Pytorch实现Faster-RCNN

1
2
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200614150822116.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMzc1MzE4,size_16,color_FFFFFF,t_70)

1
2
3
4
5
6
7
        
        features = self.backbone(images.tensors)
 
        proposals, proposal_losses = self.rpn(images, features, targets)
        detections, detector_losses = self.roi_heads(features, proposals, images.image_sizes, targets)
   

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22



    def forward(self, x):
        identity = x

        out = self.conv1(x)
        out = self.bn1(out)
        out = self.relu(out)

        out = self.conv2(out)
        out = self.bn2(out)

        if self.downsample is not None:
            identity = self.downsample(x)

        out += identity
        out = self.relu(out)

        return out

1
2
3
4
5
objectness, pred_bbox_deltas = self.head(features)
anchors = self.anchor_generator(images, features)

boxes, scores = self.filter_proposals(proposals, objectness, images.image_sizes, num_anchors_per_level)

1
2
3
4
5
6
7
8
9
10
    def forward(self, x):
        # type: (List[Tensor])
        logits = []
        bbox_reg = []
        for feature in x:
            t = F.relu(self.conv(feature))
            logits.append(self.cls_logits(t))  # 对t分类
            bbox_reg.append(self.bbox_pred(t))  # 对t回归
        return logits, bbox_reg

1
2
![在这里插入图片描述](https://img-blog.csdnimg.cn/2020061418492833.png)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
 for boxes, scores, lvl, img_shape in zip(proposals, objectness, levels, image_shapes):
            boxes = box_ops.clip_boxes_to_image(boxes, img_shape)
            keep = box_ops.remove_small_boxes(boxes, self.min_size)
            boxes, scores, lvl = boxes[keep], scores[keep], lvl[keep]
            # non-maximum suppression, independently done per level
            
            # NMS的实现
            keep = box_ops.batched_nms(boxes, scores, lvl, self.nms_thresh)



            # keep only topk scoring predictions
            # keep就是最终保留的
            keep = keep[:self.post_nms_top_n()]



            boxes, scores = boxes[keep], scores[keep]
            final_boxes.append(boxes)
            final_scores.append(scores)
        return final_boxes, final_scores

1
2
![在这里插入图片描述](https://img-blog.csdnimg.cn/2020061419074471.png)

1
2
3
4
5
        box_features = self.box_roi_pool(features, proposals, image_shapes)
        box_features = self.box_head(box_features)
        class_logits, box_regression = self.box_predictor(box_features)
        #class_logits： 分类概率 和 box_regression ：边界框回归

1
2
3
4
        detections, detector_losses = self.roi_heads(features, proposals, images.image_sizes, targets)
        # 映射回原图
        detections = self.transform.postprocess(detections, images.image_sizes, original_image_sizes)  

1
2
        detections = self.transform.postprocess(detections, images.image_sizes, original_image_sizes)  

1
2
![在这里插入图片描述](https://img-blog.csdnimg.cn/20200614150916150.png?x-oss-process=image/watermark,type_ZmFuZ3poZW5naGVpdGk,shadow_10,text_aHR0cHM6Ly9ibG9nLmNzZG4ubmV0L3FxXzQxMzc1MzE4,size_16,color_FFFFFF,t_70)

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
import os
import time
import torch.nn as nn
import torch
import random
import numpy as np
import torchvision.transforms as transforms
import torchvision
from PIL import Image
import torch.nn.functional as F
from tools.my_dataset import PennFudanDataset
#from tools.common_tools import set_seed
from torch.utils.data import DataLoader
from matplotlib import pyplot as plt
from torchvision.models.detection.faster_rcnn import FastRCNNPredictor
from torchvision.transforms import functional as F

#set_seed(1)  # 设置随机种子

BASE_DIR = os.path.dirname(os.path.abspath(__file__))
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

# classes_coco
COCO_INSTANCE_CATEGORY_NAMES = [
    '__background__', 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
    'train', 'truck', 'boat', 'traffic light', 'fire hydrant', 'N/A', 'stop sign',
    'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
    'elephant', 'bear', 'zebra', 'giraffe', 'N/A', 'backpack', 'umbrella', 'N/A', 'N/A',
    'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
    'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
    'bottle', 'N/A', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
    'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
    'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed', 'N/A', 'dining table',
    'N/A', 'N/A', 'toilet', 'N/A', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
    'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'N/A', 'book',
    'clock', 'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush'
]


def vis_bbox(img, output, classes, max_vis=40, prob_thres=0.4):
    fig, ax = plt.subplots(figsize=(12, 12))
    ax.imshow(img, aspect='equal')
    
    out_boxes = output_dict["boxes"].cpu()
    out_scores = output_dict["scores"].cpu()
    out_labels = output_dict["labels"].cpu()
    
    num_boxes = out_boxes.shape[0]
    for idx in range(0, min(num_boxes, max_vis)):

        score = out_scores[idx].numpy()
        bbox = out_boxes[idx].numpy()
        class_name = classes[out_labels[idx]]

        if score < prob_thres:
            continue

        ax.add_patch(plt.Rectangle((bbox[0], bbox[1]), bbox[2] - bbox[0], bbox[3] - bbox[1], fill=False,
                                   edgecolor='red', linewidth=3.5))
        ax.text(bbox[0], bbox[1] - 2, '{:s} {:.3f}'.format(class_name, score), bbox=dict(facecolor='blue', alpha=0.5),
                fontsize=14, color='white')
    plt.show()
    plt.close()


class Compose(object):
    def __init__(self, transforms):
        self.transforms = transforms

    def __call__(self, image, target):
        for t in self.transforms:
            image, target = t(image, target)
        return image, target


class RandomHorizontalFlip(object):
    def __init__(self, prob):
        self.prob = prob

    def __call__(self, image, target):
        if random.random() < self.prob:
            height, width = image.shape[-2:]
            image = image.flip(-1)
            bbox = target["boxes"]
            bbox[:, [0, 2]] = width - bbox[:, [2, 0]]
            target["boxes"] = bbox
        return image, target


class ToTensor(object):
    def __call__(self, image, target):
        image = F.to_tensor(image)
        return image, target


if __name__ == "__main__":

    # config
    LR = 0.001
    num_classes = 2
    batch_size = 1
    start_epoch, max_epoch = 0, 30
    train_dir = os.path.join(BASE_DIR, "data", "PennFudanPed")
    train_transform = Compose([ToTensor(), RandomHorizontalFlip(0.5)])

    # step 1: data
    train_set = PennFudanDataset(data_dir=train_dir, transforms=train_transform)

    # 收集batch data的函数
    def collate_fn(batch):
        return tuple(zip(*batch))

    train_loader = DataLoader(train_set, batch_size=batch_size, collate_fn=collate_fn)

    # step 2: model
    model = torchvision.models.detection.fasterrcnn_resnet50_fpn(pretrained=True)
    in_features = model.roi_heads.box_predictor.cls_score.in_features
    model.roi_heads.box_predictor = FastRCNNPredictor(in_features, num_classes) # replace the pre-trained head with a new one

    model.to(device)

    # step 3: loss
    # in lib/python3.6/site-packages/torchvision/models/detection/roi_heads.py
    # def fastrcnn_loss(class_logits, box_regression, labels, regression_targets)

    # step 4: optimizer scheduler
    params = [p for p in model.parameters() if p.requires_grad]
    optimizer = torch.optim.SGD(params, lr=LR, momentum=0.9, weight_decay=0.0005)
    lr_scheduler = torch.optim.lr_scheduler.StepLR(optimizer, step_size=10, gamma=0.1)

    # step 5: Iteration

    for epoch in range(start_epoch, max_epoch):

        model.train()
        for iter, (images, targets) in enumerate(train_loader):

            images = list(image.to(device) for image in images)
            targets = [{k: v.to(device) for k, v in t.items()} for t in targets]

            # if torch.cuda.is_available():
            #     images, targets = images.to(device), targets.to(device)

            loss_dict = model(images, targets)  # images is list; targets is [ dict["boxes":**, "labels":**], dict[] ]

            losses = sum(loss for loss in loss_dict.values())

            print("Training:Epoch[{:0>3}/{:0>3}] Iteration[{:0>3}/{:0>3}] Loss: {:.4f} ".format(
                epoch, max_epoch, iter + 1, len(train_loader), losses.item()))

            optimizer.zero_grad()
            losses.backward()
            optimizer.step()

        lr_scheduler.step()

    # test
    model.eval()

    # config
    vis_num = 5
    vis_dir = os.path.join(BASE_DIR, "data", "PennFudanPed", "PNGImages")
    img_names = list(filter(lambda x: x.endswith(".png"), os.listdir(vis_dir)))
    random.shuffle(img_names)
    preprocess = transforms.Compose([transforms.ToTensor(), ])

    for i in range(0, vis_num):

        path_img = os.path.join(vis_dir, img_names[i])
        # preprocess
        input_image = Image.open(path_img).convert("RGB")
        img_chw = preprocess(input_image)

        # to device
        if torch.cuda.is_available():
            img_chw = img_chw.to('cuda')
            model.to('cuda')

        # forward
        input_list = [img_chw]
        with torch.no_grad():
            tic = time.time()
            print("input img tensor shape:{}".format(input_list[0].shape))
            output_list = model(input_list)
            output_dict = output_list[0]
            print("pass: {:.3f}s".format(time.time() - tic))

        # visualization
        vis_bbox(input_image, output_dict, COCO_INSTANCE_CATEGORY_NAMES, max_vis=20, prob_thres=0.5)  # for 2 epoch for nms