objectdetection-saliency-maps

objectdetection-saliency-maps copied to clipboard

MMdetection 2.x 可视化问题

1

您好，我在进行可视化操作时出现以下报错信息，请问是为什么呢？ 'NoneType' object is not subscriptable File "/data/LiTing/MMdet/interpretation/gradcam.py", line 207, in __call__ gradient = self.gradient[0] # [C,H,W] File "/data/LiTing/MMdet/grade_cam_yolov3.py", line 221, in main mask, box, class_id, score = grad_cam(data, args.bbox_index)...

liting1018

mmdetection3.x版本gradcam可视化

6

你好，请问如何在mmdetection3.x版本上进行gradcam可视化？

LinSY546749

Is it possible for D-RISE to generate heatmaps for mask R-CNN?

9

Hi, I see you use **Yolo v3** to do many tests. Is it possible to apply your D-RISE to the **mask R-CNN**?

mingqiJ

generate a multiple saliency map for different objects at once

3

Hello , I am interested to know how can i generate the saliency map for multiple object in one image. I know how to find a saliency map only for...

alaa-shubbak

How to modify to use in RetinaNet?

13

How can I modify the [gradcam_yolov3.py](https://github.com/RuoyuChen10/objectdetection-saliency-maps/blob/main/tutorial/gradcam-yolov3.ipynb) to use in RetinaNet?

chandlerbing65nm

RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn

2

你好，在使用`gradcam-yolov3`时报错：`RuntimeError: element 0 of tensors does not require grad and does not have a grad_fn` 使用的模型和权重是自己在`mmdetection`中训练的，可用在`gradcam-yolov3`中正确画出框并输出结果。但是在使用`GradCAM_YOLOV3`函数时出现梯度的错误。在该文件定义时使用到`self.net.eval()`，去掉后依旧没有梯度，请问可以解决嘛？

P-HL

您好！ 感谢您精彩的工作和分享！ 我的研究方向是自动驾驶，所以我想调整检测对象的类，将您代码中的 `label_names = [ 'person bev', 'car bev', 'van bev', 'truck bev', 'bus bev', 'person', 'car', 'aeroplane', 'bus', 'train', 'truck', 'boat', 'bird', 'camouflage man' ]` 调整成 `label_names =...

KexuanXia