cavis/libnd4j/include/ops/declarable/generic/nn
Yurii Shyrma 23e4aa99ad
Shyrma lstm layer bp (#370)
* - start working on bp for lstm

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further working on bp for lstmLayer

Signed-off-by: Yurii <iuriish@yahoo.com>

* - minor change

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 3

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 4

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 5

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 6

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 7

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 8

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 9

Signed-off-by: Yurii <iuriish@yahoo.com>

* - provide lstmLayerCell and lstmLayerCellBp as separate CUSTOM_OPs

Signed-off-by: Yurii <iuriish@yahoo.com>

* - testing and fixing lstmLayerCellBp helper

Signed-off-by: Yurii <iuriish@yahoo.com>

* - implement lstmLayerCellBp as separate op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - implement lstmLayerBp as separate op (not tested)

Signed-off-by: Yurii <iuriish@yahoo.com>

* - fixing calculations of dLdWp and dLdb in lstmLayerCellBp

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 10

Signed-off-by: Yurii <iuriish@yahoo.com>

* - fixing typo in lstmLayerTimeLoop

Signed-off-by: Yurii <iuriish@yahoo.com>

* - forgot to perform clipping of c array and calculate corresponding derivative in lstmLayerCellBp

Signed-off-by: Yurii <iuriish@yahoo.com>

* - further work on bp for lstmLayer 10

Signed-off-by: Yurii <iuriish@yahoo.com>

* - testing and fixing bugs in lstmLayer_bp op 1

Signed-off-by: Yurii <iuriish@yahoo.com>

* - testing and fixing bugs in lstmLayer_bp op 2

Signed-off-by: Yurii <iuriish@yahoo.com>

* - turn off heavy tests for cuda for lstmLayer_bp op

Signed-off-by: Yurii <iuriish@yahoo.com>

* - forgot to nullify gradients at eliminated time steps (when sequnce length array is present )

Signed-off-by: Yurii <iuriish@yahoo.com>
2020-04-13 13:21:51 +03:00
..
activations some structure for ops (#337) 2020-03-23 07:28:54 +03:00
convo Shyrma weights format (#329) 2020-03-20 12:11:27 +03:00
pooling Shyrma weights format (#329) 2020-03-20 12:11:27 +03:00
recurrent Shyrma lstm layer bp (#370) 2020-04-13 13:21:51 +03:00
apply_sgd.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
batchnorm.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
bias_add.cpp some structure for ops (#337) 2020-03-23 07:28:54 +03:00
dot_product_attention.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
embedding_lookup.cpp some structure for ops (#337) 2020-03-23 07:28:54 +03:00
fusedBatchNorm.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
layer_norm.cpp some structure for ops (#337) 2020-03-23 07:28:54 +03:00
logSoftmax.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
lrn.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
multi_head_dot_product_attention.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
relu_layer.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
softmax.cpp libnd4j polishing (#273) 2020-03-02 12:49:41 +03:00
xw_plus_b.cpp xw_plus_b mkldnn implementation (#247) 2020-03-31 13:03:10 +03:00