repro.mlir:72:11: error: 'linalg.conv_2d_nchw_fchw' op inferred input/output operand #1 has shape's dimension #1 to be 4, but found 3
    %24 = linalg.conv_2d_nchw_fchw {dilations = dense<1> : vector<2xi64>, strides = dense<2> : vector<2xi64>} ins(%padded, %arg1 : tensor<?x?x?x?xf32>, tensor<32x3x3x3xf32>) outs(%broadcasted : tensor<?x32x?x?xf32>) -> tensor<?x32x?x?xf32>
          ^
repro.mlir:7:3: note: called from
  func.func @torch_jit(%arg0: tensor<1x3x224x224xf32>, %arg1: tensor<32x3x3x3xf32>) -> tensor<?x32x?x?xf32> {
  ^
repro.mlir:72:11: note: see current operation: 
%12 = "linalg.conv_2d_nchw_fchw"(%8, %5, %11) <{dilations = dense<1> : vector<2xi64>, operandSegmentSizes = array<i32: 2, 1>, strides = dense<2> : vector<2xi64>}> ({
^bb0(%arg5: f32, %arg6: f32, %arg7: f32):
  %17 = "arith.mulf"(%arg5, %arg6) <{fastmath = #arith.fastmath<none>}> : (f32, f32) -> f32
  %18 = "arith.addf"(%arg7, %17) <{fastmath = #arith.fastmath<none>}> : (f32, f32) -> f32
  "linalg.yield"(%18) : (f32) -> ()
}) {linalg.memoized_indexing_maps = [affine_map<(d0, d1, d2, d3, d4, d5, d6) -> (d0, d4, d2 * 2 + d5, d3 * 2 + d6)>, affine_map<(d0, d1, d2, d3, d4, d5, d6) -> (d1, d4, d5, d6)>, affine_map<(d0, d1, d2, d3, d4, d5, d6) -> (d0, d1, d2, d3)>]} : (tensor<2x4x224x224xf32>, tensor<32x3x3x3xf32>, tensor<2x32x111x111xf32>) -> tensor<2x32x111x111xf32>
    %24 = linalg.conv_2d_nchw_fchw {dilations = dense<1> : vector<2xi64>, strides = dense<2> : vector<2xi64>} ins(%padded, %arg1 : tensor<?x?x?x?xf32>, tensor<32x3x3x3xf32>) outs(%broadcasted : tensor<?x32x?x?xf32>) -> tensor<?x32x?x?xf32>
          ^