p.Optab = uint16(cap(optab) - cap(ops) + i + 1)
			return op
		}
	}

	c.ctxt.Diag("illegal combination %v %v %v %v %v %v %v", p.As, DRconv(a1), DRconv(a2), DRconv(a3), DRconv(a4), DRconv(a5), DRconv(a6))
	prasm(p)
	if ops == nil {
		ops = optab
	}
	return &ops[0]
}

// Compare two operand types (ex C_REG, or C_U15CON)

			p.Optab = uint16(cap(optab) - cap(ops) + i + 1)
			return op
		}
	}

	c.ctxt.Diag("illegal combination: %v %v %v %v %v %v, %d %d", p, DRconv(a1), DRconv(a2), DRconv(a3), DRconv(a4), DRconv(a5), p.From.Type, p.To.Type)
	// Turn illegal instruction into an UNDEF, avoid crashing in asmout
	return &Optab{obj.AUNDEF, C_NONE, C_NONE, C_NONE, C_NONE, C_NONE, 90, 4, 0, 0, 0}
}

			cmp[4][op.a5] && cmp[5][op.a6] {
			p.Optab = uint16(cap(optab) - cap(ops) + i + 1)
			return op
		}
	}

	// Cannot find a case; abort.
	s := ""
	for _, a := range args {
		s += fmt.Sprintf(" %v", DRconv(int(a)))
	}
	c.ctxt.Diag("illegal combination %v%v\n", p.As, s)
	c.ctxt.Diag("prog: %v\n", p)
	return nil
}

func cmp(a int, b int) bool {
	if a == b {
		return true
	}
	switch a {

        input_shape=(1, 3, 4, 3), filter_shape=(2, 3, 3, 2)
    )

    signatures = {
        'serving_default': model.conv.get_concrete_function(),
    }
    save_opts = save_options.SaveOptions(
        function_aliases={'conv_func': model.conv}
    )

    saved_model_save.save(
        model, self._input_saved_model_path, signatures, save_opts
    )

			return Yi32
		}

		if a.Sym != nil || a.Name != obj.NAME_NONE {
			ctxt.Diag("unexpected addr: %v", obj.Dconv(p, a))
		}
		fallthrough

	case obj.TYPE_CONST:
		if a.Sym != nil {
			ctxt.Diag("TYPE_CONST with symbol: %v", obj.Dconv(p, a))
		}

		v := a.Offset
		if ctxt.Arch.Family == sys.I386 {
			v = int64(int32(v))
		}
		switch {
		case v == 0:

        "node": ">=8"
      },
      "funding": {
        "url": "https://github.com/sponsors/sindresorhus"
      }
    },
    "node_modules/iconv-lite": {
      "version": "0.6.3",
      "resolved": "https://registry.npmjs.org/iconv-lite/-/iconv-lite-0.6.3.tgz",
      "integrity": "sha512-4fCk79wshMdzMp2rH06qWrJE4iolqLhCUH+OiuIgU++RB0+94NlDL81atO7GX55uUKueo0txHNtvEyI6D7WdMw==",
      "dependencies": {

  if (elements_depth == 1) {
    return true;
  }

  // In TFLite Conv2D uses OHWI format for filter, and 1HWO for Depthwise Conv.
  // For conv:
  // Check if last dimension in filter equals the first dimension
  // For depthwise conv:
  // Check if the first in filter dimension equals the first dimension.
  if (filter_shape.empty() ||
      (is_depthwise ? filter_shape.back() != elements_depth

            (i != out_batch_dim && out_type.isDynamicDim(i))) {
          return false;
        }
      }
    }

    // All ones in "lhs_dilation" means this "mhlo.conv" op should be
    // converted to "tf.Conv2D" or "tf.DepthwiseConv2dNativeOp".
    auto lhs_dilation = conv_op.getLhsDilation().value();
    if (!lhs_dilation.isSplat() || lhs_dilation.getSplatValue<int64_t>() != 1)

    // CHECK: %[[SHAPE:.*]] = "tf.Shape"
    // CHECK: %[[CONV:.*]] = "tf.Conv2DBackpropInput"(%[[SHAPE]]
    // CHECK-SAME: (tensor<4xi32>, tensor<1x1x1x1xf32>, tensor<1x1x1x1xf32>) -> tensor<1x1x1x1xf32>
    // CHECK: return %[[CONV]] : tensor<1x1x1x1xf32>
    %0 = "tf.Shape"(%arg0) : (tensor<1x1x1x1xi32>) -> tensor<4xi32>
    %1 = "tf.Conv2DBackpropInput"(%0, %arg1, %arg1) {

      }
      func @_func(%input: tensor<2x112x112x12xf32>, %filter: tensor<7x7x3x64xf32>) {
        %filter_transform = "tf.Pad/tf.Transpose/tf.Reshape"(%filter): tensor<7x7x3x64xf32>) -> tensor<4x4x12x64xf32>
        %conv = "tf.Conv2D"(%input, %filter_transfrom) {strides = [1, 1, 1, 1]}: (tensor<2x112x112x12xf32>, tensor<4x4x12x64xf32>) -> tensor<2x112x112x64xf32>
      }
    }
    ```