fabio-sim LightGlue-ONNX issues

fabio-sim / LightGlue-ONNX

ONNX-compatible LightGlue: Local Feature Matching at Light Speed. Supports TensorRT, OpenVINO

Apache License 2.0

375 stars 34 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Conversion of lightglue's model to tensorRT format with trtexec failed

#98 emmmmm196 opened 1 week ago
0
long inference time of using TensorrtExecutionProvider

#97 noahzn opened 1 week ago
0
Could you tell me your versions of tensorrt and cuDNN? I encountered compatibility issues, thank you

#96 XL634663985 closed 3 weeks ago
2
TracerWarning: torch.tensor results are registered as constants in the trace.

#95 zhj296409022 opened 1 month ago
1
feat: Add OpenVINO

#94 fabio-sim closed 1 month ago
0
OPENVINO

#93 pinnintipraneethkumar closed 1 month ago
2
match extractor_type

#92 Fantesim closed 1 month ago
1
feat: pure TensorRT example

#91 fabio-sim closed 1 month ago
0
Lightglue produces wrong matches after TensorRT optimization

#90 PeppeFacoltativo closed 1 month ago
2
QKV Error when keypoint number is small

#89 biggiantpigeon closed 1 month ago
1
onnx vs pth performance

#88 JaouadROS closed 2 months ago
3
feat: DISK end-to-end batch pipeline

#87 fabio-sim closed 4 months ago
0
Match indices out of range

#86 llschloesser closed 3 months ago
2
Convert 2.0 End-to-end parallel ONNX file to TensorRT engine

#85 EvW1998 closed 1 month ago
4
fix: BC torch version < 2.4

#84 fabio-sim closed 4 months ago
0
support for different sizes of inputs

#83 GreatZeZuo closed 1 month ago
3
feat: Dynamic batch

#82 fabio-sim closed 4 months ago
0
Key points from thesuperpoint

#81 l333wang closed 1 month ago
3
the possiblity of supporting batch input

#80 noahzn closed 4 months ago
12
ONNX support for lightglue-sift

#79 lvfengkun opened 5 months ago
2
error when using TensorrtExecutionProvider for ONNX models

#78 noahzn closed 5 months ago
18
convert SuperPoint from onnx to engine

#77 midskymid closed 4 months ago
1
False Positive Keypoints on uniform Images

#76 DavideCatto closed 5 months ago
3
UnsupportedOperatorError: Exporting the operator 'aten::scaled_dot_product_attention' to ONNX opset version 17

#75 BayRanger closed 6 months ago
3
Use providers argument for extractor

#74 davidtvs closed 7 months ago
1
LightGlue

#73 Ddd195 closed 4 months ago
0
how to convert onnx into an rknn model？

#72 ouxiand closed 6 months ago
8
Adding support for SIFT

#71 demplo opened 7 months ago
3
".trt.onnx"export example

#70 WYKXD closed 5 months ago
1
ALIKED Support

#69 mug1wara26 opened 8 months ago
2
some problem that delopy on device, such as snapdragon snpe.

#68 guker closed 5 months ago
1
Error when building the end2end onnx file.

#67 najingligong1111 closed 4 months ago
1
Internal Error (/lightglue/ArgMax)

#66 chenscottus closed 7 months ago
4
error when convert tensorRt engine model

#65 long-senpai closed 4 months ago
4
Converting a trained model to ONNX

#63 ikaftan closed 7 months ago
4
Result diffrent from the original repository?

#62 1191658517 closed 9 months ago
3
Running inference throws a CUDA exception

#61 laxnpander closed 4 months ago
1
Running inference using exported models in C++ very unstable/non-deterministic

#60 will-kudan closed 7 months ago
2
The output shape of lightglue's onnx model is dynamic. Does tensorrt support dynamic output?

#59 weihaoysgs closed 11 months ago
4
Build Superpoint onnx file to Tensorrt engine failed, encounter Error (Could not find any implementation for node {ForeignNode[/Flatten.../Transpose_3]}

#58 weihaoysgs closed 11 months ago
5
feat: LightGlue TensorRT engine inference

#57 fabio-sim closed 11 months ago
0
Is the lightglue run in the tensorrt mode, and how to using C++ inferface build engine?

#56 weihaoysgs closed 11 months ago
6
aliked

#55 sushi31415926 closed 11 months ago
2
support dynamic batch size

#54 WalkerWen closed 11 months ago
1
jetson

#53 sushi31415926 closed 7 months ago
1
[softMaxV2Runner.cpp::execute::226] Error Code 1: Cask (shader run failed)

#52 fighterzzzh closed 7 months ago
2
NOT_IMPLEMENTED : Non-zero status code returned while running MultiHeadAttention node

#51 dmoti closed 1 year ago
3
我在jetson agx上运行infer.py，花费19s才完成，是我的环境有问题吗？tensorrt的版本一定要是8.6吗

#50 Ddd195 closed 7 months ago
1
How do I export without specifying an img size

#49 SpenceraM closed 1 year ago
1
optim: topk trick

#47 fabio-sim closed 1 year ago
0