
1e84a23
1fca7a7
1e84a23
916d4aa
1e84a23
 
 
 
12b0c04
 
 
1e84a23
 
ff02ae0
1e84a23
 
 
 
 
 
 
 
 
 
 
 
ff02ae0
1e84a23
 
 
 
 
 
b5659d1
1e84a23
 
 
 
 
 
 
 
 
 
ff02ae0
 
1e84a23
 
 
 
 
 
 
 
 
 
 
 
 
 
b5659d1
1e84a23
b5659d1
1e84a23
 
 
 
 
 
 
 
 
 
 
 
 
5387d47
 
c4cb785
 
3b57cb5
 
c4cb785
 
3b57cb5
c4cb785
 
 
 
 
 
3b57cb5
 
 
 
 
 
 
 
 
f542926
3b57cb5
f542926
3b57cb5
f542926
 
 
 
 
3b57cb5
 
f542926
 
3b57cb5
 
f542926
 
3b57cb5
f542926
3b57cb5
f542926
225845e
 
f542926
 
3b57cb5
 
 
 
f542926
3b57cb5
 
 
 
 
f542926
 
 
3b57cb5
 
 
f542926
 
 
 
 
 
 
 
 
 
 
 
 
 
 
199c9c7
 
f542926
 
225845e
f542926
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3b57cb5
225845e
 
 
 
 
 
 
 
 
 
 
3b57cb5
5387d47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a97c3f9
 
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
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
# This file contains modules common to various models

import math

import numpy as np
import torch
import torch.nn as nn
from PIL import Image, ImageDraw

from utils.datasets import letterbox
from utils.general import non_max_suppression, make_divisible, scale_coords, xyxy2xywh
from utils.plots import color_list


def autopad(k, p=None):  # kernel, padding
    # Pad to 'same'
    if p is None:
        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
    return p


def DWConv(c1, c2, k=1, s=1, act=True):
    # Depthwise convolution
    return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)


class Conv(nn.Module):
    # Standard convolution
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super(Conv, self).__init__()
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
        self.bn = nn.BatchNorm2d(c2)
        self.act = nn.Hardswish() if act else nn.Identity()

    def forward(self, x):
        return self.act(self.bn(self.conv(x)))

    def fuseforward(self, x):
        return self.act(self.conv(x))


class Bottleneck(nn.Module):
    # Standard bottleneck
    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
        super(Bottleneck, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_, c2, 3, 1, g=g)
        self.add = shortcut and c1 == c2

    def forward(self, x):
        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))


class BottleneckCSP(nn.Module):
    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
        super(BottleneckCSP, self).__init__()
        c_ = int(c2 * e)  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
        self.cv4 = Conv(2 * c_, c2, 1, 1)
        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
        self.act = nn.LeakyReLU(0.1, inplace=True)
        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])

    def forward(self, x):
        y1 = self.cv3(self.m(self.cv1(x)))
        y2 = self.cv2(x)
        return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))


class SPP(nn.Module):
    # Spatial pyramid pooling layer used in YOLOv3-SPP
    def __init__(self, c1, c2, k=(5, 9, 13)):
        super(SPP, self).__init__()
        c_ = c1 // 2  # hidden channels
        self.cv1 = Conv(c1, c_, 1, 1)
        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])

    def forward(self, x):
        x = self.cv1(x)
        return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))


class Focus(nn.Module):
    # Focus wh information into c-space
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
        super(Focus, self).__init__()
        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)

    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
        return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))


class Concat(nn.Module):
    # Concatenate a list of tensors along dimension
    def __init__(self, dimension=1):
        super(Concat, self).__init__()
        self.d = dimension

    def forward(self, x):
        return torch.cat(x, self.d)


class NMS(nn.Module):
    # Non-Maximum Suppression (NMS) module
    conf = 0.25  # confidence threshold
    iou = 0.45  # IoU threshold
    classes = None  # (optional list) filter by class

    def __init__(self):
        super(NMS, self).__init__()

    def forward(self, x):
        return non_max_suppression(x[0], conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)


class autoShape(nn.Module):
    # input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
    img_size = 640  # inference size (pixels)
    conf = 0.25  # NMS confidence threshold
    iou = 0.45  # NMS IoU threshold
    classes = None  # (optional list) filter by class

    def __init__(self, model):
        super(autoShape, self).__init__()
        self.model = model.eval()

    def forward(self, imgs, size=640, augment=False, profile=False):
        # supports inference from various sources. For height=720, width=1280, RGB images example inputs are:
        #   opencv:     imgs = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(720,1280,3)
        #   PIL:        imgs = Image.open('image.jpg')  # HWC x(720,1280,3)
        #   numpy:      imgs = np.zeros((720,1280,3))  # HWC
        #   torch:      imgs = torch.zeros(16,3,720,1280)  # BCHW
        #   multiple:   imgs = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images

        p = next(self.model.parameters())  # for device and type
        if isinstance(imgs, torch.Tensor):  # torch
            return self.model(imgs.to(p.device).type_as(p), augment, profile)  # inference

