未验证 提交 f4a3956b 编写于 作者: G Guo Sheng 提交者: GitHub

Update some en api docs (#20496) (#20516)

* Fix api docs. test=document-fix

* Fix en docs. test=develop

* Fix the doc of dynamic_gru. test=document_fix

* Update API.spec. test=document_fix

* Fix codestyle test=develop, test=document_fix
上级 8975d6fe
......@@ -127,15 +127,15 @@ paddle.fluid.layers.center_loss (ArgSpec(args=['input', 'label', 'num_classes',
paddle.fluid.layers.embedding (ArgSpec(args=['input', 'size', 'is_sparse', 'is_distributed', 'padding_idx', 'param_attr', 'dtype'], varargs=None, keywords=None, defaults=(False, False, None, None, 'float32')), ('document', 'c51fcac7a4f5786ca41f27fa60bd22c5'))
paddle.fluid.layers.dynamic_lstm (ArgSpec(args=['input', 'size', 'h_0', 'c_0', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'dtype', 'name'], varargs=None, keywords=None, defaults=(None, None, None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'float32', None)), ('document', 'd4a82e2f5feb20c4a23ced8054e047ed'))
paddle.fluid.layers.dynamic_lstmp (ArgSpec(args=['input', 'size', 'proj_size', 'param_attr', 'bias_attr', 'use_peepholes', 'is_reverse', 'gate_activation', 'cell_activation', 'candidate_activation', 'proj_activation', 'dtype', 'name', 'h_0', 'c_0', 'cell_clip', 'proj_clip'], varargs=None, keywords=None, defaults=(None, None, True, False, 'sigmoid', 'tanh', 'tanh', 'tanh', 'float32', None, None, None, None, None)), ('document', 'b35fe3e0c2ecca15a8be658277e064ec'))
paddle.fluid.layers.dynamic_gru (ArgSpec(args=['input', 'size', 'param_attr', 'bias_attr', 'is_reverse', 'gate_activation', 'candidate_activation', 'h_0', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, False, 'sigmoid', 'tanh', None, False)), ('document', '83617c165827e030636c80486d5de6f3'))
paddle.fluid.layers.gru_unit (ArgSpec(args=['input', 'hidden', 'size', 'param_attr', 'bias_attr', 'activation', 'gate_activation', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, 'tanh', 'sigmoid', False)), ('document', '33974b9bfa69f2f1eb85e6f956dff04e'))
paddle.fluid.layers.dynamic_gru (ArgSpec(args=['input', 'size', 'param_attr', 'bias_attr', 'is_reverse', 'gate_activation', 'candidate_activation', 'h_0', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, False, 'sigmoid', 'tanh', None, False)), ('document', 'a3364b36fb3190b9bd75e419aa75573b'))
paddle.fluid.layers.gru_unit (ArgSpec(args=['input', 'hidden', 'size', 'param_attr', 'bias_attr', 'activation', 'gate_activation', 'origin_mode'], varargs=None, keywords=None, defaults=(None, None, 'tanh', 'sigmoid', False)), ('document', '0b10a755b469d0b85b3a5cac38b4cf01'))
paddle.fluid.layers.linear_chain_crf (ArgSpec(args=['input', 'label', 'param_attr', 'length'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'b28bdb43160e9667be2a3457d19d9f5b'))
paddle.fluid.layers.crf_decoding (ArgSpec(args=['input', 'param_attr', 'label', 'length'], varargs=None, keywords=None, defaults=(None, None)), ('document', '708ce0348b74d3e0c7885c2c524b7fa7'))
paddle.fluid.layers.cos_sim (ArgSpec(args=['X', 'Y'], varargs=None, keywords=None, defaults=None), ('document', '48ec1ba2d75c4e2faf8d9a47350462ae'))
paddle.fluid.layers.cross_entropy (ArgSpec(args=['input', 'label', 'soft_label', 'ignore_index'], varargs=None, keywords=None, defaults=(False, -100)), ('document', 'd1985a930a59c3bd41a7c1d72594f5b9'))
paddle.fluid.layers.bpr_loss (ArgSpec(args=['input', 'label', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'ae57e6e5136dade436f0df1f11770afa'))
paddle.fluid.layers.square_error_cost (ArgSpec(args=['input', 'label'], varargs=None, keywords=None, defaults=None), ('document', '4ed09e115b50ec7393674c4c09d223a2'))
paddle.fluid.layers.chunk_eval (ArgSpec(args=['input', 'label', 'chunk_scheme', 'num_chunk_types', 'excluded_chunk_types', 'seq_length'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'b02844e0ad4bd713c5fe6802aa13219c'))
