pytorch/caffe2/python/layers
Xianjie Chen 8a7f00d61b fix mean pooling
Summary:
Segment based Ops requires increasing seg id, and without gap. Lengths based Ops does not
have this requirements.

Otherpooling methods, e.g., LogExpMean does not have Lengths based Ops available yet.

Differential Revision: D5019165

fbshipit-source-id: ab01a220e10d4ed9fa2162939579d346607f905e
2017-05-08 01:09:07 -07:00
..
__init__.py fbsync. TODO: check if build files need update. 2016-11-15 00:00:46 -08:00
batch_distill_lr_loss.py Fix tags to be based on EXCLUDE_FROM_{CONTEXT} 2017-05-02 09:32:27 -07:00
batch_lr_loss.py Fix tags to be based on EXCLUDE_FROM_{CONTEXT} 2017-05-02 09:32:27 -07:00
batch_mse_loss.py Fix tags to be based on EXCLUDE_FROM_{CONTEXT} 2017-05-02 09:32:27 -07:00
batch_sigmoid_cross_entropy_loss.py Fix tags to be based on EXCLUDE_FROM_{CONTEXT} 2017-05-02 09:32:27 -07:00
batch_softmax_loss.py Fix tags to be based on EXCLUDE_FROM_{CONTEXT} 2017-05-02 09:32:27 -07:00
build_index.py MapToRange layer 2017-04-25 16:03:58 -07:00
concat.py Concat axis=0 2017-05-01 12:19:34 -07:00
dot_product.py doxygen python block added 2017-03-29 06:46:16 -07:00
expand_dims.py doxygen python block added 2017-03-29 06:46:16 -07:00
fc.py doxygen python block added 2017-03-29 06:46:16 -07:00
fc_without_bias.py doxygen python block added 2017-03-29 06:46:16 -07:00
functional.py allow to specify output dtypes for functional layers 2017-04-18 16:34:52 -07:00
gather_record.py GatherRecord layer 2017-04-13 15:02:44 -07:00
last_n_window_collector.py LastNWindowCollector 2017-05-04 17:32:09 -07:00
layers.py add workflow for user complicated embedding 2017-05-02 10:46:52 -07:00
optimizers.py Re-apply #266 2017-04-25 21:17:04 -07:00
sampling_train.py Add option to subtract log odd from sampled trained prediction. 2017-04-03 17:50:58 -07:00
sampling_trainable_mixin.py doxygen python block added 2017-03-29 06:46:16 -07:00
select_record_by_context.py JoinContext 2017-05-02 17:32:26 -07:00
simple_operator_layers.py Coerce input of FunctionalLayer to record 2017-04-17 19:26:06 -07:00
sparse_lookup.py fix mean pooling 2017-05-08 01:09:07 -07:00
sparse_to_dense.py Add option to use id_score_list_features column 2017-04-03 17:03:09 -07:00
split.py doxygen python block added 2017-03-29 06:46:16 -07:00
tags.py Fix tags to be based on EXCLUDE_FROM_{CONTEXT} 2017-05-02 09:32:27 -07:00
uniform_sampling.py Re-apply #266 2017-04-25 21:17:04 -07:00