mirror of
https://github.com/saymrwulf/pytorch.git
synced 2026-05-15 21:00:47 +00:00
22d4eaeb9e
Summary: Layer to allow model to follow different paths for each instantiation context and join later. Together with tagging system cleanup (this is a separate issue), this should reduce the need to write a layer to differentiate between context. Re: tagging system clean up, we should make exclusion more explicit: EXCLUDE_FROM_<CONTEXT>. This would simplify instation code. TRAIN_ONLY should become a set of all EXCLUDE_FROM_*, except EXCLUDE_FROM_TRAIN. Reviewed By: kennyhorror Differential Revision: D4964949 fbshipit-source-id: ba6453b0deb92d1989404efb9d86e1ed25297202 |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| batch_distill_lr_loss.py | ||
| batch_lr_loss.py | ||
| batch_mse_loss.py | ||
| batch_sigmoid_cross_entropy_loss.py | ||
| batch_softmax_loss.py | ||
| build_index.py | ||
| concat.py | ||
| dot_product.py | ||
| expand_dims.py | ||
| fc.py | ||
| fc_without_bias.py | ||
| functional.py | ||
| gather_record.py | ||
| layers.py | ||
| optimizers.py | ||
| sampling_train.py | ||
| sampling_trainable_mixin.py | ||
| select_record_by_context.py | ||
| simple_operator_layers.py | ||
| sparse_lookup.py | ||
| sparse_to_dense.py | ||
| split.py | ||
| tags.py | ||
| uniform_sampling.py | ||