        # Pre-process
        if not isinstance(imgs, list):
            imgs = [imgs]
        shape0, shape1 = [], []  # image and inference shapes
        batch = range(len(imgs))  # batch size
        for i in batch:
            imgs[i] = np.array(imgs[i])  # to numpy
            if imgs[i].shape[0] < 5:  # image in CHW
                imgs[i] = imgs[i].transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
            imgs[i] = imgs[i][:, :, :3] if imgs[i].ndim == 3 else np.tile(imgs[i][:, :, None], 3)  # enforce 3ch input
            s = imgs[i].shape[:2]  # HWC
            shape0.append(s)  # image shape
            g = (size / max(s))  # gain
            shape1.append([y * g for y in s])
        shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)]  # inference shape
        x = [letterbox(imgs[i], new_shape=shape1, auto=False)[0] for i in batch]  # pad
        x = np.stack(x, 0) if batch[-1] else x[0][None]  # stack
        x = np.ascontiguousarray(x.transpose((0, 3, 1, 2)))  # BHWC to BCHW
        x = torch.from_numpy(x).to(p.device).type_as(p) / 255.  # uint8 to fp16/32

        # Inference
        with torch.no_grad():
            y = self.model(x, augment, profile)[0]  # forward
        y = non_max_suppression(y, conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)  # NMS

        # Post-process
        for i in batch:
            if y[i] is not None:
                y[i][:, :4] = scale_coords(shape1, y[i][:, :4], shape0[i])

        return Detections(imgs, y, self.names)


class Detections:
    # detections class for YOLOv5 inference results
    def __init__(self, imgs, pred, names=None):
        super(Detections, self).__init__()
        self.imgs = imgs  # list of images as numpy arrays
        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
        self.names = names  # class names
        self.xyxy = pred  # xyxy pixels
        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
        d = pred[0].device  # device
        gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs]  # normalizations
        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
        self.n = len(self.pred)

    def display(self, pprint=False, show=False, save=False):
        colors = color_list()
        for i, (img, pred) in enumerate(zip(self.imgs, self.pred)):
            str = f'Image {i + 1}/{len(self.pred)}: {img.shape[0]}x{img.shape[1]} '
            if pred is not None:
                for c in pred[:, -1].unique():
                    n = (pred[:, -1] == c).sum()  # detections per class
                    str += f'{n} {self.names[int(c)]}s, '  # add to string
                if show or save:
                    img = Image.fromarray(img.astype(np.uint8)) if isinstance(img, np.ndarray) else img  # from np
                    for *box, conf, cls in pred:  # xyxy, confidence, class
                        # str += '%s %.2f, ' % (names[int(cls)], conf)  # label
                        ImageDraw.Draw(img).rectangle(box, width=4, outline=colors[int(cls) % 10])  # plot
            if save:
                f = f'results{i}.jpg'
                str += f"saved to '{f}'"
                img.save(f)  # save
            if show:
                img.show(f'Image {i}')  # show
            if pprint:
                print(str)

    def print(self):
        self.display(pprint=True)  # print results

    def show(self):
        self.display(show=True)  # show results

    def save(self):
        self.display(save=True)  # save results

    def __len__(self):
        return self.n

    def tolist(self):
        # return a list of Detections objects, i.e. 'for result in results.tolist():'
        x = [Detections([self.imgs[i]], [self.pred[i]], self.names) for i in range(self.n)]
        for d in x:
            for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
                setattr(d, k, getattr(d, k)[0])  # pop out of list
        return x


class Flatten(nn.Module):
    # Use after nn.AdaptiveAvgPool2d(1) to remove last 2 dimensions
    @staticmethod
    def forward(x):
        return x.view(x.size(0), -1)


class Classify(nn.Module):
    # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
        super(Classify, self).__init__()
        self.aap = nn.AdaptiveAvgPool2d(1)  # to x(b,c1,1,1)
        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)  # to x(b,c2,1,1)
        self.flat = Flatten()

    def forward(self, x):
        z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1)  # cat if list
        return self.flat(self.conv(z))  # flatten to x(b,c2)