paddle.fluid.layers.chunk_eval (ArgSpec(args=['input', 'label', 'chunk_scheme', 'num_chunk_types', 'excluded_chunk_types', 'seq_length'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'a8aa2071cae18df1e8dde9183d64bfb1'))
paddle.fluid.layers.sequence_conv (ArgSpec(args=['input', 'num_filters', 'filter_size', 'filter_stride', 'padding', 'padding_start', 'bias_attr', 'param_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(3, 1, True, None, None, None, None, None)), ('document', 'ebddcc5a1073ef065d22b4673e36b1d2'))
paddle.fluid.layers.conv2d (ArgSpec(args=['input', 'num_filters', 'filter_size', 'stride', 'padding', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name', 'data_format'], varargs=None, keywords=None, defaults=(1, 0, 1, None, None, None, True, None, None, 'NCHW')), ('document', 'e91c63b8ac8c35982c0ac518537e44bf'))
paddle.fluid.layers.conv3d (ArgSpec(args=['input', 'num_filters', 'filter_size', 'stride', 'padding', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name', 'data_format'], varargs=None, keywords=None, defaults=(1, 0, 1, None, None, None, True, None, None, 'NCDHW')), ('document', 'feff9c8ebb4d4d0be5345f9042f57c8e'))
......@@ -149,14 +149,14 @@ paddle.fluid.layers.adaptive_pool3d (ArgSpec(args=['input', 'pool_size', 'pool_t
paddle.fluid.layers.batch_norm (ArgSpec(args=['input', 'act', 'is_test', 'momentum', 'epsilon', 'param_attr', 'bias_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var', 'fuse_with_relu', 'use_global_stats'], varargs=None, keywords=None, defaults=(None, False, 0.9, 1e-05, None, None, 'NCHW', False, None, None, None, False, False, False)), ('document', '1400433bae7876d0407ae205be39b7a1'))
paddle.fluid.layers.instance_norm (ArgSpec(args=['input', 'epsilon', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(1e-05, None, None, None)), ('document', '23d6fba8ad8495f67a66d8878be5b0be'))
paddle.fluid.layers.data_norm (ArgSpec(args=['input', 'act', 'epsilon', 'param_attr', 'data_layout', 'in_place', 'name', 'moving_mean_name', 'moving_variance_name', 'do_model_average_for_mean_and_var'], varargs=None, keywords=None, defaults=(None, 1e-05, None, 'NCHW', False, None, None, None, False)), ('document', '5ba4cdb4ea5c03382da545335ffc05b7'))
paddle.fluid.layers.beam_search_decode (ArgSpec(args=['ids', 'scores', 'beam_size', 'end_id', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '83e08f21af41ac8bac37aeab1f86fdd0'))
paddle.fluid.layers.beam_search_decode (ArgSpec(args=['ids', 'scores', 'beam_size', 'end_id', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'eafa177a7fed6178a51c1affa7f46a40'))
paddle.fluid.layers.conv2d_transpose (ArgSpec(args=['input', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name', 'data_format'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None, 'NCHW')), ('document', 'ed24c2d0f82cd9a3b40488157285a584'))
paddle.fluid.layers.conv3d_transpose (ArgSpec(args=['input', 'num_filters', 'output_size', 'filter_size', 'padding', 'stride', 'dilation', 'groups', 'param_attr', 'bias_attr', 'use_cudnn', 'act', 'name', 'data_format'], varargs=None, keywords=None, defaults=(None, None, 0, 1, 1, None, None, None, True, None, None, 'NCDHW')), ('document', 'efb1e3bc87339cb26faa2edae210e8b0'))
paddle.fluid.layers.sequence_expand (ArgSpec(args=['x', 'y', 'ref_level', 'name'], varargs=None, keywords=None, defaults=(-1, None)), ('document', '10e122eb755c2bd1f78ef2332b28f1a0'))
paddle.fluid.layers.sequence_expand_as (ArgSpec(args=['x', 'y', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '858c432e7cbd8bb952cc2eb555457d50'))
paddle.fluid.layers.sequence_pad (ArgSpec(args=['x', 'pad_value', 'maxlen', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'df08b9c499ab3a90f95d08ab5b6c6c62'))
