FM / python

/usr/local/lib64/python3.6/site-packages/caffe2/python/

/usr/local/lib64/python3.6/site-packages/caffe2/python

Name	Size	Mode	Actions
docs/	-	0755	rm
examples/	-	0755	rm
fakelowp/	-	0755	rm
helpers/	-	0755	rm
ideep/	-	0755	rm
layers/	-	0755	rm
mint/	-	0755	rm
mkl/	-	0755	rm
modeling/	-	0755	rm
models/	-	0755	rm
onnx/	-	0755	rm
operator_test/	-	0755	rm
predictor/	-	0755	rm
rnn/	-	0755	rm
serialized_test/	-	0755	rm
test/	-	0755	rm
trt/	-	0755	rm
__pycache__/	-	0755	rm
allcompare_test.py	2255	0644	edit dl rm
attention.py	12359	0644	edit dl rm
benchmark_generator.py	4912	0644	edit dl rm
binarysize.py	5521	0644	edit dl rm
brew.py	4762	0644	edit dl rm
brew_test.py	11739	0644	edit dl rm
build.py	153	0644	edit dl rm
cached_reader.py	4394	0644	edit dl rm
caffe2_pybind11_state.cpython-36m-x86_64-linux-gnu.so	48299712	0755	edit dl rm
caffe2_pybind11_state_gpu.cpython-36m-x86_64-linux-gnu.so	49048144	0755	edit dl rm
caffe_translator.py	35227	0644	edit dl rm
caffe_translator_test.py	3553	0644	edit dl rm
checkpoint.py	32101	0644	edit dl rm
checkpoint_test.py	13405	0644	edit dl rm
cnn.py	7626	0644	edit dl rm
context.py	2841	0644	edit dl rm
context_test.py	1792	0644	edit dl rm
control.py	19309	0644	edit dl rm
control_ops_grad.py	28893	0644	edit dl rm
control_ops_grad_test.py	1752	0644	edit dl rm
control_ops_util.py	10863	0644	edit dl rm
control_test.py	12276	0644	edit dl rm
convert.py	55	0644	edit dl rm
convert_test.py	201	0644	edit dl rm
convnet_benchmarks.py	20533	0644	edit dl rm
convnet_benchmarks_test.py	839	0644	edit dl rm
core.py	119400	0644	edit dl rm
core_gradients_test.py	38022	0644	edit dl rm
core_test.py	47683	0644	edit dl rm
crf.py	13250	0644	edit dl rm
crf_predict.py	1159	0644	edit dl rm
crf_viterbi_test.py	1663	0644	edit dl rm
dataio.py	23532	0644	edit dl rm
dataio_test.py	17575	0644	edit dl rm
dataset.py	12886	0644	edit dl rm
data_parallel_model.py	83100	0644	edit dl rm
data_parallel_model_test.py	56145	0644	edit dl rm
data_workers.py	15941	0644	edit dl rm
data_workers_test.py	6561	0644	edit dl rm
db_file_reader.py	6608	0644	edit dl rm
db_test.py	1110	0644	edit dl rm
device_checker.py	5157	0644	edit dl rm
dyndep.py	1533	0644	edit dl rm
embedding_generation_benchmark.py	5256	0644	edit dl rm
experiment_util.py	3625	0644	edit dl rm
extension_loader.py	744	0644	edit dl rm
fakefp16_transform_lib.py	322	0644	edit dl rm
filler_test.py	748	0644	edit dl rm
functional.py	4415	0644	edit dl rm
functional_test.py	4204	0644	edit dl rm
fused_8bit_rowwise_conversion_ops_test.py	3945	0644	edit dl rm
gradient_checker.py	15377	0644	edit dl rm
gradient_check_test.py	20729	0644	edit dl rm
gru_cell.py	5129	0644	edit dl rm
hip_test_util.py	405	0644	edit dl rm
hsm_util.py	2259	0644	edit dl rm
hypothesis_test.py	105762	0644	edit dl rm
hypothesis_test_util.py	26853	0644	edit dl rm
ideep_test_util.py	998	0644	edit dl rm
layers_test.py	92931	0644	edit dl rm
layer_model_helper.py	29340	0644	edit dl rm
layer_model_instantiator.py	3935	0644	edit dl rm
