MolecularDiffusion.modules.layers.equiformer_v2_s.drop¶
Add extra_repr into DropPath implemented by timm for displaying more info.
Classes¶
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). |
|
Consider batch for graph data when dropping paths. |
Functions¶
|
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). |
Module Contents¶
- class MolecularDiffusion.modules.layers.equiformer_v2_s.drop.DropPath(drop_prob=None)¶
Bases:
torch.nn.ModuleDrop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).
- extra_repr()¶
- forward(x)¶
- drop_prob = None¶
- class MolecularDiffusion.modules.layers.equiformer_v2_s.drop.EquivariantDropout(irreps, drop_prob)¶
Bases:
torch.nn.Module- forward(x)¶
- drop¶
- drop_prob¶
- irreps¶
- mul¶
- num_irreps¶
- class MolecularDiffusion.modules.layers.equiformer_v2_s.drop.EquivariantDropoutArraySphericalHarmonics(drop_prob, drop_graph=False)¶
Bases:
torch.nn.Module- extra_repr()¶
- forward(x, batch=None)¶
- drop¶
- drop_graph = False¶
- drop_prob¶
- class MolecularDiffusion.modules.layers.equiformer_v2_s.drop.EquivariantScalarsDropout(irreps, drop_prob)¶
Bases:
torch.nn.Module- extra_repr()¶
- forward(x)¶
- drop_prob¶
- irreps¶
- class MolecularDiffusion.modules.layers.equiformer_v2_s.drop.GraphDropPath(drop_prob=None)¶
Bases:
torch.nn.ModuleConsider batch for graph data when dropping paths.
- extra_repr()¶
- forward(x, batch)¶
- drop_prob = None¶
- MolecularDiffusion.modules.layers.equiformer_v2_s.drop.drop_path(x, drop_prob: float = 0.0, training: bool = False)¶
Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks). This is the same as the DropConnect impl I created for EfficientNet, etc networks, however, the original name is misleading as ‘Drop Connect’ is a different form of dropout in a separate paper… See discussion: https://github.com/tensorflow/tpu/issues/494#issuecomment-532968956 … I’ve opted for changing the layer and argument names to ‘drop path’ rather than mix DropConnect as a layer name and use ‘survival rate’ as the argument.