paddle.fluid.layers.sequence_unpad (ArgSpec(args=['x', 'length', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'e478180d5bc010a84f35af958cafa62c'))
paddle.fluid.layers.lstm_unit (ArgSpec(args=['x_t', 'hidden_t_prev', 'cell_t_prev', 'forget_bias', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(0.0, None, None, None)), ('document', 'fe126c58e4339410e875ab1eba246d21'))
paddle.fluid.layers.lstm_unit (ArgSpec(args=['x_t', 'hidden_t_prev', 'cell_t_prev', 'forget_bias', 'param_attr', 'bias_attr', 'name'], varargs=None, keywords=None, defaults=(0.0, None, None, None)), ('document', 'f5a878b6166f34878376a58d7e6fa95c'))
paddle.fluid.layers.reduce_sum (ArgSpec(args=['input', 'dim', 'keep_dim', 'name'], varargs=None, keywords=None, defaults=(None, False, None)), ('document', 'ecb55075fdf89a866bcede85e60aebad'))
paddle.fluid.layers.reduce_mean (ArgSpec(args=['input', 'dim', 'keep_dim', 'name'], varargs=None, keywords=None, defaults=(None, False, None)), ('document', '968c9b17affaf714e5021c3dc8d68c73'))
paddle.fluid.layers.reduce_max (ArgSpec(args=['input', 'dim', 'keep_dim', 'name'], varargs=None, keywords=None, defaults=(None, False, None)), ('document', 'd37e3a9a05c00e032d4b7876c4f6b414'))
......@@ -181,7 +181,7 @@ paddle.fluid.layers.im2sequence (ArgSpec(args=['input', 'filter_size', 'stride',
paddle.fluid.layers.nce (ArgSpec(args=['input', 'label', 'num_total_classes', 'sample_weight', 'param_attr', 'bias_attr', 'num_neg_samples', 'name', 'sampler', 'custom_dist', 'seed', 'is_sparse'], varargs=None, keywords=None, defaults=(None, None, None, None, None, 'uniform', None, 0, False)), ('document', '38297567127888e01542857839058d52'))
paddle.fluid.layers.sampled_softmax_with_cross_entropy (ArgSpec(args=['logits', 'label', 'num_samples', 'num_true', 'remove_accidental_hits', 'use_customized_samples', 'customized_samples', 'customized_probabilities', 'seed'], varargs=None, keywords=None, defaults=(1, True, False, None, None, 0)), ('document', 'd4435a63d34203339831ee6a86ef9242'))
paddle.fluid.layers.hsigmoid (ArgSpec(args=['input', 'label', 'num_classes', 'param_attr', 'bias_attr', 'name', 'path_table', 'path_code', 'is_custom', 'is_sparse'], varargs=None, keywords=None, defaults=(None, None, None, None, None, False, False)), ('document', 'b83e7dfa81059b39bb137922dc914f50'))
paddle.fluid.layers.beam_search (ArgSpec(args=['pre_ids', 'pre_scores', 'ids', 'scores', 'beam_size', 'end_id', 'level', 'is_accumulated', 'name', 'return_parent_idx'], varargs=None, keywords=None, defaults=(0, True, None, False)), ('document', '1270395ce97a4e1b556104abbb14f096'))
paddle.fluid.layers.beam_search (ArgSpec(args=['pre_ids', 'pre_scores', 'ids', 'scores', 'beam_size', 'end_id', 'level', 'is_accumulated', 'name', 'return_parent_idx'], varargs=None, keywords=None, defaults=(0, True, None, False)), ('document', '2b505ddaa309fd7b9be5445e41ca76d5'))
paddle.fluid.layers.row_conv (ArgSpec(args=['input', 'future_context_size', 'param_attr', 'act'], varargs=None, keywords=None, defaults=(None, None)), ('document', 'a6477957b44907787b3c74157400b80c'))
paddle.fluid.layers.multiplex (ArgSpec(args=['inputs', 'index'], varargs=None, keywords=None, defaults=None), ('document', '2c4d1ae83da6ed35e3b36ba1b3b51d23'))
paddle.fluid.layers.layer_norm (ArgSpec(args=['input', 'scale', 'shift', 'begin_norm_axis', 'epsilon', 'param_attr', 'bias_attr', 'act', 'name'], varargs=None, keywords=None, defaults=(True, True, 1, 1e-05, None, None, None, None)), ('document', '678de6d6d0c93da74189990b039daae8'))
......@@ -281,7 +281,7 @@ paddle.fluid.layers.similarity_focus (ArgSpec(args=['input', 'axis', 'indexes',
paddle.fluid.layers.hash (ArgSpec(args=['input', 'hash_size', 'num_hash', 'name'], varargs=None, keywords=None, defaults=(1, None)), ('document', 'a0b73c21be618cec0281e7903039e5e3'))
