return true
	}
	// match: (Cvt64Fto32F sqrt0:(Sqrt (Cvt32Fto64F x)))
	// cond: sqrt0.Uses==1
	// result: (Sqrt32 x)
	for {
		sqrt0 := v_0
		if sqrt0.Op != OpSqrt {
			break
		}
		sqrt0_0 := sqrt0.Args[0]
		if sqrt0_0.Op != OpCvt32Fto64F {
			break
		}
		x := sqrt0_0.Args[0]
		if !(sqrt0.Uses == 1) {
			break
		}
		v.reset(OpSqrt32)
		v.AddArg(x)
		return true
	}

		return true
	case OpSignExt8to64:
		v.Op = OpARM64MOVBreg
		return true
	case OpSlicemask:
		return rewriteValueARM64_OpSlicemask(v)
	case OpSqrt:
		v.Op = OpARM64FSQRTD
		return true
	case OpSqrt32:
		v.Op = OpARM64FSQRTS
		return true
	case OpStaticCall:
		v.Op = OpARM64CALLstatic
		return true
	case OpStore:
		return rewriteValueARM64_OpStore(v)
	case OpSub16:
		v.Op = OpARM64SUB

        1e-10))` Alternatively, you can override `convolution_op`: `python class
        StandardizedConv2D(tf.keras.Layer): def convolution_op(self, inputs,
        kernel): mean, var = tf.nn.moments(kernel, axes=[0, 1, 2],
        keepdims=True) # Author code uses std + 1e-5 return
        super().convolution_op(inputs, (kernel - mean) / tf.sqrt(var + 1e-10))`