Skip to content

Releases: shelfwise/receptivefield

Initial Pytorch API

21 Jul 12:27
Compare
Choose a tag to compare

Release 0.4.0

Major Features And Improvements

  • Added initial Pytorch API with PytorchReceptiveField.

Multiple feature maps

20 Jul 11:19
0b8fb41
Compare
Choose a tag to compare

Release 0.3.0

Major Features And Improvements

  • Update Keras and Tensorflow api for multiple feature maps calculation
  • Change of api in compute function: removed output_layer: str
    and replaced with output_layers: List[str], which can accept a list
    of names for feature maps for which we want to compute receptive fields.
  • Change in plot_gradient_at, added new parameter which control for
    which feature map gradient is plotted. Same for plot_rf_grid function.
  • New functions for plotting: plot_rf_grids and plot_gradients_at.
  • Improved tensorflow API, now one does have to initialize model with
    InteractiveSession, this is handled by the TFReceptiveField.
  • A new API for tensorflow: TFFeatureMapsReceptiveField.

Beta version

27 Nov 20:06
Compare
Choose a tag to compare

First initial version of the repo