-
Hi,
Thanks for the amazing work.
I am working on a windows 10 OS with a RTX2060. The TensorRT is installed correctly. But I have some problem installing the torch2trt.
So I can't run the with the "…
-
## Description
When I convert a PyTorch model to onnx and then use TensorRT to parse it, I get this error.
> [8] Assertion failed: (transformationMode == "asymmetric") && "This version of TensorR…
-
--------------------------------------------------------------------------------
Warning: Encountered known unsupported method torch.Tensor.__format__
Warning: Encountered known unsupported method t…
-
Hi, I'm trying to install torch2trt when building docker image in a jetson xavier nx. I'm using as base image a nvidia container with tensorrt and pytorch installed, but the next error appears:
``…
-
Thanks for sharing this amazing work, however when I predict my own image by using `python3 eval.py --config yolact_edge_pytorch_config --trained_model=weights/yolact_edge_14_3000.pth --top_k=100 …
-
## Description
I have converted a pytorch segmentation model to tensorrt.But when I try to infer from this model using the python tensorrt API I get junk valuesfrom the model ,on the other hand w…
-
## Description
I make Efficiennet onnx file using this repository.
(https://github.com/rwightman/gen-efficientnet-pytorch)
and I'm try inference using torch2trt.
(https://github.com/NVIDIA-AI-…
-
I've been trying to evaluate my own random jpg file, however I keep getting errors as below.
Traceback (most recent call last):
**File "eval.py", line 1282, in
calibration_dataset = [cal…
-
This is more of a question rather than an issue, but does torch2trt support multiple inputs as in a list/dict of tensors?
I've been eyeing torch2trt as an alternative to torch.onnx.export because t…
-
1. Do I need a annotations file for calibrations?
2. I am using TensorRT fp16 optimize (--use_fp16_tensorrt) but the network didn't find even one object (without the TensorRT it's works perfect).
It…