quant_conv.xml

<?xml version="1.0"?>
<net name="torch_jit" version="11">
	<layers>
		<layer id="0" name="h" type="Parameter" version="opset1">
			<data shape="1,32,128,32" element_type="f32" />
			<output>
				<port id="0" precision="FP32" names="h">
					<dim>1</dim>
					<dim>32</dim>
					<dim>128</dim>
					<dim>32</dim>
				</port>
			</output>
		</layer>
		<layer id="1" name="weight_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="32, 32, 1, 1" offset="0" size="2048" />
			<output>
				<port id="0" precision="FP16">
					<dim>32</dim>
					<dim>32</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="2" name="weight" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>32</dim>
					<dim>32</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32" names="weight">
					<dim>32</dim>
					<dim>32</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="3" name="/Conv/WithoutBiases" type="Convolution" version="opset1">
			<data strides="1, 1" dilations="1, 1" pads_begin="0, 0" pads_end="0, 0" auto_pad="explicit" />
			<input>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>32</dim>
					<dim>128</dim>
					<dim>32</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>32</dim>
					<dim>32</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32">
					<dim>1</dim>
					<dim>32</dim>
					<dim>128</dim>
					<dim>32</dim>
				</port>
			</output>
		</layer>
		<layer id="4" name="Reshape_16_compressed" type="Const" version="opset1">
			<data element_type="f16" shape="1, 32, 1, 1" offset="2048" size="64" />
			<output>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>32</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="5" name="Reshape_16" type="Convert" version="opset1">
			<data destination_type="f32" />
			<rt_info>
				<attribute name="decompression" version="0" />
			</rt_info>
			<input>
				<port id="0" precision="FP16">
					<dim>1</dim>
					<dim>32</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>32</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</output>
		</layer>
		<layer id="6" name="moments" type="Add" version="opset1">
			<data auto_broadcast="numpy" />
			<input>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>32</dim>
					<dim>128</dim>
					<dim>32</dim>
				</port>
				<port id="1" precision="FP32">
					<dim>1</dim>
					<dim>32</dim>
					<dim>1</dim>
					<dim>1</dim>
				</port>
			</input>
			<output>
				<port id="2" precision="FP32" names="moments">
					<dim>1</dim>
					<dim>32</dim>
					<dim>128</dim>
					<dim>32</dim>
				</port>
			</output>
		</layer>
		<layer id="7" name="moments/sink_port_0" type="Result" version="opset1">
			<input>
				<port id="0" precision="FP32">
					<dim>1</dim>
					<dim>32</dim>
					<dim>128</dim>
					<dim>32</dim>
				</port>
			</input>
		</layer>
	</layers>
	<edges>
		<edge from-layer="0" from-port="0" to-layer="3" to-port="0" />
		<edge from-layer="1" from-port="0" to-layer="2" to-port="0" />
		<edge from-layer="2" from-port="1" to-layer="3" to-port="1" />
		<edge from-layer="3" from-port="2" to-layer="6" to-port="0" />
		<edge from-layer="4" from-port="0" to-layer="5" to-port="0" />
		<edge from-layer="5" from-port="1" to-layer="6" to-port="1" />
		<edge from-layer="6" from-port="2" to-layer="7" to-port="0" />
	</edges>
	<rt_info>
		<MO_version value="2024.4.0-16579-c3152d32c9c-releases/2024/4" />
		<Runtime_version value="2024.4.0-16579-c3152d32c9c-releases/2024/4" />
		<conversion_parameters>
			<input_model value="DIR\quant_conv.onnx" />
			<is_python_api_used value="False" />
		</conversion_parameters>
		<legacy_frontend value="False" />
	</rt_info>
</net>