Coverage for /pythoncovmergedfiles/medio/medio/usr/local/lib/python3.8/site-packages/keras/src/layers/pooling/base_pooling2d.py: 26%

43 statements  

« prev     ^ index     » next       coverage.py v7.4.0, created at 2024-01-03 07:57 +0000

1# Copyright 2015 The TensorFlow Authors. All Rights Reserved. 

2# 

3# Licensed under the Apache License, Version 2.0 (the "License"); 

4# you may not use this file except in compliance with the License. 

5# You may obtain a copy of the License at 

6# 

7# http://www.apache.org/licenses/LICENSE-2.0 

8# 

9# Unless required by applicable law or agreed to in writing, software 

10# distributed under the License is distributed on an "AS IS" BASIS, 

11# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 

12# See the License for the specific language governing permissions and 

13# limitations under the License. 

14# ============================================================================== 

15"""Private base class for pooling 2D layers.""" 

16 

17 

18import tensorflow.compat.v2 as tf 

19 

20from keras.src import backend 

21from keras.src.engine.base_layer import Layer 

22from keras.src.engine.input_spec import InputSpec 

23from keras.src.utils import conv_utils 

24 

25 

26class Pooling2D(Layer): 

27 """Pooling layer for arbitrary pooling functions, for 2D data (e.g. images). 

28 

29 This class only exists for code reuse. It will never be an exposed API. 

30 

31 Args: 

32 pool_function: The pooling function to apply, e.g. `tf.nn.max_pool2d`. 

33 pool_size: An integer or tuple/list of 2 integers: 

34 (pool_height, pool_width) 

35 specifying the size of the pooling window. 

36 Can be a single integer to specify the same value for 

37 all spatial dimensions. 

38 strides: An integer or tuple/list of 2 integers, 

39 specifying the strides of the pooling operation. 

40 Can be a single integer to specify the same value for 

41 all spatial dimensions. 

42 padding: A string. The padding method, either 'valid' or 'same'. 

43 Case-insensitive. 

44 data_format: A string, one of `channels_last` (default) or 

45 `channels_first`. 

46 The ordering of the dimensions in the inputs. 

47 `channels_last` corresponds to inputs with shape 

48 `(batch, height, width, channels)` while `channels_first` corresponds to 

49 inputs with shape `(batch, channels, height, width)`. 

50 name: A string, the name of the layer. 

51 """ 

52 

53 def __init__( 

54 self, 

55 pool_function, 

56 pool_size, 

57 strides, 

58 padding="valid", 

59 data_format=None, 

60 name=None, 

61 **kwargs 

62 ): 

63 super().__init__(name=name, **kwargs) 

64 if data_format is None: 

65 data_format = backend.image_data_format() 

66 if strides is None: 

67 strides = pool_size 

68 self.pool_function = pool_function 

69 self.pool_size = conv_utils.normalize_tuple(pool_size, 2, "pool_size") 

70 self.strides = conv_utils.normalize_tuple( 

71 strides, 2, "strides", allow_zero=True 

72 ) 

73 self.padding = conv_utils.normalize_padding(padding) 

74 self.data_format = conv_utils.normalize_data_format(data_format) 

75 self.input_spec = InputSpec(ndim=4) 

76 

77 def call(self, inputs): 

78 if self.data_format == "channels_last": 

79 pool_shape = (1,) + self.pool_size + (1,) 

80 strides = (1,) + self.strides + (1,) 

81 else: 

82 pool_shape = (1, 1) + self.pool_size 

83 strides = (1, 1) + self.strides 

84 outputs = self.pool_function( 

85 inputs, 

86 ksize=pool_shape, 

87 strides=strides, 

88 padding=self.padding.upper(), 

89 data_format=conv_utils.convert_data_format(self.data_format, 4), 

90 ) 

91 return outputs 

92 

93 def compute_output_shape(self, input_shape): 

94 input_shape = tf.TensorShape(input_shape).as_list() 

95 if self.data_format == "channels_first": 

96 rows = input_shape[2] 

97 cols = input_shape[3] 

98 else: 

99 rows = input_shape[1] 

100 cols = input_shape[2] 

101 rows = conv_utils.conv_output_length( 

102 rows, self.pool_size[0], self.padding, self.strides[0] 

103 ) 

104 cols = conv_utils.conv_output_length( 

105 cols, self.pool_size[1], self.padding, self.strides[1] 

106 ) 

107 if self.data_format == "channels_first": 

108 return tf.TensorShape([input_shape[0], input_shape[1], rows, cols]) 

109 else: 

110 return tf.TensorShape([input_shape[0], rows, cols, input_shape[3]]) 

111 

112 def get_config(self): 

113 config = { 

114 "pool_size": self.pool_size, 

115 "padding": self.padding, 

116 "strides": self.strides, 

117 "data_format": self.data_format, 

118 } 

119 base_config = super().get_config() 

120 return dict(list(base_config.items()) + list(config.items())) 

121