Hi! I’m trying to import a PyTorch model to TensorRT, but I’m not able to do so because there’s no operation to have different
(left, right, top, bottom) padding operator in TensorRT. Can anyone please point me to a relevant resource?
Following is the relevant PyTorch code:
F.max_pool2d( F.pad(x, (padding_left, padding_right, padding_top, padding_bottom), mode='replicate'), self.size, stride=self.stride )
TensorRT Version: 7.1
GPU Type: Jetson NX