the result of the tensor is not equal when the padh not equal padw

the result of a tensorrt tensor is wrong when the conv pad is different on two is the layer

layer {
  name: "dd"
  type: "Convolution"
  bottom: "d2"
  top: "d3"
  param {
    lr_mult: 1
    decay_mult: 1
  param {
    lr_mult: 2
    decay_mult: 0
  convolution_param {
    num_output: 512
    stride: 1
    weight_filler {
      type: "msra"
    pad_h: 1
    pad_w: 0
    kernel_h: 1
    kernel_w: 1

this previous layer of this layer is concat.the result of tensor is right in x86 devices,but is wrong in px2.Does nvidia support the conv like this?


Do you use the same TensorRT version between host and device?

In general, the result of TensorRT should be identical. (correct or incorrect)
Could you share the version number of each environment with us?