torch2trt icon indicating copy to clipboard operation
torch2trt copied to clipboard

An easy to use PyTorch to TensorRT converter

Results 235 torch2trt issues
Sort by recently updated
recently updated
newest added

Hello, As a summary, I try to run yolox with deepsort on a nvidia jetson xavier AGX dev kit I tried and managed to run YOLOX-S with deepsort and a...

Currently my PyTorch model has the following inputs: - A tensor with size (B, 1, 300) where B is the batch size - A list of [pack_padded_sequence](https://pytorch.org/docs/master/generated/torch.nn.utils.rnn.pack_padded_sequence.html) objects, each of...

python3 tools/trt.py -f ./exps/default/yolox_s.py -c ./yolox-s-1189-640x640.pth 2022-03-29 18:56:36.631 | INFO | __main__:main:57 - loaded checkpoint done. [03/29/2022-18:56:39] [TRT] [I] [MemUsageChange] Init CUDA: CPU +306, GPU +0, now: CPU 3148, GPU...

I tried to create a .engine file form my mmsegemetation pytorch model with the following script: ``` import sys sys.path.insert(0,'/workspace/torch2trt') sys.path.insert(1,'/workspace/mmsegmentation') import torch from torch2trt import torch2trt from mmseg.apis import...

torch.Tensor.transpose converter is missed. I just add the annotation to link torch.Tensor.transpose and torch.transpose

I got some warning while converting model. ``` Warning: Encountered known unsupported method torch.Tensor.transpose ``` It seems torch2trt has `torch.transpose` converter but it dose not applied to `torch.Tensor.transpose`. So, I...

Dear Authors, We have the following hardware and software configuration: Hardware: Nvidia Jetson Nano 4GB Software: 1. JetPack 4.4 (L4T 32.4.3); 2. PyTorch 1.6.0; 3. TensorRT 7.1.3.0 However, we failed...

hi, when I was running this code: import torch import os from torch2trt import torch2trt from torchvision.models.resnet import resnet18 os.environ["CUDA_VISIBLE_DEVICES"]="2" model = resnet18(pretrained=True).eval().cuda() x = torch.ones((1, 3, 224, 224)).cuda() model_trt...

Hi, from the pip list I find that torch2trt was installed successfully but "from torch2trt import torch2trt" conducted the above error. So I try to just import torch2trt, and use...