Visualizations

Tensorboard visuals

monai.visualize.img2tensorboard.add_animated_gif(writer, tag, image_tensor, max_out, scale_factor, global_step=None)[source]

Creates an animated gif out of an image tensor in ‘CHWD’ format and writes it with SummaryWriter.

Parameters
  • writer (SummaryWriter) – Tensorboard SummaryWriter to write to

  • tag (str) – Data identifier

  • image_tensor (Union[ndarray, Tensor]) – tensor for the image to add, expected to be in CHWD format

  • max_out (int) – maximum number of slices to animate through

  • scale_factor (float) – amount to multiply values by. If the image data is between 0 and 1, using 255 for this value will scale it to displayable range

  • global_step (Optional[int]) – Global step value to record

Return type

None

monai.visualize.img2tensorboard.add_animated_gif_no_channels(writer, tag, image_tensor, max_out, scale_factor, global_step=None)[source]

Creates an animated gif out of an image tensor in ‘HWD’ format that does not have a channel dimension and writes it with SummaryWriter. This is similar to the “add_animated_gif” after inserting a channel dimension of 1.

Parameters
  • writer (SummaryWriter) – Tensorboard SummaryWriter to write to

  • tag (str) – Data identifier

  • image_tensor (Union[ndarray, Tensor]) – tensor for the image to add, expected to be in CHWD format

  • max_out (int) – maximum number of slices to animate through

  • scale_factor (float) – amount to multiply values by. If the image data is between 0 and 1, using 255 for this value will scale it to displayable range

  • global_step (Optional[int]) – Global step value to record

Return type

None

monai.visualize.img2tensorboard.make_animated_gif_summary(tag, image, max_out=3, animation_axes=(3), image_axes=(1, 2), other_indices=None, scale_factor=1.0)[source]

Creates an animated gif out of an image tensor in ‘CHWD’ format and returns Summary.

Parameters
  • tag (str) – Data identifier

  • image (Union[ndarray, Tensor]) – The image, expected to be in CHWD format

  • max_out (int) – maximum number of slices to animate through

  • animation_axes (Sequence[int]) – axis to animate on (not currently used)

  • image_axes (Sequence[int]) – axes of image (not currently used)

  • other_indices (Optional[Dict]) – (not currently used)

  • scale_factor (float) – amount to multiply values by. if the image data is between 0 and 1, using 255 for this value will scale it to displayable range

Return type

Summary

monai.visualize.img2tensorboard.plot_2d_or_3d_image(data, step, writer, index=0, max_channels=1, max_frames=64, tag='output')[source]

Plot 2D or 3D image on the TensorBoard, 3D image will be converted to GIF image.

Note

Plot 3D or 2D image(with more than 3 channels) as separate images.

Parameters
  • data (Union[Tensor, ndarray]) – target data to be plotted as image on the TensorBoard. The data is expected to have ‘NCHW[D]’ dimensions, and only plot the first in the batch.

  • step (int) – current step to plot in a chart.

  • writer (SummaryWriter) – specify TensorBoard SummaryWriter to plot the image.

  • index (int) – plot which element in the input data batch, default is the first element.

  • max_channels (int) – number of channels to plot.

  • max_frames (int) – number of frames for 2D-t plot.

  • tag (str) – tag of the plotted image on TensorBoard.

Return type

None

Class activation map

class monai.visualize.class_activation_maps.CAM(nn_module, target_layers, fc_layers='fc', upsampler=<function default_upsampler>, postprocessing=<function default_normalizer>)[source]

Compute class activation map from the last fully-connected layers before the spatial pooling.

Examples

# densenet 2d
from monai.networks.nets import densenet121
from monai.visualize import CAM

model_2d = densenet121(spatial_dims=2, in_channels=1, out_channels=3)
cam = CAM(nn_module=model_2d, target_layers="class_layers.relu", fc_layers="class_layers.out")
result = cam(x=torch.rand((1, 1, 48, 64)))

# resnet 2d
from monai.networks.nets import se_resnet50
from monai.visualize import CAM

model_2d = se_resnet50(spatial_dims=2, in_channels=3, num_classes=4)
cam = CAM(nn_module=model_2d, target_layers="layer4", fc_layers="last_linear")
result = cam(x=torch.rand((2, 3, 48, 64)))
Parameters
  • nn_module (Module) – the model to be visualized

  • target_layers (str) – name of the model layer to generate the feature map.

  • fc_layers (Union[str, Callable]) – a string or a callable used to get fully-connected weights to compute activation map from the target_layers (without pooling). and evaluate it at every spatial location.

  • upsampler (Callable) – An upsampling method to upsample the output image. Default is N dimensional linear (bilinear, trilinear, etc.) depending on num spatial dimensions of input.

