Dear Sir,

The example of OcclusionSensitivity in your example is not workable(https://docs.monai.io/en/latest/visualize.html?highlight=OcclusionSensitivity).

Run:

densenet 3d

from monai.networks.nets import DenseNet
from monai.visualize import OcclusionSensitivity

model_3d = DenseNet(spatial_dims=3, in_channels=1, out_channels=3, init_features=2, growth_rate=2, block_config=(6,))
occ_sens = OcclusionSensitivity(nn_module=model_3d, n_batch=10, stride=2)
occ_map, most_probable_class = occ_sens(torch.rand(1, 1, 6, 6, 6), class_idx=1, b_box=[-1, -1, 2, 3, -1, -1, -1, -1])

Error:

TypeError Traceback (most recent call last)
in
5 model_3d = DenseNet(spatial_dims=3, in_channels=1, out_channels=3, init_features=2, growth_rate=2, block_config=(6,))
6 occ_sens = OcclusionSensitivity(nn_module=model_3d, n_batch=10, stride=2)
----> 7 occ_map, most_probable_class = occ_sens(torch.rand(1, 1, 6, 6, 6), class_idx=1, b_box=[-1, -1, 2, 3, -1, -1, -1, -1])

TypeError: call() got an unexpected keyword argument 'class_idx'

When I deleted 'class_idx', I still had an error:

ValueError Traceback (most recent call last)
in
5 model_3d = DenseNet(spatial_dims=3, in_channels=1, out_channels=3, init_features=2, growth_rate=2, block_config=(6,))
6 occ_sens = OcclusionSensitivity(nn_module=model_3d, n_batch=10, stride=2)
----> 7 occ_map, most_probable_class = occ_sens(torch.rand(1, 1, 6, 6, 6), b_box=[-1, -1, 2, 3, -1, -1, -1, -1])

/environment/python/versions/miniconda3-4.7.12/lib/python3.7/site-packages/monai/visualize/occlusion_sensitivity.py in call(self, x, b_box)
297
298 # Generate sensitivity images
--> 299 sensitivity_ims_list, output_im_shape = self._compute_occlusion_sensitivity(x, b_box)
300
301 # Loop over image for each classification

/environment/python/versions/miniconda3-4.7.12/lib/python3.7/site-packages/monai/visualize/occlusion_sensitivity.py in _compute_occlusion_sensitivity(self, x, b_box)
218 raise ValueError(
219 "Stride and mask size should both be odd or even (element-wise). "
--> 220 + f"stride={self.stride}, mask_size={self.mask_size}"
221 )
222

ValueError: Stride and mask size should both be odd or even (element-wise). stride=[1 2 2 2], mask_size=[ 1 15 15 15]

I have used the corresponding version Monai.