yolo-v4-预测图像绘制

    def detect_image(self, image):
        #---------------------------------------------------#
        #   计算输入图片的高和宽
        #---------------------------------------------------#
        image_shape = np.array(np.shape(image)[0:2])
        #---------------------------------------------------------#
        #   在这里将图像转换成RGB图像，防止灰度图在预测时报错。
        #   代码仅仅支持RGB图像的预测，所有其它类型的图像都会转化成RGB
        #---------------------------------------------------------#
        image       = cvtColor(image)
        #---------------------------------------------------------#
        #   给图像增加灰条，实现不失真的resize
        #   也可以直接resize进行识别
        #---------------------------------------------------------#
        image_data  = resize_image(image, (self.input_shape[1],self.input_shape[0]), self.letterbox_image)
        #---------------------------------------------------------#
        #   添加上batch_size维度
        #---------------------------------------------------------#
        image_data  = np.expand_dims(np.transpose(preprocess_input(np.array(image_data, dtype='float32')), (2, 0, 1)), 0)

        with torch.no_grad():
            images = torch.from_numpy(image_data)
            if self.cuda:
                images = images.cuda()
            #---------------------------------------------------------#
            #   将图像输入网络当中进行预测！
            #---------------------------------------------------------#
            outputs = self.net(images)
            outputs = self.bbox_util.decode_box(outputs)
            #---------------------------------------------------------#
            #   将预测框进行堆叠，然后进行非极大抑制
            #---------------------------------------------------------#
            results = self.bbox_util.non_max_suppression(torch.cat(outputs, 1), self.num_classes, self.input_shape, 
                        image_shape, self.letterbox_image, conf_thres = self.confidence, nms_thres = self.nms_iou)
                                                    
            if results[0] is None: 
                return image

            top_label   = np.array(results[0][:, 6], dtype = 'int32')
            top_conf    = results[0][:, 4] * results[0][:, 5]
            top_boxes   = results[0][:, :4]
        #---------------------------------------------------------#
        #   设置字体与边框厚度
        #---------------------------------------------------------#
        font        = ImageFont.truetype(font='model_data/simhei.ttf', size=np.floor(3e-2 * image.size[1] + 0.5).astype('int32'))
        thickness   = int(max((image.size[0] + image.size[1]) // np.mean(self.input_shape), 1))
        
        #---------------------------------------------------------#
        #   图像绘制
        #---------------------------------------------------------#
        for i, c in list(enumerate(top_label)):
            predicted_class = self.class_names[int(c)]
            box             = top_boxes[i]
            score           = top_conf[i]

            top, left, bottom, right = box

            top     = max(0, np.floor(top).astype('int32'))
            left    = max(0, np.floor(left).astype('int32'))
            bottom  = min(image.size[1], np.floor(bottom).astype('int32'))
            right   = min(image.size[0], np.floor(right).astype('int32'))

            label = '{} {:.2f}'.format(predicted_class, score)
            draw = ImageDraw.Draw(image)
            label_size = draw.textsize(label, font)
            label = label.encode('utf-8')
            print(label, top, left, bottom, right)
            
            if top - label_size[1] >= 0:
                text_origin = np.array([left, top - label_size[1]])
            else:
                text_origin = np.array([left, top + 1])

            for i in range(thickness):
                draw.rectangle([left + i, top + i, right - i, bottom - i], outline=self.colors[c])
            draw.rectangle([tuple(text_origin), tuple(text_origin + label_size)], fill=self.colors[c])
            draw.text(text_origin, str(label,'UTF-8'), fill=(0, 0, 0), font=font)
            del draw

        return image

ImageDraw.Draw.text()用法