New CAM technique: KPCA-CAM (#534)

* Update svd_on_activations.py

added kernel pca

* Create kpca_cam.py

* Update svd_on_activations.py

Author: SachinKarmani

pytorch_grad_cam/kpca_cam.py

@@ -0,0 +1,20 @@
+from pytorch_grad_cam.base_cam import BaseCAM
+from pytorch_grad_cam.utils.svd_on_activations import get_2d_projection_kernel
+
+class KPCA_CAM(BaseCAM):
+    def __init__(self, model, target_layers, 
+                 reshape_transform=None, kernel='sigmoid', gamma=None):
+        super(KPCA_CAM, self).__init__(model,
+                                       target_layers,
+                                       reshape_transform,
+                                       uses_gradients=False,
+                                       kernel=kernel, gamma=gamma)
+
+    def get_cam_image(self,
+                      input_tensor,
+                      target_layer,
+                      target_category,
+                      activations,
+                      grads,
+                      eigen_smooth):
+        return get_2d_projection_kernel(activations, self.kernel, self.gamma)

pytorch_grad_cam/utils/svd_on_activations.py

@@ -1,4 +1,5 @@
 import numpy as np
+from sklearn.decomposition import KernelPCA
 
 
 def get_2d_projection(activation_batch):
@@ -17,3 +18,18 @@ def get_2d_projection(activation_batch):
         projection = projection.reshape(activations.shape[1:])
         projections.append(projection)
     return np.float32(projections)
+
+
+
+def get_2d_projection_kernel(activation_batch, kernel='sigmoid', gamma=None):
+    activation_batch[np.isnan(activation_batch)] = 0
+    projections = []
+    for activations in activation_batch:
+        reshaped_activations = activations.reshape(activations.shape[0], -1).transpose()
+        reshaped_activations = reshaped_activations - reshaped_activations.mean(axis=0)
+        # Apply Kernel PCA
+        kpca = KernelPCA(n_components=1, kernel=kernel, gamma=gamma)
+        projection = kpca.fit_transform(reshaped_activations)
+        projection = projection.reshape(activations.shape[1:])
+        projections.append(projection)
+    return np.float32(projections)