Helper Module for Deep Learning.

Module that provides tools to compute class activation map.

class pynet.cam.FeatureExtractor(model, target_layers)[source]¶

Class for extracting activations and registering gradients from targetted intermediate layers.

__init__(model, target_layers)[source]¶

Initialize self. See help(type(self)) for accurate signature.

save_gradient(grad)[source]¶

class pynet.cam.GradCam(model, target_layers, labels, top=1)[source]¶

Class for computing class activation map.

__init__(model, target_layers, labels, top=1)[source]¶

Initialize self. See help(type(self)) for accurate signature.

forward(input)[source]¶

class pynet.cam.ModelOutputs(model, target_layers)[source]¶

Class for making a forward pass, and getting: 1- the network output. 2- activations from intermeddiate targetted layers. 3- gradients from intermeddiate targetted layers.

__init__(model, target_layers)[source]¶

Initialize self. See help(type(self)) for accurate signature.

get_activations(x)[source]¶

get_activations_gradient()[source]¶