GithubHelp home page GithubHelp logo

Comments (9)

openppl-public avatar openppl-public commented on August 16, 2024

What's the command you ran in this case?

from ppl.nn.

Maosquerade avatar Maosquerade commented on August 16, 2024

pplnn-build/tools/pplnn --onnx-model ~/model/maskrcnn/mask_rcnn.onnx --input binary_data.bin --in-shapes 1_3_224_224

from ppl.nn.

Si-XU avatar Si-XU commented on August 16, 2024

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.

tangyanf avatar tangyanf commented on August 16, 2024

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.

Maosquerade avatar Maosquerade commented on August 16, 2024

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.

tangyanf avatar tangyanf commented on August 16, 2024

@Maosquerade

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.

Maosquerade avatar Maosquerade commented on August 16, 2024

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.

openppl-public avatar openppl-public commented on August 16, 2024

Please send your input file to [email protected]

from ppl.nn.

Maosquerade avatar Maosquerade commented on August 16, 2024

It worked! Thanks again!

from ppl.nn.

Related Issues (20)

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo 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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.