Description
class Traversability(nn.Module):
def forward(self, untraversable: torch.Tensor) -> torch.Tensor:
return (untraversable == 1) | (untraversable == 2)
...
dummy_input = torch.randint(0, 4, (3, 224, 224), dtype=torch.int8)
...
results in
[04/08/2024-16:10:14] [TRT] [E] 4: input: input/output with DataType Int8 in network without Q/DQ layers must have dynamic range set when no calibrator is used.
[04/08/2024-16:10:14] [TRT] [E] 4: [network.cpp::validate::2772] Error Code 4: Internal Error (DataType does not match TensorFormats.)
[04/08/2024-16:10:14] [TRT] [E] 2: [builder.cpp::buildSerializedNetwork::751] Error Code 2: Internal Error (Assertion engine != nullptr failed. )
Environment
TensorRT Version: 8.5
GPU Type: GeForce RTX 3060
Nvidia Driver Version: 550.54.15
CUDA Version: 11.8
CUDNN Version: 8.9.7
Operating System + Version: Ubuntu 20.04
Python Version (if applicable): 3.8
PyTorch Version (if applicable): 2.2.2
Baremetal or Container (if container which image + tag): nvidia/cuda:11.4.3-devel-ubuntu20.04
Relevant Files
Steps To Reproduce
From that branch (bug5)
./docker/build.sh
./docker/run.sh
python3 trav.py save # Creates the onnx file
python3 convert.py