MCPcopy
hub / github.com/FACEGOOD/FACEGOOD-Audio2Face / conv2d_layer

Function conv2d_layer

code/train/model_paper.py:21–33  ·  view source on GitHub ↗

Conv2D Layer Args: filters: int, the output channels of the conv2d layer kernel_size: list, the kernel size of the conv2d layer strides: list, the strides of the conv2d layer

(filters=256, kernel_size=None, strides=None)

Source from the content-addressed store, hash-verified

19
20
21def conv2d_layer(filters=256, kernel_size=None, strides=None):
22 """Conv2D Layer
23 Args:
24 filters: int, the output channels of the conv2d layer
25 kernel_size: list, the kernel size of the conv2d layer
26 strides: list, the strides of the conv2d layer
27 """
28 if kernel_size is None:
29 kernel_size = [1, 1]
30 if strides is None:
31 strides = [1, 1]
32 conv2d = Conv2D(filters=filters, kernel_size=kernel_size, padding="same", activation='relu', strides=strides)
33 return conv2d
34
35class FormantLayer(Model):
36 """Formant Layer

Callers 2

__init__Method · 0.85
__init__Method · 0.85

Calls

no outgoing calls

Tested by

no test coverage detected