1. 10 Aug, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Add support of MViTv2 video variants (#6373) · 7e8186e0
      Vasilis Vryniotis authored
      * Extending to support MViTv2
      
      * Fix docs, mypy and linter
      
      * Refactor the relative positional code.
      
      * Code refactoring.
      
      * Rename vars.
      
      * Update docs.
      
      * Replace assert with exception.
      
      * Updat docs.
      
      * Minor refactoring.
      
      * Remove the square input limitation.
      
      * Moving methods around.
      
      * Modify the shortcut in the attention layer.
      
      * Add ported weights.
      
      * Introduce a `residual_cls` config on the attention layer.
      
      * Make the patch_embed kernel/padding/stride configurable.
      
      * Apply changes from code-review.
      
      * Remove stale todo.
      7e8186e0
  2. 24 Jun, 2022 1 commit
    • Vasilis Vryniotis's avatar
      Add MViT architecture in TorchVision (#6198) · fb7f9a16
      Vasilis Vryniotis authored
      * Adding MViT v2 architecture (#6105)
      
      * Adding mvitv2 architecture
      
      * Fixing memory issues on tests and minor refactorings.
      
      * Adding input validation
      
      * Adding docs and minor refactoring
      
      * Add `min_temporal_size` in the supported meta-data.
      
      * Switch Tuple[int, int, int] with List[int] to support easier the 2D case
      
      * Adding more docs and references
      
      * Change naming conventions of classes to follow the same pattern as MobileNetV3
      
      * Fix test breakage.
      
      * Update todos
      
      * Performance optimizations.
      
      * Add support to MViT v1 (#6179)
      
      * Switch implementation to v1 variant.
      
      * Fix docs
      
      * Adding back a v2 pseudovariant
      
      * Changing the way the network are configured.
      
      * Temporarily removing v2
      
      * Adding weights.
      
      * Expand _squeeze/_unsqueeze to support arbitrary dims.
      
      * Update references script.
      
      * Fix tests.
      
      * Fixing frames and preprocessing.
      
      * Fix std/mean values in transforms.
      
      * Add permanent Dropout and update the weights.
      
      * Update accuracies.
      
      * Fix documentation
      
      * Remove unnecessary expected file.
      
      * Skip big model test
      
      * Rewrite the configuration logic to reduce LOC.
      
      * Fix mypy
      fb7f9a16