layer_parameter_sharing_test.py	9148	0644	edit dl rm
layer_test_util.py	4875	0644	edit dl rm
lazy.py	277	0644	edit dl rm
lazy_dyndep.py	2562	0644	edit dl rm
lazy_dyndep_test.py	3914	0644	edit dl rm
lengths_reducer_fused_8bit_rowwise_ops_test.py	7575	0644	edit dl rm
lengths_reducer_rowwise_8bit_ops_test.py	5710	0644	edit dl rm
lstm_benchmark.py	10649	0644	edit dl rm
memonger.py	34041	0644	edit dl rm
memonger_test.py	36910	0644	edit dl rm
mkl_test_util.py	1142	0644	edit dl rm
model_device_test.py	4777	0644	edit dl rm
model_helper.py	23492	0644	edit dl rm
model_helper_test.py	2336	0644	edit dl rm
modifier_context.py	1772	0644	edit dl rm
muji.py	8131	0644	edit dl rm
muji_test.py	3058	0644	edit dl rm
net_builder.py	27679	0644	edit dl rm
net_builder_test.py	11382	0644	edit dl rm
net_drawer.py	14264	0644	edit dl rm
net_printer.py	12704	0644	edit dl rm
net_printer_test.py	3190	0644	edit dl rm
nomnigraph.py	4216	0644	edit dl rm
nomnigraph_test.py	15427	0644	edit dl rm
nomnigraph_transformations.py	3787	0644	edit dl rm
nomnigraph_transformations_test.py	5767	0644	edit dl rm
normalizer.py	1411	0644	edit dl rm
normalizer_context.py	1007	0644	edit dl rm
normalizer_test.py	487	0644	edit dl rm
numa_benchmark.py	2230	0644	edit dl rm
numa_test.py	1663	0644	edit dl rm
observer_test.py	5316	0644	edit dl rm
operator_fp_exceptions_test.py	1248	0644	edit dl rm
optimizer.py	78813	0644	edit dl rm
optimizer_context.py	1462	0644	edit dl rm
optimizer_test.py	30705	0644	edit dl rm
optimizer_test_util.py	9187	0644	edit dl rm
parallelize_bmuf_distributed_test.py	9908	0644	edit dl rm
parallel_workers.py	7682	0644	edit dl rm
parallel_workers_test.py	3501	0644	edit dl rm
pipeline.py	17283	0644	edit dl rm
pipeline_test.py	2542	0644	edit dl rm
predictor_constants.py	198	0644	edit dl rm
python_op_test.py	9169	0644	edit dl rm
queue_util.py	4459	0644	edit dl rm
record_queue.py	4453	0644	edit dl rm
recurrent.py	13297	0644	edit dl rm
regularizer.py	21120	0644	edit dl rm
regularizer_context.py	1013	0644	edit dl rm
regularizer_test.py	10266	0644	edit dl rm
rnn_cell.py	68233	0644	edit dl rm
schema.py	45621	0644	edit dl rm
schema_test.py	15754	0644	edit dl rm
scope.py	3623	0644	edit dl rm
scope_test.py	5249	0644	edit dl rm
session.py	7642	0644	edit dl rm
session_test.py	2078	0644	edit dl rm
sparse_to_dense_mask_test.py	6565	0644	edit dl rm
sparse_to_dense_test.py	3556	0644	edit dl rm
task.py	24274	0644	edit dl rm
task_test.py	870	0644	edit dl rm
test_util.py	3524	0644	edit dl rm
text_file_reader.py	1990	0644	edit dl rm
timeout_guard.py	4054	0644	edit dl rm
toy_regression_test.py	2822	0644	edit dl rm
transformations.py	1832	0644	edit dl rm
transformations_test.py	11960	0644	edit dl rm
tt_core.py	9349	0644	edit dl rm
tt_core_test.py	2518	0644	edit dl rm
utils.py	14181	0644	edit dl rm
utils_test.py	1399	0644	edit dl rm
visualize.py	6315	0644	edit dl rm
workspace.py	25263	0644	edit dl rm
workspace_test.py	34844	0644	edit dl rm
_import_c_extension.py	2250	0644	edit dl rm
__init__.py	3925	0644	edit dl rm

