Is there a problem with using hook and fx together?
when I use the torch.fx to get quantizated-module, but as the same as with hook to get output’s param, it return the Proxy type, why.
Thanks
Is there a problem with using hook and fx together?
when I use the torch.fx to get quantizated-module, but as the same as with hook to get output’s param, it return the Proxy type, why.
Thanks
Is there any way to change Proxy to Tensor?
def __init__(self, node: Node, tracer: 'Optional[TracerBase]' = None):
if tracer is None:
# This allows you to create a Proxy object around a raw Node
tracer = GraphAppendingTracer(node.graph)
self.tracer = tracer
self.node = node