  • postprocessing (Callable) – a callable that applies on the upsampled output image. Default is normalizing between min=1 and max=0 (i.e., largest input will become 0 and smallest input will become 1).

compute_map(x, class_idx=None, layer_idx=- 1)[source]

Compute the actual feature map with input tensor x.

class monai.visualize.class_activation_maps.GradCAM(nn_module, target_layers, upsampler=<function default_upsampler>, postprocessing=<function default_normalizer>, register_backward=True)[source]

Computes Gradient-weighted Class Activation Mapping (Grad-CAM). This implementation is based on:

Selvaraju et al., Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization, https://arxiv.org/abs/1610.02391

Examples

# densenet 2d
from monai.networks.nets import densenet121
from monai.visualize import GradCAM

model_2d = densenet121(spatial_dims=2, in_channels=1, out_channels=3)
cam = GradCAM(nn_module=model_2d, target_layers="class_layers.relu")
result = cam(x=torch.rand((1, 1, 48, 64)))

# resnet 2d
from monai.networks.nets import se_resnet50
from monai.visualize import GradCAM

model_2d = se_resnet50(spatial_dims=2, in_channels=3, num_classes=4)
cam = GradCAM(nn_module=model_2d, target_layers="layer4")
result = cam(x=torch.rand((2, 3, 48, 64)))
compute_map(x, class_idx=None, retain_graph=False, layer_idx=- 1)[source]

Compute the actual feature map with input tensor x.

class monai.visualize.class_activation_maps.GradCAMpp(nn_module, target_layers, upsampler=<function default_upsampler>, postprocessing=<function default_normalizer>, register_backward=True)[source]

Computes Gradient-weighted Class Activation Mapping (Grad-CAM++). This implementation is based on:

Chattopadhyay et al., Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networks, https://arxiv.org/abs/1710.11063

compute_map(x, class_idx=None, retain_graph=False, layer_idx=- 1)[source]

Compute the actual feature map with input tensor x.

class monai.visualize.class_activation_maps.ModelWithHooks(nn_module, target_layer_names, register_forward=False, register_backward=False)[source]

A model wrapper to run model forward/backward steps and storing some intermediate feature/gradient information.

Parameters
  • nn_module – the model to be wrapped.

  • target_layer_names (Union[str, Sequence[str]]) – the names of the layer to cache.

  • register_forward (bool) – whether to cache the forward pass output corresponding to target_layer_names.

  • register_backward (bool) – whether to cache the backward pass output corresponding to target_layer_names.

get_layer(layer_id)[source]
Parameters

layer_id (Union[str, Callable]) – a layer name string or a callable. If it is a callable such as lambda m: m.fc, this method will return the module self.model.fc.

Returns

a submodule from self.model.

monai.visualize.class_activation_maps.default_normalizer(x)[source]

A linear intensity scaling by mapping the (min, max) to (1, 0).

N.B.: This will flip magnitudes (i.e., smallest will become biggest and vice versa).

Return type

ndarray

Occlusion sensitivity

class monai.visualize.occlusion_sensitivity.OcclusionSensitivity(nn_module, pad_val=None, mask_size=15, n_batch=128, stride=1, upsampler=functools.partial(<function default_upsampler>, align_corners=True), verbose=True)[source]

This class computes the occlusion sensitivity for a model’s prediction of a given image. By occlusion sensitivity, we mean how the probability of a given prediction changes as the occluded section of an image changes. This can be useful to understand why a network is making certain decisions.

As important parts of the image are occluded, the probability of classifying the image correctly will decrease. Hence, more negative values imply the corresponding occluded volume was more important in the decision process.

Two torch.Tensor will be returned by the __call__ method: an occlusion map and an image of the most probable class. Both images will be cropped if a bounding box used, but voxel sizes will always match the input.

The occlusion map shows the inference probabilities when the corresponding part of the image is occluded. Hence, more -ve values imply that region was important in the decision process. The map will have shape BCHW(D)N, where N is the number of classes to be inferred by the network. Hence, the occlusion for class i can be seen with map[...,i].

The most probable class is an image of the probable class when the corresponding part of the image is occluded (equivalent to occ_map.argmax(dim=-1)).

See: R. R. Selvaraju et al. Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization. https://doi.org/10.1109/ICCV.2017.74.

Examples:

# densenet 2d
from monai.networks.nets import densenet121
from monai.visualize import OcclusionSensitivity

model_2d = densenet121(spatial_dims=2, in_channels=1, out_channels=3)
occ_sens = OcclusionSensitivity(nn_module=model_2d)
occ_map, most_probable_class = occ_sens(x=torch.rand((1, 1, 48, 64)), class_idx=None, b_box=[-1, -1, 2, 40, 1, 62])

# 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])

See also

  • monai.visualize.occlusion_sensitivity.OcclusionSensitivity.

Occlusion sensitivitiy constructor.

Parameters
  • nn_module (Module) – Classification model to use for inference

  • pad_val (Optional[float]) – When occluding part of the image, which values should we put in the image? If None is used, then the average of the image will be used.

  • mask_size (Union[int, Sequence]) – Size of box to be occluded, centred on the central voxel. To ensure that the occluded area is correctly centred, mask_size and stride should both be odd or even.

  • n_batch (int) – Number of images in a batch for inference.

  • stride (Union[int, Sequence]) – Stride in spatial directions for performing occlusions. Can be single value or sequence (for varying stride in the different directions). Should be >= 1. Striding in the channel direction will always be 1.

  • upsampler (Optional[Callable]) – An upsampling method to upsample the output image. Default is N-dimensional linear (bilinear, trilinear, etc.) depending on num spatial dimensions of input.

  • verbose (bool) – Use tdqm.trange output (if available).