Edit: /usr/local/lib64/python3.6/site-packages/caffe2/python/attention.py (12359B)

## @package attention
# Module caffe2.python.attention

from caffe2.python import brew

class AttentionType:
    Regular, Recurrent, Dot, SoftCoverage = tuple(range(4))

def s(scope, name):
    # We have to manually scope due to our internal/external blob
    # relationships.
    return "{}/{}".format(str(scope), str(name))

# c_i = \sum_j w_{ij}\textbf{s}_j
def _calc_weighted_context(
    model,
    encoder_outputs_transposed,
    encoder_output_dim,
    attention_weights_3d,
    scope,
):
    # [batch_size, encoder_output_dim, 1]
    attention_weighted_encoder_context = brew.batch_mat_mul(
        model,
        [encoder_outputs_transposed, attention_weights_3d],
        s(scope, 'attention_weighted_encoder_context'),
    )
    # [batch_size, encoder_output_dim]
    attention_weighted_encoder_context, _ = model.net.Reshape(
        attention_weighted_encoder_context,
        [
            attention_weighted_encoder_context,
            s(scope, 'attention_weighted_encoder_context_old_shape'),
        ],
        shape=[1, -1, encoder_output_dim],
    )
    return attention_weighted_encoder_context

# Calculate a softmax over the passed in attention energy logits
def _calc_attention_weights(
    model,
    attention_logits_transposed,
    scope,
    encoder_lengths=None,
):
    if encoder_lengths is not None:
        attention_logits_transposed = model.net.SequenceMask(
            [attention_logits_transposed, encoder_lengths],
            ['masked_attention_logits'],
            mode='sequence',
        )

# [batch_size, encoder_length, 1]
    attention_weights_3d = brew.softmax(
        model,
        attention_logits_transposed,
        s(scope, 'attention_weights_3d'),
        engine='CUDNN',
        axis=1,
    )
    return attention_weights_3d

# e_{ij} = \textbf{v}^T tanh \alpha(\textbf{h}_{i-1}, \textbf{s}_j)
def _calc_attention_logits_from_sum_match(
    model,
    decoder_hidden_encoder_outputs_sum,
    encoder_output_dim,
    scope,
):
    # [encoder_length, batch_size, encoder_output_dim]
    decoder_hidden_encoder_outputs_sum = model.net.Tanh(
        decoder_hidden_encoder_outputs_sum,
        decoder_hidden_encoder_outputs_sum,
    )

# [encoder_length, batch_size, 1]
    attention_logits = brew.fc(
        model,
        decoder_hidden_encoder_outputs_sum,
        s(scope, 'attention_logits'),
        dim_in=encoder_output_dim,
        dim_out=1,
        axis=2,
        freeze_bias=True,
    )

# [batch_size, encoder_length, 1]
    attention_logits_transposed = brew.transpose(
        model,
        attention_logits,
        s(scope, 'attention_logits_transposed'),
        axes=[1, 0, 2],
    )
    return attention_logits_transposed

# \textbf{W}^\alpha used in the context of \alpha_{sum}(a,b)
def _apply_fc_weight_for_sum_match(
    model,
    input,
    dim_in,
    dim_out,
    scope,
    name,
):
    output = brew.fc(
        model,
        input,
        s(scope, name),
        dim_in=dim_in,
        dim_out=dim_out,
        axis=2,
    )
    output = model.net.Squeeze(
        output,
        output,
        dims=[0],
    )
    return output