paddle.fluid.layers.grid_sampler (ArgSpec(args=['x', 'grid', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '90c74742f48c70b103f1fbb9eb129066'))
paddle.fluid.layers.log_loss (ArgSpec(args=['input', 'label', 'epsilon', 'name'], varargs=None, keywords=None, defaults=(0.0001, None)), ('document', 'ef1701e11d60508fe8f02dd2a8c60bdf'))
paddle.fluid.layers.add_position_encoding (ArgSpec(args=['input', 'alpha', 'beta', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'e399f9436fed5f7ff480d8532e42c937'))
paddle.fluid.layers.add_position_encoding (ArgSpec(args=['input', 'alpha', 'beta', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'bd8b28e6c1640b13a42b0524f86f7800'))
paddle.fluid.layers.bilinear_tensor_product (ArgSpec(args=['x', 'y', 'size', 'act', 'name', 'param_attr', 'bias_attr'], varargs=None, keywords=None, defaults=(None, None, None, None)), ('document', '6755168c4b2308e1e4f54cb56fa7dcb2'))
paddle.fluid.layers.merge_selected_rows (ArgSpec(args=['x', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'b2b0e5d5c155ce24bafc38b78cd0b164'))
paddle.fluid.layers.get_tensor_from_selected_rows (ArgSpec(args=['x', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '2c568321feb4d16c41a83df43f95089d'))
......@@ -922,7 +922,7 @@ paddle.fluid.transpiler.DistributeTranspilerConfig.__init__ (ArgSpec(args=['self
paddle.fluid.nets.simple_img_conv_pool (ArgSpec(args=['input', 'num_filters', 'filter_size', 'pool_size', 'pool_stride', 'pool_padding', 'pool_type', 'global_pooling', 'conv_stride', 'conv_padding', 'conv_dilation', 'conv_groups', 'param_attr', 'bias_attr', 'act', 'use_cudnn'], varargs=None, keywords=None, defaults=(0, 'max', False, 1, 0, 1, 1, None, None, None, True)), ('document', '5e89c978199c4ecce2b26d5fed1ec52b'))
paddle.fluid.nets.sequence_conv_pool (ArgSpec(args=['input', 'num_filters', 'filter_size', 'param_attr', 'act', 'pool_type', 'bias_attr'], varargs=None, keywords=None, defaults=(None, 'sigmoid', 'max', None)), ('document', 'b2d435f782ac8ea3ca480b8d24e7f5b4'))
paddle.fluid.nets.glu (ArgSpec(args=['input', 'dim'], varargs=None, keywords=None, defaults=(-1,)), ('document', '3efe197c8e3e75f84a4c464d8b74e943'))
paddle.fluid.nets.scaled_dot_product_attention (ArgSpec(args=['queries', 'keys', 'values', 'num_heads', 'dropout_rate'], varargs=None, keywords=None, defaults=(1, 0.0)), ('document', 'b1a07a0000eb9103e3a143ca8c13de5b'))
paddle.fluid.nets.scaled_dot_product_attention (ArgSpec(args=['queries', 'keys', 'values', 'num_heads', 'dropout_rate'], varargs=None, keywords=None, defaults=(1, 0.0)), ('document', '375898e47266633635f4c2096e1ac296'))
paddle.fluid.nets.img_conv_group (ArgSpec(args=['input', 'conv_num_filter', 'pool_size', 'conv_padding', 'conv_filter_size', 'conv_act', 'param_attr', 'conv_with_batchnorm', 'conv_batchnorm_drop_rate', 'pool_stride', 'pool_type', 'use_cudnn'], varargs=None, keywords=None, defaults=(1, 3, None, None, False, 0.0, 1, 'max', True)), ('document', 'a59c581d5969266427e841abe69f694a'))
paddle.fluid.optimizer.SGDOptimizer ('paddle.fluid.optimizer.SGDOptimizer', ('document', 'c3c8dd3193d991adf8bda505560371d6'))
paddle.fluid.optimizer.SGDOptimizer.__init__ (ArgSpec(args=['self', 'learning_rate', 'regularization', 'name'], varargs=None, keywords=None, defaults=(None, None)), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
......
此差异已折叠。
......@@ -363,67 +363,67 @@ def scaled_dot_product_attention(queries,
num_heads=1,
dropout_rate=0.):
"""
The dot-product attention.
This interface Multi-Head Attention using scaled dot product.
Attention mechanism can be seen as mapping a query and a set of key-value
pairs to an output. The output is computed as a weighted sum of the values,
where the weight assigned to each value is computed by a compatibility
function (dot-product here) of the query with the corresponding key.
