NVIDIA-AI-IOT torch2trt issues

NVIDIA-AI-IOT / torch2trt

An easy to use PyTorch to TensorRT converter

MIT License

4.56k stars 673 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

There are issues with support for `ConvTranspose2d`

#946 mortal-Zero opened 1 week ago
1
Handle None in output_size

#945 eamonn-ss opened 1 month ago
0
Unsupported methods encountered issue, `torch.Tensor.to(torch.device("cuda"))`. Will torch.Tensor.to for devices be implemented?

#944 darrenchang opened 1 month ago
1
when use own defined convertor, why int tensor input has no _trt attribute?

#943 lantudou opened 1 month ago
2
Add ProfilingVerbosity Option to Engine Build Configuration

#942 Houssem-kikleo opened 1 month ago
0
apiVersion: apps/v1 kind: Deployment metadata: name: titan-dataguard spec: replicas: 3 selector: matchLabels: app: titan-dataguard template: metadata: labels: app: titan-dataguard spec: containers: - name: titan-dataguard image: your_docker_image ports: - containerPort: 80 --- apiVersion: v1 kind: Service metadata: name: titan-dataguard spec: selector: app: titan-dataguard ports: - protocol: TCP port: 80 targetPort: 80 type: LoadBalancer

#941 felipeliliti opened 2 months ago
0
Unsupported method!

#940 boge2023 opened 2 months ago
1
ROOT CAUSE？when used `nn.Transpose3d `, the shape of weight of transpose3d was consistency with nn.Transpose3D in torch.

#939 Yuxiang1990 opened 2 months ago
0
ROOT CAUSE? `InstanceNorm3D` with tensorRT result consistency with nn.Instance_norm3d

#938 Yuxiang1990 opened 2 months ago
0
Failed to 'sudo python3 setup.py install --plugins'

#937 CMeiyi opened 3 months ago
0
AttributeError when using torch.nn.functional.pad

#936 clementabary opened 3 months ago
0
ONNX export mode is set to TrainingMode.EVAL, but operator 'instance_norm' is set to train=True

#935 edwardnguyen1705 closed 2 months ago
2
input of batchnorm1d can also be (N,C)

#934 taotaoorange opened 3 months ago
0
Is that available on orin nano?

#933 adrenalin7237 opened 3 months ago
2
Support text models

#932 aliencaocao opened 3 months ago
0
Unable to convert SigLIP text transformer due to missing model input when exporting model to onnx

#931 aliencaocao opened 3 months ago
0
SyntaxWarning of dataset.py:61

#930 grapevine-AI opened 3 months ago
1
OSS-Fuzz Integration

#929 ennamarie19 opened 3 months ago
0
How to save a model to TRT file? Not covered in the docs

#928 talcs opened 3 months ago
1
_trt.shape overflow when converting from pytorch to TRT

#927 Justin020718 opened 3 months ago
5
There are questions about the parameters needed for forward propagation in model transformation

#926 huangshilong911 opened 4 months ago
2
AttributeError: 'DataParallel' object has no attribute 'img_size'

#925 huangshilong911 closed 4 months ago
2
Segmentation fault on nn.Linear

#924 brazhenko opened 4 months ago
1
increment version to v0.5.0

#923 jaybdub closed 4 months ago
0
[WIP] Dev trt 10 refactor

#922 jaybdub closed 4 months ago
0
fix dynamic axes name specification in onnx export

#921 jaybdub closed 4 months ago
0
AttributeError: 'tensorrt_bindings.tensorrt.INetworkDefinition' object has no attribute 'add_convolution'. Did you mean: 'add_convolution_nd'?

#920 AWallyAllah opened 5 months ago
3
Package is not PEP 517 compliant, making it incompatible with package managing tools

#919 elisa-aleman opened 5 months ago
0
Error in converting hybridnets model using torch2trt

#918 moscaAle29 opened 6 months ago
0
[Question & FeatureRequest] Is that possible to convert a torch.nn.Module to TRTMoudle?

#917 ElinLiu0 opened 6 months ago
1
torch2trt shows error when converting a model, even though regular pytorch -> onnx -> tensorrt and inference is successful

#916 ninono12345 closed 8 months ago
0
python model successfully tested on polygraphy tensorrt, but failed, when loading on torch2trt

#915 ninono12345 opened 8 months ago
0
dla check bugfix

#914 jaybdub closed 8 months ago
0
'tensorrt.tensorrt.Builder' object has no attribute 'build_cuda_engine'

#913 maxmelichov opened 8 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model with ConvTranspose2d operator

#912 hongliyu0716 opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model with Interpolate operator

#911 hongliyu0716 opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model with BatchNorm or InstanceNorm operator

#910 hongliyu0716 opened 9 months ago
1
Inconsistent inference results between PyTorch and converted TensorRT model with MaxPool2d operator

#909 hongliyu0716 opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model with Selu operator

#908 hongliyu0716 opened 9 months ago
0
repvggblock in torch2trt

#907 chennaikai11 opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model with Pad operator

#906 hongliyu0716 opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model with AvgPool2d operator

#905 hongliyu0716 opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model using with Linear operator

#904 Thrsu opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model using with Normalize operator

#903 Thrsu opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model using with Silu operator

#902 Thrsu opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model using with Softplus operator

#901 Thrsu opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model using with LogSoftmax operator

#900 Thrsu opened 9 months ago
0
Inconsistent inference results between PyTorch and converted TensorRT model using with GumbelSoftmax operator

#899 Thrsu opened 9 months ago
0
torch_dim_to_trt_axes does not handle dim=-1 correctly

#898 Thrsu opened 9 months ago
0
TypeError: 'int' object is not iterable when using torch2trt to convert a PyTorch model with Transformer operator

#897 Thrsu opened 9 months ago
1