在类别激活图可视化时EdgeNeXt模型为何报错

[xiadaidiyishenqing]

代码为：
python tools/vis_cam.py datasets/test/female/2023-11-27160803.png models/edgenext/edgenext_small.py

错误信息如下：
Automatically choose the last norm layer as target_layer.
Traceback (most recent call last):
File "tools/vis_cam.py", line 357, in
main()
File "tools/vis_cam.py", line 351, in main
aug_smooth=args.aug_smooth)
File "D:\anaconda\envs\CD\lib\site-packages\pytorch_grad_cam\base_cam.py", line 189, in call
targets, eigen_smooth)
File "D:\anaconda\envs\CD\lib\site-packages\pytorch_grad_cam\base_cam.py", line 97, in forward
eigen_smooth)
File "D:\anaconda\envs\CD\lib\site-packages\pytorch_grad_cam\base_cam.py", line 132, in compute_cam_per_layer
eigen_smooth)
File "D:\anaconda\envs\CD\lib\site-packages\pytorch_grad_cam\base_cam.py", line 54, in get_cam_image
grads)
File "D:\anaconda\envs\CD\lib\site-packages\pytorch_grad_cam\grad_cam.py", line 22, in get_cam_weights
return np.mean(grads, axis=(2, 3))
File "<array_function internals>", line 6, in mean
File "D:\anaconda\envs\CD\lib\site-packages\numpy\core\fromnumeric.py", line 3373, in mean
out=out, **kwargs)
File "D:\anaconda\envs\CD\lib\site-packages\numpy\core_methods.py", line 148, in _mean
rcount = _count_reduce_items(arr, axis)
File "D:\anaconda\envs\CD\lib\site-packages\numpy\core_methods.py", line 67, in _count_reduce_items
items *= arr.shape[mu.normalize_axis_index(ax, arr.ndim)]
numpy.AxisError: axis 2 is out of bounds for array of dimension 2