fasterRCNN检测时取消/不输出置信度conf

fasterRCNN 检测时取消/不输出置信度conf

在predict.py中，ctrl+鼠标左键点击draw_objs进入draw_box_utils.py中的draw_text函数：


将54行：

isplay_str = f"{category_index[str(cls)]}: {int(100 * score)}%"

改为：

display_str = f"{category_index[str(cls)]}"  # # 不绘制置信度信息conf

然后回去运行predict.py即可。

运行predict.py方法

修改的地方主要有“

model = create_model(num_classes=2)  # 改成自己的类别数目+1，要加上背景）

忘记改这里会报错：

RuntimeError: Error(s) in loading state_dict for FasterRCNN:
	size mismatch for roi_heads.box_predictor.cls_score.weight: copying a param with shape torch.Size([2, 1024]) from checkpoint, the shape in current model is torch.Size([21, 1024]).
	size mismatch for roi_heads.box_predictor.cls_score.bias: copying a param with shape torch.Size([2]) from checkpoint, the shape in current model is torch.Size([21]).
	size mismatch for roi_heads.box_predictor.bbox_pred.weight: copying a param with shape torch.Size([8, 1024]) from checkpoint, the shape in current model is torch.Size([84, 1024]).
	size mismatch for roi_heads.box_predictor.bbox_pred.bias: copying a param with shape torch.Size([8]) from checkpoint, the shape in current model is torch.Size([84]).
python-BaseException

weights_path = "./save_weights/resNetFpn-model-199.pth"   # 换成自己的权重路径

label_json_path = './pascal_voc_classes.json'  # 换成自己的类别的json文件

original_img = Image.open("/media/BilibalaWZ/deep-learning-for-image-processing-master/pytorch_object_detection/faster_rcnn/data_set/test_v5VSobbyyds/B_540_22.jpg")   # 换成自己的图片路径

plot_img.save("./runs/predict/exp2/B_540_22.jpg")  # 更换保存路径

ps：本文使用的fasterrcnn的代码为b站霹雳吧啦WZ的github仓库fasterrcnn代码包。