OSSForks/pytorch
1
0
Fork 0
mirror of https://github.com/zebrajr/pytorch.git synced 2025-12-07 12:21:27 +01:00
Code Issues Actions 38 Packages Projects Releases Wiki Activity
2bc6a7a260
pytorch/caffe2/python/layers
History
Frank Jiang b827a40880 Implement bucket-based attention pooling for IdScoreList features (#13004) 
Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/13004

Implement BucketWeighted model layer, which learns a weight for each possible score in an IdScoreList. Here, we assume that the scores in the IdScoreList have already been converted into the appropriate 'buckets'. If this is not done, then essentially each score represents its own bucket.

We assume that the scores/buckets are integers, and if max_score is not set, we assume that the maximum cardinality of the score is less than or equal to the cardinality of the ids.

Reviewed By: chonglinsun

Differential Revision: D10413186

fbshipit-source-id: 743e643a1b36adf124502a8b6b29976158cdb130
2018-10-25 18:04:08 -07:00
..
__init__.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
adaptive_weight.py fbshipit-source-id: ba600fcd2b5cefc7621357bdeb05e24cea02e5af 2018-06-27 04:50:56 -07:00
add_bias.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
arc_cosine_feature_map.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
batch_distill_lr_loss.py Co-disitillation with different archs and/or feature set (#9793) 2018-07-25 10:10:27 -07:00
batch_lr_loss.py [Caffe2][fbcode=>GH sync] Update from facebook 4323b18ce13c (#7116) 2018-05-01 20:49:00 -07:00
batch_mse_loss.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
batch_normalization.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
batch_sigmoid_cross_entropy_loss.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
batch_softmax_loss.py [GanH] Label Smooth: Add Layer and Integrate to SparseNN 2018-03-27 18:10:39 -07:00
blob_weighted_sum.py Update from facebook (#8384) 2018-06-13 13:10:45 -07:00
bucket_weighted.py Implement bucket-based attention pooling for IdScoreList features (#13004) 2018-10-25 18:04:08 -07:00
build_index.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
concat.py refactor preproc, support dense in TumHistory layer 2018-09-05 16:10:13 -07:00
constant_weight.py [Caffe2] Changes done inside Facebook (#6378) 2018-04-10 21:11:43 -07:00
conv.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
dropout.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
fc_without_bias.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
fc.py Update from facebook (#8384) 2018-06-13 13:10:45 -07:00
feature_sparse_to_dense.py support generic feature in DPER2 (#10197) 2018-08-04 15:25:13 -07:00
functional.py Update from facebook (#7855) 2018-05-29 11:38:02 -07:00
gather_record.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
homotopy_weight.py [Caffe2] Changes done inside Facebook (#6378) 2018-04-10 21:11:43 -07:00
label_smooth.py [GanH] Label Smooth: Add Layer and Integrate to SparseNN 2018-03-27 18:10:39 -07:00
last_n_window_collector.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
layer_normalization.py Allow use substitute ops for LayerNorm (#12177) 2018-10-11 17:36:10 -07:00
layers.py [Caffe2][fbcode=>GH sync] Update from facebook 4323b18ce13c (#7116) 2018-05-01 20:49:00 -07:00
margin_rank_loss.py Allow calculating average margin rank loss 2018-03-20 13:34:22 -07:00
merge_id_lists.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
pairwise_similarity.py move matrix formation for dot products to precompute/request-only (#10531) 2018-08-15 11:02:10 -07:00
position_weighted.py Remove unused code base for distributed training (#10282) 2018-08-16 20:10:17 -07:00
random_fourier_features.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
reservoir_sampling.py [Caffe2] Changes done inside Facebook (#6378) 2018-04-10 21:11:43 -07:00
sampling_train.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
sampling_trainable_mixin.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
select_record_by_context.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
semi_random_features.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
sparse_feature_hash.py Update from facebook (#7451) 2018-05-10 23:14:27 -07:00
sparse_lookup.py Revert D10123465: Set the correct engine name for position weighted pooling when fp16 is used for training 2018-10-15 01:53:48 -07:00
split.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00
tags.py Remove unused code base for distributed training (#10282) 2018-08-16 20:10:17 -07:00
uniform_sampling.py Remove Apache headers from source. 2018-03-27 13:10:18 -07:00