Skip to content
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.

Sign up for GitHub

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

Jump to bottom

operation requirements #74

Closed
li-qing opened this issue May 15, 2019 · 107 comments
Closed

operation requirements #74

li-qing opened this issue May 15, 2019 · 107 comments
Labels
pinned

Comments

@li-qing
Copy link
Contributor

li-qing commented May 15, 2019 •
edited by czy2014hust
Loading

Known Op Requirements For TensorFlow

Ops(TensorArrayxxx) is from tensorflow Detection postprocess API, which are not necessary to support, because DetectionPostProcess is supported.

Known Op Requirements For TensorFlow Lite

Known Op Requirements For ONNX

Known Op Requirements For Caffe

  • route (@RobertAuditore)
  • power (@OOYueshenOO)
  • Upsample (@cyf518)

If you have any op requirements, you could write a comment to let us know, even if it's mentioned above. Please specify where the op comes from(Tensorflow, Caffe, or ONNX) like this:

Framework:
...

Not Supported OP:
...
@li-qing li-qing pinned this issue May 15, 2019
@li-qing li-qing changed the title tracking of operation requirements operation requirements May 15, 2019
@jxt1234 jxt1234 unpinned this issue May 15, 2019
@jxt1234 jxt1234 pinned this issue May 15, 2019
@CodingBoO
Copy link
Contributor

power op

@92ypli
Copy link

92ypli commented May 17, 2019

shuffle op

@xiaohaipeng
Copy link

Constant op

@czy2014hust
Copy link
Collaborator

Please specify where the op comes from(Tensorflow, Caffe, or ONNX)
like this:

  • Not Supported OP:
    ...
  • Framework
    ...

@yizhaoyanbo
Copy link
Contributor

yizhaoyanbo commented May 21, 2019 •
edited
Loading

  • Not Supported OP:

pad
clip
LeakyReLU

  • Framework:

ONNX

@czy2014hust czy2014hust mentioned this issue May 24, 2019
Closed
@valwang
Copy link

valwang commented May 24, 2019

Not Supported OP:
18 Mul

Framework:
TFLITE

@92ypli
Copy link

92ypli commented May 29, 2019

Not Supported OP:
shufflenet

Framework:
pytorch or onnx

@li-qing
Copy link
Contributor Author

li-qing commented May 30, 2019

Not Supported OP:
shufflenet

Framework:
pytorch or onnx

ShuffleNet is a network not an op

@92ypli
Copy link

92ypli commented May 30, 2019

Sorry, my meaning is ShuffleChannel.

@czy2014hust
Copy link
Collaborator

Sorry, my meaning is ShuffleChannel.

ShuffleChannel is NOT a OP in pytorch、onnx or tensorflow! By the way tensorflow-shufflenet is tested. You can try.

@ChisenZhang
Copy link

not support OP:
Neg
Framework:
ONNX

@rkshuai
Copy link

rkshuai commented Jun 3, 2019

  • Not Supported OP:

pad

  • Framework:

tensorflow

@chienkan
Copy link

chienkan commented Jun 3, 2019

Not Supported OP:
Transpose
Fully_Connected

Framework:
TensorFlow Lite

@92ypli
Copy link

92ypli commented Jun 11, 2019

Framework:
onnx

Not Supported OP:
Transpose

@AddASecond
Copy link

Framework:
Tensorflow

Not Supported OP:
FusedBatchNorm

Framework:
caffe

Not Supported OP:
route (yolo2)

@563816752
Copy link

Op Requirements For ONNX
Mul
ReLU6

@tanhui2975
Copy link

Framework:
onnx

Not Supported OP:
Transpose

@crj0322
Copy link

crj0322 commented Jun 18, 2019

Not Supported OP:
FusedBatchNormV3

Framework:
Tensorflow

@WenguoLi
Copy link

WenguoLi commented Jun 20, 2019 •
edited
Loading

Not Supported OP:
ResizeBilinear Uint8 quantized Mode

Error:
Start to Convert Other Model Format To MNN Model...
terminate called after throwing an instance of 'Error'
what(): [16:44:02] /home/apuser/deeplearning/alibaba/MNN/tools/converter/source/tflite/ResizeBilinear.cpp:16: Check failed: !quantizedModel ==>