# Implement RecAtt due to section 4.1 in http://arxiv.org/abs/1601.03317
def apply_recurrent_attention(
    model,
    encoder_output_dim,
    encoder_outputs_transposed,
    weighted_encoder_outputs,
    decoder_hidden_state_t,
    decoder_hidden_state_dim,
    attention_weighted_encoder_context_t_prev,
    scope,
    encoder_lengths=None,
):
    weighted_prev_attention_context = _apply_fc_weight_for_sum_match(
        model=model,
        input=attention_weighted_encoder_context_t_prev,
        dim_in=encoder_output_dim,
        dim_out=encoder_output_dim,
        scope=scope,
        name='weighted_prev_attention_context',
    )

weighted_decoder_hidden_state = _apply_fc_weight_for_sum_match(
        model=model,
        input=decoder_hidden_state_t,
        dim_in=decoder_hidden_state_dim,
        dim_out=encoder_output_dim,
        scope=scope,
        name='weighted_decoder_hidden_state',
    )
    # [1, batch_size, encoder_output_dim]
    decoder_hidden_encoder_outputs_sum_tmp = model.net.Add(
        [
            weighted_prev_attention_context,
            weighted_decoder_hidden_state,
        ],
        s(scope, 'decoder_hidden_encoder_outputs_sum_tmp'),
    )
    # [encoder_length, batch_size, encoder_output_dim]
    decoder_hidden_encoder_outputs_sum = model.net.Add(
        [
            weighted_encoder_outputs,
            decoder_hidden_encoder_outputs_sum_tmp,
        ],
        s(scope, 'decoder_hidden_encoder_outputs_sum'),
        broadcast=1,
    )
    attention_logits_transposed = _calc_attention_logits_from_sum_match(
        model=model,
        decoder_hidden_encoder_outputs_sum=decoder_hidden_encoder_outputs_sum,
        encoder_output_dim=encoder_output_dim,
        scope=scope,
    )

# [batch_size, encoder_length, 1]
    attention_weights_3d = _calc_attention_weights(
        model=model,
        attention_logits_transposed=attention_logits_transposed,
        scope=scope,
        encoder_lengths=encoder_lengths,
    )

# [batch_size, encoder_output_dim, 1]
    attention_weighted_encoder_context = _calc_weighted_context(
        model=model,
        encoder_outputs_transposed=encoder_outputs_transposed,
        encoder_output_dim=encoder_output_dim,
        attention_weights_3d=attention_weights_3d,
        scope=scope,
    )
    return attention_weighted_encoder_context, attention_weights_3d, [
        decoder_hidden_encoder_outputs_sum,
    ]

def apply_regular_attention(
    model,
    encoder_output_dim,
    encoder_outputs_transposed,
    weighted_encoder_outputs,
    decoder_hidden_state_t,
    decoder_hidden_state_dim,
    scope,
    encoder_lengths=None,
):
    weighted_decoder_hidden_state = _apply_fc_weight_for_sum_match(
        model=model,
        input=decoder_hidden_state_t,
        dim_in=decoder_hidden_state_dim,
        dim_out=encoder_output_dim,
        scope=scope,
        name='weighted_decoder_hidden_state',
    )

# [encoder_length, batch_size, encoder_output_dim]
    decoder_hidden_encoder_outputs_sum = model.net.Add(
        [weighted_encoder_outputs, weighted_decoder_hidden_state],
        s(scope, 'decoder_hidden_encoder_outputs_sum'),
        broadcast=1,
        use_grad_hack=1,
    )

attention_logits_transposed = _calc_attention_logits_from_sum_match(
        model=model,
        decoder_hidden_encoder_outputs_sum=decoder_hidden_encoder_outputs_sum,
        encoder_output_dim=encoder_output_dim,
        scope=scope,
    )

