The Wayback Machine - http://web.archive.org/web/20201117053151/https://github.com/microsoft/onnxruntime/issues
Skip to content

/ onnxruntime

Pinned issues

Please help us improve ONNX Runtime by participating in our s...
#5726 opened Nov 6, 2020 by natke
Open
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

149 Open 1,304 Closed
149 Open 1,304 Closed
Author
Filter by author
Label
Filter by label
Use alt + click/return to exclude labels.
Projects
Filter by project
Milestones
Filter by milestone
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀
onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : The node is not placed on any Execution Provider. OneHot(11) (node while/cond_5/one_hot).
#5825 opened Nov 17, 2020 by oswen
3
index: 1 Got: 3 Expected: 416 index: 3 Got: 416 Expected: 3 Please fix either the inputs or the model.
#5819 opened Nov 16, 2020 by MuhammadAsadJaved
@zhanghuanrong
2
Memory usage with Cuda ExecutionProvider ep:CUDA type:performance type:support
#5801 opened Nov 13, 2020 by radikalliberal
2
Different output when running on CUDA (compared to CPU and keras) type:bug
#5798 opened Nov 13, 2020 by bazukas
@hariharans29
2
memory keep increasing with dynamic input shape of network ep:DNNL type:support
#5796 opened Nov 13, 2020 by yflv-yanxia
Building with "--minimal_build" fails component:build feature: mobile type:bug
#5786 opened Nov 12, 2020 by Linux13524
1
Inputs with UINT8 should fallback to CUDA instead of failing to compile with TRT execution provider ep:CUDA ep:TensorRT type:enhancement
#5785 opened Nov 12, 2020 by joba01
4
Any suggestions to speed up onnx model inference speed ? type:performance type:support
#5784 opened Nov 12, 2020 by quant-science
1
Build with DNNL execution provider failing on macOS, but working on Linux component:build ep:DNNL type:bug
#5783 opened Nov 12, 2020 by j-paulus
2
Any support for double type tensor when loading pytorch onnx model ? type:support
#5782 opened Nov 12, 2020 by quant-science
3
How to loading a pytorch model with input shape of (None, 32) using the C# inference ? api:C# type:support
#5781 opened Nov 12, 2020 by quant-science
3
IR_VERSION and Opset Versions support via C API api:Java type:enhancement
#5780 opened Nov 12, 2020 by jji2019
3
The same input, sometimes the output is different ep:CUDA type:bug
#5769 opened Nov 11, 2020 by feipxyz
@hariharans29
1
Complete example to use yolov3.onnx model for inference status:duplicate type:support
#5765 opened Nov 11, 2020 by MuhammadAsadJaved
1
U8S8 QLinearMatMul NOT_IMPLEMENTED component:operator feature:quantization type:support
#5754 opened Nov 10, 2020 by volcacius
@tracysh
openvino build failed nuget component:build ep:OpenVINO type:support
#5749 opened Nov 10, 2020 by connordouglas1
3
Quantization for LSTM feature: mobile feature:quantization type:enhancement
#5747 opened Nov 10, 2020 by slevental
1
coding bug api:C/C++ status:more-info-needed type:support
#5735 opened Nov 9, 2020 by cqray1990
1
Please help us improve ONNX Runtime by participating in our survey
#5726 opened Nov 6, 2020 by natke
Op in first training step is much slower component:training-core type:performance type:support
#5715 opened Nov 5, 2020 by jupvfranco
2
How to reduce memory used? component:coreruntime type:support
#5711 opened Nov 5, 2020 by nistarlwc
5
TRT FP16 compilation fails on SSD model "could not build engine for fused node" ep:TensorRT type:bug
#5709 opened Nov 5, 2020 by joba01
5
Python 3.8 and newer api:Python type:enhancement
#5697 opened Nov 4, 2020 by evrial
3
Compile error in C++ API header type:bug
#5673 opened Nov 3, 2020 by xkszltl
@yuslepukhin
5
Runtime error when converting T5 decoder with multiple dynamic axes inputs type:bug
#5646 opened Oct 30, 2020 by amanpreet692
@tianleiwu @wangyems
5
ProTip! Adding no:label will show everything without a label.
You can’t perform that action at this time.