CosineSimilarity¶

class paddle.nn. CosineSimilarity ( axis=1, eps=1e-08 ) [source]

This interface is used to compute cosine similarity between x1 and x2 along axis.

Parameters

axis (int) – Dimension of vectors to compute cosine similarity. Default is 1.
eps (float) – Small value to avoid division by zero. Default is 1e-8.

Returns

None

Examples

           Case 0:
    x1 = [[0.8024077  0.9927354  0.27238318 0.8344984 ]
         [0.48949873 0.5797396  0.65444374 0.66510963]
         [0.1031398  0.9614342  0.08365563 0.6796464 ]
         [0.10760343 0.7461209  0.7726148  0.5801006 ]]
    x2 = [[0.62913156 0.1536727  0.9847992  0.04591406]
         [0.9098952  0.15715368 0.8671125  0.3156102 ]
         [0.4427798  0.54136837 0.5276275  0.32394758]
         [0.3769419  0.8535014  0.48041078 0.9256797 ]]
    axis = 1
    eps = 1e-8
    Out: [0.5275037  0.8368967  0.75037485 0.9245899]

          

Code Examples:

             import paddle
import paddle.nn as nn

x1 = paddle.to_tensor([[1., 2., 3.],
                    [2., 3., 4.]], dtype="float32")
x2 = paddle.to_tensor([[8., 3., 3.],
                    [2., 3., 4.]], dtype="float32")

cos_sim_func = nn.CosineSimilarity(axis=0)
result = cos_sim_func(x1, x2)
print(result)
# Tensor(shape=[3], dtype=float32, place=Place(gpu:0), stop_gradient=True,
#        [0.65079135, 0.98058069, 1.        ])

            

forward ( x1, x2 ) forward¶

Defines the computation performed at every call. Should be overridden by all subclasses.

Parameters

*inputs (tuple) – unpacked tuple arguments
**kwargs (dict) – unpacked dict arguments

extra_repr ( ) extra_repr¶: Extra representation of this layer, you can have custom implementation of your own layer.

CosineSimilarity¶

forward¶

extra_repr¶