data = torch.ones((1, 1, 512, 32, 32), dtype=torch.float32)
grid = torch.ones((1, 512, 32, 32, 3), dtype=torch.float32).cuda()
res = torch.nn.functional.grid_sample(img, grid)
The ONNX model performs inference correctly, but conversion to TensorRT fails. The error indicates that the GridSample operator does not support 5D input format.