export_waveglow_onnx Namespace Reference

Functions
def	parse_args (parser)
def	convert_convinv_1d_to_2d (convinv)
def	convert_conv_1d_to_2d (conv1d)
def	convert_WN_1d_to_2d_ (WN)
def	convert_1d_to_2d_ (glow)
def	infer_onnx (self, spect, z, sigma=0.9)
def	export_onnx (parser, args)
def	main ()

Variables
	n_early_every

Function Documentation

parse_args()

def export_waveglow_onnx.parse_args

(

parser

)

Parse commandline arguments.

Here is the caller graph for this function:

convert_convinv_1d_to_2d()

def export_waveglow_onnx.convert_convinv_1d_to_2d

(

convinv

)

Takes an invertible 1x1 1-d convolution and returns a 2-d convolution that does
the inverse

Here is the caller graph for this function:

convert_conv_1d_to_2d()

def export_waveglow_onnx.convert_conv_1d_to_2d

(

conv1d

)

Here is the caller graph for this function:

convert_WN_1d_to_2d_()

def export_waveglow_onnx.convert_WN_1d_to_2d_

(

WN

)

Modifies the WaveNet like affine coupling layer in-place to use 2-d convolutions

Here is the call graph for this function:

Here is the caller graph for this function:

convert_1d_to_2d_()

def export_waveglow_onnx.convert_1d_to_2d_

(

glow

)

Caffe2 and TensorRT don't seem to support 1-d convolutions or properly
convert ONNX exports with 1d convolutions to 2d convolutions yet, so we
do the conversion to 2-d convolutions before ONNX export

Here is the call graph for this function:

Here is the caller graph for this function:

infer_onnx()

def export_waveglow_onnx.infer_onnx	(		self,
			spect,
			z,
			sigma = 0.9
	)

export_onnx()

def export_waveglow_onnx.export_onnx	(		parser,
			args
	)

Here is the call graph for this function:

Here is the caller graph for this function:

main()

def export_waveglow_onnx.main

(

)

Here is the call graph for this function:

Variable Documentation

n_early_every

export_waveglow_onnx.n_early_every