tinynn/graph/quantization/quantizer.py [847:896]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        graph.module.qconfig = qconfig
        if self.backend == 'qnnpack':
            if qconfig_c is not None:
                q = queue.Queue()
                q.put(graph.module)

                while not q.empty():
                    m = q.get()
                    if type(m).__name__ in (
                        'Conv2d',
                        'ConvBnReLU2d',
                        'ConvBn2d',
                        'ConvReLU2d',
                        'Conv1d',
                        'ConvBnReLU1d',
                        'ConvBn1d',
                    ):
                        m.qconfig = qconfig_c
                    else:
                        for c in m.children():
                            q.put(c)
        elif self.backend == 'fbgemm':
            if qconfig_c is not None:
                q = queue.Queue()
                q.put(graph.module)

                while not q.empty():
                    m = q.get()
                    if type(m).__name__ in ('Linear', 'LinearReLU'):
                        m.qconfig = qconfig_c
                    else:
                        for c in m.children():
                            q.put(c)

        def _lstm_node(node, custom_data):
            return isinstance(node.module, nn.LSTM)

        if self.dynamic_lstm_quant:
            lstm_nodes = graph.filter_forward_nodes(_lstm_node)
            for node in lstm_nodes:
                node.quantized = True
                node.module.qconfig = torch_q.default_dynamic_qconfig

    def prepare_qat(
        self,
        graph: TraceGraph,
        is_input_quantized: typing.Optional[typing.Tuple[bool]] = None,
        backend: str = 'qnnpack',
        fuse_only: bool = False,
    ) -> torch.nn.Module:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



tinynn/graph/quantization/quantizer.py [3730:3779]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        graph.module.qconfig = qconfig
        if self.backend == 'qnnpack':
            if qconfig_c is not None:
                q = queue.Queue()
                q.put(graph.module)

                while not q.empty():
                    m = q.get()
                    if type(m).__name__ in (
                        'Conv2d',
                        'ConvBnReLU2d',
                        'ConvBn2d',
                        'ConvReLU2d',
                        'Conv1d',
                        'ConvBnReLU1d',
                        'ConvBn1d',
                    ):
                        m.qconfig = qconfig_c
                    else:
                        for c in m.children():
                            q.put(c)
        elif self.backend == 'fbgemm':
            if qconfig_c is not None:
                q = queue.Queue()
                q.put(graph.module)

                while not q.empty():
                    m = q.get()
                    if type(m).__name__ in ('Linear', 'LinearReLU'):
                        m.qconfig = qconfig_c
                    else:
                        for c in m.children():
                            q.put(c)

        def _lstm_node(node, custom_data):
            return isinstance(node.module, nn.LSTM)

        if self.dynamic_lstm_quant:
            lstm_nodes = graph.filter_forward_nodes(_lstm_node)
            for node in lstm_nodes:
                node.quantized = True
                node.module.qconfig = torch_q.default_dynamic_qconfig

    def prepare_qat(
        self,
        graph: TraceGraph,
        is_input_quantized: typing.Optional[typing.Tuple[bool]] = None,
        backend: str = 'qnnpack',
        fuse_only: bool = False,
    ) -> torch.nn.Module:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -