Comments (9)
What's the command you ran in this case?
from ppl.nn.
pplnn-build/tools/pplnn --onnx-model ~/model/maskrcnn/mask_rcnn.onnx --input binary_data.bin --in-shapes 1_3_224_224
from ppl.nn.
Hi, I cannot export maskrcnn onnx model directly because mmdet just updated and required mmcv version over than 1.3.7 ( right now, pplnn only support mmcv until 1.3.5).
Could your send your onnx model to [email protected]? I would like to check if it is our fault.
from ppl.nn.
pplnn-build/tools/pplnn --onnx-model ~/model/maskrcnn/mask_rcnn.onnx --input binary_data.bin --in-shapes 1_3_224_224
Have you modified the code of mmdetection,if not could you provide version of mmdetection/mmcv/torchvision/torch/onnx you are using? @Maosquerade
from ppl.nn.
I'm using
mmdet 2.14.0
mmcv-full 1.3.8
torch-vision 0.10.0
torch 1.9.0
onnx 1.9.0
from ppl.nn.
I'm using
mmdet 2.14.0 mmcv-full 1.3.8 torch-vision 0.10.0 torch 1.9.0 onnx 1.9.0
i have tried to generate a model with the environment you provide,use the same command,
python ../tools/deployment/pytorch2onnx.py ../configs/mask_rcnn/mask_rcnn_r50_fpn_mstrain-poly_3x_coco.py \
mask_rcnn_r50_fpn_mstrain-poly_3x_coco_20210524_201154-21b550bb.pth \
--output-file mask_rcnn.onnx --dynamic-export
But the model is different from the one you provided, I will send it to you through the official email
from ppl.nn.
Thanks for reply! I recieved the model you provided, but it seems to have the same problem as before, it failed with
[INFO][2021-07-16 14:25:01.533][pplnn.cc:708] ppl.nn version: 5528434e92a1d7a5a923e69a13e2f8f7c4f0e237-dirty
[WARNING][2021-07-16 14:25:03.017][engine.cc:211] Default input dims for dynamic graph are 1_3_224_224, we recommend using '--dims' to set a suitable training shape.
[ERROR][2021-07-16 14:25:03.017][quant_param_parser.cc:103] open quant file[] failed.
[INFO][2021-07-16 14:25:03.017][engine.cc:278] Quant tensor size: 0
[INFO][2021-07-16 14:25:03.017][pplnn.cc:109] ***** register CudaEngine *****
[ERROR][2021-07-16 14:25:03.332][shape_param.h:41] Matrix has unknown dim count and cannot append.
[ERROR][2021-07-16 14:25:03.332][shape_param.h:41] Matrix has unknown dim count and cannot append.
[ERROR][2021-07-16 14:25:03.332][shape_param.h:41] Matrix has unknown dim count and cannot append.
[ERROR][2021-07-16 14:25:03.332][shape_param.h:41] Matrix has unknown dim count and cannot append.
[ERROR][2021-07-16 14:25:03.332][shape_param.h:41] Matrix has unknown dim count and cannot append.
[INFO][2021-07-16 14:25:03.333][simple_graph_partitioner.cc:107] total partition(s) of graph[torch-jit-export]: 1.
[ERROR][2021-07-16 14:25:03.334][reshape_reshape.cc:66] infer shape failed.
[ERROR][2021-07-16 14:25:03.350][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.351][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.351][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.352][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.352][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.352][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.352][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.353][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.353][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.353][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.353][reshape_unsqueeze.cc:36] axes overflow.
[ERROR][2021-07-16 14:25:03.353][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.353][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.353][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.353][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.353][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.353][reshape_split.cc:59] splited axis and sum of split point not match.
[INFO][2021-07-16 14:25:03.353][simple_graph_partitioner.cc:107] total partition(s) of graph[torch-jit-export1]: 1.
[INFO][2021-07-16 14:25:03.353][opt_graph.cc:202] Create 2 TensorImpl
[INFO][2021-07-16 14:25:03.353][opt_graph.cc:314] added 2 new bridge kernels
[INFO][2021-07-16 14:25:03.354][opt_graph.cc:481] deleted 1 bridge kernels
[INFO][2021-07-16 14:25:03.354][simple_graph_partitioner.cc:107] total partition(s) of graph[torch-jit-export2]: 1.
[INFO][2021-07-16 14:25:03.354][opt_graph.cc:202] Create 20 TensorImpl
[INFO][2021-07-16 14:25:03.354][opt_graph.cc:314] added 21 new bridge kernels
[INFO][2021-07-16 14:25:03.356][opt_graph.cc:481] deleted 14 bridge kernels
[ERROR][2021-07-16 14:25:03.356][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.356][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.356][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.356][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.356][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.356][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.356][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.356][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.356][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.389][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.389][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.389][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.389][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.389][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.389][reshape_add.cc:39] unbroadcastable input.
[ERROR][2021-07-16 14:25:03.389][reshape_unsqueeze.cc:36] axes overflow.
[ERROR][2021-07-16 14:25:03.389][reshape_unsqueeze.cc:36] axes overflow.
[INFO][2021-07-16 14:25:03.390][simple_graph_partitioner.cc:107] total partition(s) of graph[torch-jit-export3]: 1.
[INFO][2021-07-16 14:25:03.390][opt_graph.cc:202] Create 2 TensorImpl
[INFO][2021-07-16 14:25:03.390][opt_graph.cc:314] added 2 new bridge kernels
[INFO][2021-07-16 14:25:03.390][opt_graph.cc:481] deleted 1 bridge kernels
[INFO][2021-07-16 14:25:03.390][simple_graph_partitioner.cc:107] total partition(s) of graph[torch-jit-export4]: 1.
[INFO][2021-07-16 14:25:03.390][opt_graph.cc:202] Create 20 TensorImpl
[INFO][2021-07-16 14:25:03.390][opt_graph.cc:314] added 21 new bridge kernels
[INFO][2021-07-16 14:25:03.391][opt_graph.cc:481] deleted 14 bridge kernels
[ERROR][2021-07-16 14:25:03.391][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.391][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.391][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.391][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.391][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.391][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.392][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.392][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.392][reshape_split.cc:59] splited axis and sum of split point not match.
[ERROR][2021-07-16 14:25:03.394][reshape_split.cc:59] splited axis and sum of split point not match.
[INFO][2021-07-16 14:25:03.394][simple_graph_partitioner.cc:107] total partition(s) of graph[torch-jit-export5]: 1.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[ERROR][2021-07-16 14:25:03.394][reshape_concat.cc:42] input shape not match.
[INFO][2021-07-16 14:25:03.394][opt_graph.cc:202] Create 116 TensorImpl
[INFO][2021-07-16 14:25:03.395][opt_graph.cc:314] added 152 new bridge kernels
[INFO][2021-07-16 14:25:03.397][opt_graph.cc:481] deleted 131 bridge kernels
[INFO][2021-07-16 14:25:03.397][opt_graph.cc:202] Create 1885 TensorImpl
[INFO][2021-07-16 14:25:03.472][opt_graph.cc:314] added 2146 new bridge kernels
[INFO][2021-07-16 14:26:40.894][opt_graph.cc:481] deleted 2073 bridge kernels
[ERROR][2021-07-16 14:26:40.945][scheduler_common.cc:170] exec kernel[Pad_146] failed: invalid value
[ERROR][2021-07-16 14:26:40.945][sequential_scheduler.cc:116] execute kernel[Pad_146] failed: invalid value
[ERROR][2021-07-16 14:26:40.946][pplnn.cc:809] Run() failed: invalid value
Does that model work for you?
from ppl.nn.
Please send your input file to [email protected]
from ppl.nn.
It worked! Thanks again!
from ppl.nn.
Related Issues (20)
- Onnx run error HOT 2
- 请问支持int8在高通芯片上cDSP进行推理吗?
- Slice op question HOT 1
- pplnn run mobilenet v2 model failed. (use cuda) HOT 7
- linux compile error protobuf static assertion failed HOT 3
- malloc_consolidate(): invalid chunk size HOT 2
- pplnn save-input 得到的NDARRAY的 shape不正确 HOT 1
- 如何使用cmake的将ppl.nn和依赖ppl.nn的代码一同编译? HOT 3
- Segmentation fault at ppl::nn::x86::X86Kernel::DumpOutputTensors HOT 5
- 获取模型推理结果(GetOutputs)耗时长 HOT 2
- Install Error HOT 1
- The compilation passed, but an error was reported in test phase HOT 2
- Floating point exception (core dumped) ? HOT 4
- 使用x86 engine运行resnet50 fp16 onnx模型 core dump
- (Ask) why InferInheritedType handle int8 to fp16 out? HOT 3
- Got wrong output shape when run a Gemm op(transB=0) use cuda HOT 4
- Crash with ONNX Split operator
- 关于全局engine,其他线程引用导致的性能下降问题 HOT 4
- 推理误差排查
- 多模型pipeline的示例
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ppl.nn.