def apply_dot_attention(
    model,
    encoder_output_dim,
    # [batch_size, encoder_output_dim, encoder_length]
    encoder_outputs_transposed,
    # [1, batch_size, decoder_state_dim]
    decoder_hidden_state_t,
    decoder_hidden_state_dim,
    scope,
    encoder_lengths=None,
):
    if decoder_hidden_state_dim != encoder_output_dim:
        weighted_decoder_hidden_state = brew.fc(
            model,
            decoder_hidden_state_t,
            s(scope, 'weighted_decoder_hidden_state'),
            dim_in=decoder_hidden_state_dim,
            dim_out=encoder_output_dim,
            axis=2,
        )
    else:
        weighted_decoder_hidden_state = decoder_hidden_state_t

# [batch_size, decoder_state_dim]
    squeezed_weighted_decoder_hidden_state = model.net.Squeeze(
        weighted_decoder_hidden_state,
        s(scope, 'squeezed_weighted_decoder_hidden_state'),
        dims=[0],
    )

# [batch_size, decoder_state_dim, 1]
    expanddims_squeezed_weighted_decoder_hidden_state = model.net.ExpandDims(
        squeezed_weighted_decoder_hidden_state,
        squeezed_weighted_decoder_hidden_state,
        dims=[2],
    )

# [batch_size, encoder_output_dim, 1]
    attention_logits_transposed = model.net.BatchMatMul(
        [
            encoder_outputs_transposed,
            expanddims_squeezed_weighted_decoder_hidden_state,
        ],
        s(scope, 'attention_logits'),
        trans_a=1,
    )

def apply_soft_coverage_attention(
    model,
    encoder_output_dim,
    encoder_outputs_transposed,
    weighted_encoder_outputs,
    decoder_hidden_state_t,
    decoder_hidden_state_dim,
    scope,
    encoder_lengths,
    coverage_t_prev,
    coverage_weights,
):

# [encoder_length, batch_size, encoder_output_dim]
    decoder_hidden_encoder_outputs_sum_tmp = model.net.Add(
        [weighted_encoder_outputs, weighted_decoder_hidden_state],
        s(scope, 'decoder_hidden_encoder_outputs_sum_tmp'),
        broadcast=1,
    )
    # [batch_size, encoder_length]
    coverage_t_prev_2d = model.net.Squeeze(
        coverage_t_prev,
        s(scope, 'coverage_t_prev_2d'),
        dims=[0],
    )
    # [encoder_length, batch_size]
    coverage_t_prev_transposed = brew.transpose(
        model,
        coverage_t_prev_2d,
        s(scope, 'coverage_t_prev_transposed'),
    )

# [encoder_length, batch_size, encoder_output_dim]
    scaled_coverage_weights = model.net.Mul(
        [coverage_weights, coverage_t_prev_transposed],
        s(scope, 'scaled_coverage_weights'),
        broadcast=1,
        axis=0,
    )

# [encoder_length, batch_size, encoder_output_dim]
    decoder_hidden_encoder_outputs_sum = model.net.Add(
        [decoder_hidden_encoder_outputs_sum_tmp, scaled_coverage_weights],
        s(scope, 'decoder_hidden_encoder_outputs_sum'),
    )

# [batch_size, encoder_length, 1]
    attention_logits_transposed = _calc_attention_logits_from_sum_match(
        model=model,
        decoder_hidden_encoder_outputs_sum=decoder_hidden_encoder_outputs_sum,
        encoder_output_dim=encoder_output_dim,
        scope=scope,
    )

# [batch_size, encoder_length]
    attention_weights_2d = model.net.Squeeze(
        attention_weights_3d,
        s(scope, 'attention_weights_2d'),
        dims=[2],
    )

coverage_t = model.net.Add(
        [coverage_t_prev, attention_weights_2d],
        s(scope, 'coverage_t'),
        broadcast=1,
    )

return (
        attention_weighted_encoder_context,
        attention_weights_3d,
        [decoder_hidden_encoder_outputs_sum],
        coverage_t,
    )

cmd: