RCNN、Fast RCNN、Faster RCNN、Mask RCNN 要点简单归纳

RCNN

RCNN使用算则行搜索算法，先在图像上生成一系列候选区域，再分别在每个候选区域进行卷积运算提取特征，之后再单独进行预测

class RCNN(nn.Module):
    def __init__(self, num_classes):
        super(RCNN, self).__init__()
        # 使用预训练的 ResNet-50 作为基础网络
        self.backbone = torchvision.models.resnet50(pretrained=True)
        # 替换 ResNet-50 的最后一层全连接层
        self.backbone.fc = nn.Linear(2048, 512)

    def forward(self, x):
        # 基础网络前向传播
        features = self.backbone(x)
        # flatten
        features = features.view(features.size(0), -1)
        return features
#实例化基础网络
model=RCNN.eval()

def get_regions(image_path):
    # 使用OpenCV的选择性搜索算法生成候选区域
    img = cv2.imread(image_path)
    img_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
    ss = cv2.ximgproc.segmentation.createSelectiveSearchSegmentation()
    ss.setBaseImage(img_rgb)
    ss.switchToSelectiveSearchFast()
    rects = ss.process()
    return img_rgb, rects
def extract_features(image, rects, model, transform):
    features = []
    regions = []
    for (x