Mentions légales du service

Skip to content
Snippets Groups Projects
  1. Oct 12, 2020
  2. Sep 21, 2020
  3. Jun 26, 2020
  4. May 02, 2020
  5. Apr 07, 2020
  6. Mar 05, 2020
  7. May 07, 2019
  8. Mar 26, 2019
  9. Sep 25, 2018
  10. Sep 24, 2018
    • AUDEBERT Nicolas's avatar
      Provide a summary of the deep networks at loading time · 5ad0d66d
      AUDEBERT Nicolas authored
      Users asked for a way to see a summary of the network before training.
      We use the torch.summary() function from the torchsummary package to provide users with a list of layers, number of parameters and network weight estimation.
      5ad0d66d
    • AUDEBERT Nicolas's avatar
      Use new .to() function for CPU/GPU agnostic computing · 2eb12bc4
      AUDEBERT Nicolas authored
      PyTorch 4.0 introduced the new device API to simplify tensor storage management.
      We removed all calls to the old .cuda() function and replace them with the new .to() storage management.
        * All functions that previously took a "cuda=" keyword argument now take a "device=" argument that expects either a torch.device object (or a 'cpu' or 'cuda' string if the object is not available).
        * The --cuda CLI argument now expects an integer. -1 is CPU computing (default if omitted), else it is the ordinal of the GPU on which to perform the computation.
      2eb12bc4
  11. May 31, 2018
  12. May 30, 2018
  13. May 29, 2018
Loading