The dot-product attention can be implemented through (batch) matrix
multipication as follows:
pairs to an output. Multi-Head Attention performs attention using multi-head
parallel, and the inputs of attention would be transformed by linear projection.
The formula is as follows:
.. math::
Attention(Q, K, V)= softmax(QK^\mathrm{T})V
MultiHead(Q, K, V ) & = Concat(head_1, ..., head_h)
where \ head_i & = Attention(QW_i^Q , KW_i^K , VW_i^V )
Refer to `Attention Is All You Need
<https://arxiv.org/pdf/1706.03762.pdf>`_.
Attention(Q, K, V) & = softmax (\\frac{QK^\mathrm{T}}{\sqrt{d_k}}) V
For more details, please refer to `Attention Is All You Need
<https://arxiv.org/pdf/1706.03762.pdf>`_ .
Note that the implementation is adapted to batch, and all matrix multiplication
in :math:`Attention(Q, K, V)` is batched matrix multiplication. Refer to
:ref:`api_fluid_layers_matmul` .
Args:
queries (Variable): The input variable which should be a 3-D Tensor.
keys (Variable): The input variable which should be a 3-D Tensor.
values (Variable): The input variable which should be a 3-D Tensor.
num_heads (int): Head number to compute the scaled dot product
attention. Default: 1.
dropout_rate (float): The dropout rate to drop the attention weight.
Default: 0.0.
queries (Variable): A 3-D Tensor with shape :math:`[N, L_q, d_k \\times h]` ,
where :math:`N` stands for batch size, :math:`L_q` for the sequence length
of query, :math:`d_k \\times h` for the feature size of query, :math:`h` for
head number. The data type should be float32 or float64.
keys (Variable): A 3-D Tensor with shape :math:`[N, L_k, d_k \\times h]` ,
where :math:`N` stands for batch size, :math:`L_k` for the sequence length
of key, :math:`d_k \\times h` for the feature size of key, :math:`h` for head
number. The data type should be the same as ``queries`` .
values (Variable): A 3-D Tensor with shape :math:`[N, L_k, d_v \\times h]` ,
where :math:`N` stands for batch size, :math:`L_k` for the sequence length
of key, :math:`d_v \\times h` for the feature size of value, :math:`h` for head
number. The data type should be the same as ``queries`` .
num_heads (int, optional): Indicate the number of head. If the numher
is 1, linear projection would not be performed on inputs. Default: 1.
dropout_rate (float, optional): The rate to drop the attention weight.
Default: 0.0, which means no dropout.
Returns:
Variable: A 3-D Tensor computed by multi-head scaled dot product\
attention.
Variable: A 3-D Tensor with shape :math:`[N, L_q, d_v \\times h]` , \
where :math:`N` stands for batch size, :math:`L_q` for the sequence \
length of query, :math:`d_v \\times h` for the feature size of value. \
It has the same data type with inputs, representing the output of \
Multi-Head Attention.
Raises:
ValueError: If input queries, keys, values are not 3-D Tensors.
NOTES:
1. When num_heads > 1, three linear projections are learned respectively
to map input queries, keys and values into queries', keys' and values'.
queries', keys' and values' have the same shapes with queries, keys
and values.
2. When num_heads == 1, scaled_dot_product_attention has no learnable
parameters.
ValueError: Inputs quries, keys and values should all be 3-D tensors.
ValueError: The hidden size of queries and keys should be the same.
ValueError: The max sequence length in query batch and in key batch should be the same.
ValueError: he hidden size of keys must be divisible by the number of attention heads.
ValueError: he hidden size of values must be divisible by the number of attention heads.
Examples:
.. code-block:: python
import paddle.fluid as fluid
queries = fluid.layers.data(name="queries",
shape=[3, 5, 9],
dtype="float32",
append_batch_size=False)
queries.stop_gradient = False
keys = fluid.layers.data(name="keys",
shape=[3, 6, 9],
dtype="float32",
append_batch_size=False)
keys.stop_gradient = False
values = fluid.layers.data(name="values",
shape=[3, 6, 10],
dtype="float32",
append_batch_size=False)
values.stop_gradient = False
queries = fluid.data(name="queries", shape=[3, 5, 9], dtype="float32")
keys = fluid.data(name="keys", shape=[3, 6, 9], dtype="float32")
values = fluid.data(name="values", shape=[3, 6, 10], dtype="float32")
contexts = fluid.nets.scaled_dot_product_attention(queries, keys, values)
contexts.shape # [3, 5, 10]
"""
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册