About membership

Sign in Get started

Jeff Liu

33 Following 3 Followers

Highlighted by Jeff Liu

From ConvNets Series. Spatial Transformer Networks by Kirill Danilyuk
Layer 10: Transformer: Grid Generator and Sampler. This logic is implemented in spatial_transformer.py . This layer outputs transformed images with the same dimensions as the original one (32x32x1) with affine transformation applied to it (e.g., a zoomed in or a rotated image).
From ConvNets Series. Spatial Transformer Networks by Kirill Danilyuk
The STN is a differentiable module which can be injected in a convolutional neural network. The default choice is to place it right “after” the input layer to make it learn the best transformation matrix theta which minimizes the loss function of the main classifier (in our case, this is IDSIA).
From ConvNets Series. Spatial Transformer Networks by Kirill Danilyuk
STNs can be viewed as an alternative to image augmentation, which is a default way to achieve spatial invariance for a CNN.

Claps from Jeff Liu