se Namespace Reference

Functions
def	squeeze_excite_block (input, ratio=16)

Function Documentation

def se.squeeze_excite_block	(		input,
			ratio = 16
	)

Create a squeeze-excite block
Args:
    input: input tensor
    filters: number of output filters
    k: width factor

Returns: a keras tensor

Definition at line 5 of file se.py.

def squeeze_excite_block(input, ratio=16):
    ''' Create a squeeze-excite block
    Args:
        input: input tensor
        filters: number of output filters
        k: width factor

    Returns: a keras tensor
    '''
    init = input
    channel_axis = 1 if K.image_data_format() == "channels_first" else -1
    filters = init._keras_shape[channel_axis]
    se_shape = (1, 1, filters)

    se = GlobalAveragePooling2D()(init)
    se = Reshape(se_shape)(se)
    se = Dense(filters // ratio, activation='relu', kernel_initializer='he_normal', use_bias=False)(se)
    se = Dense(filters, activation='sigmoid', kernel_initializer='he_normal', use_bias=False)(se)

    if K.image_data_format() == 'channels_first':
        se = Permute((3, 1, 2))(se)

    x = multiply([init, se])
    return x

---

Generated by   1.8.11