Framework:
Tensorflow lite

@MoonBunnyZZZ
Copy link

Framework:
ONNX(pytorch)

Not Supported OP:
ELU

@kunyao2015
Copy link

Framework:
onnx

Not Supported OP:
Transpose

@li-qing
Copy link
Contributor Author

li-qing commented Jul 2, 2019

@92ypli @tanhui2975 @kunyao2015
Transpose for ONNX is supported in latest commit.

@li-qing
Copy link
Contributor Author

li-qing commented Jul 2, 2019

@yizhaoyanbo @563816752
Pad, Clip for ONNX are supported in latest commit.

@mchalecki
Copy link

Not Supported OP:
ReduceMean

Framework:
ONNX(pytorch)

@mchalecki
Copy link

Not Supported OP:
MirrorPad, OneHot

Framework:
Tensorflow

@xiexuliunian
Copy link

Framework:

onnx

Not Supported OP:

Asymmetrical pads

@chienkan
Copy link

chienkan commented Mar 4, 2020

Framework:
Caffe

Not Supported OP:
ConvolutionDepthwise

@czy2014hust czy2014hust mentioned this issue Mar 26, 2020
Closed
@nidetaoge
Copy link

Not Supported OP:
Tensorflow::Resampler

Framework:
tensorflow

See this issue:
#725

Thx so much!

@dragen1860
Copy link

Framework:
PyTorch/ONNX

Not Supported OP:
Deformable Convolution

@coollofty
Copy link

Framework:
TensorflowLite

Not Supported OP:
PRELU

@dzyjjpy
Copy link

dzyjjpy commented Apr 11, 2020

Framework:
PyTorch/ONNX

Not Supported OP:
Deformable Convolution

+1 dcn op needed for YOLACT++

@jelloit
Copy link

jelloit commented Apr 28, 2020

Framework:
Pytorch/ONNX

Not Supported OP:
MatMul with batch size

@stanleywang8888 stanleywang8888 unpinned this issue May 9, 2020
@JesonYYY
Copy link

Framework:
TensorflowLite

Not Supported OP:
PRELU

@Echosanmao
Copy link

Framework:
TensorflowLite

Not Supported OP:
DIV

@Kepnu4
Copy link

Kepnu4 commented May 27, 2020

Framework:
Pytorch/ONNX

Not Supported OP:
NonZero

@871699406
Copy link

871699406 commented Jun 28, 2020 •
edited
Loading

Framework:
TensorflowLite

Not Supported OP:
ResizeNearestNeighbor Uint8

@buqing2009
Copy link

Framework:
ONNX

Not Supported OP:
And
GatherElements
No
Range
ReduceL1
Slice
Where

@dragen1860
Copy link

Framework:
PyTorch/ONNX

Not Supported OP:
RoiAlign

@songyanbei
Copy link

Framework:
PyTorch/ONNX

Not Supported OP:
RoiAlign
AliasWithName
BBoxTransform
BoxWithNMSLimit
GenerateProposals

@lcaikk1314
Copy link

Framework:
tflite

Not Supported OP:
SPACE_TO_BATCH_ND

@RuisongZhou
Copy link

Framework:
PyTorch/ONNX

Not Supported OP:
PixelShuffle

@121786404
Copy link

Framework:
TensorflowLite

Not Supported OP:
PRELU

https://raw.githubusercontent.com/aqua1907/Gesture-Recognition/master/models/palm_detection_without_custom_op.tflite

@121786404 121786404 mentioned this issue Aug 26, 2020
Closed
@shwanliu
Copy link

shwanliu commented Nov 5, 2020

not support OP:
Flatten
Framework:
ONNX（pytorch）

@TianzhongSong
Copy link

opencl ArgMax (caffe)

@MingLunHan
Copy link

cosine_similiarity for onnx

@sudowind
Copy link

sudowind commented Dec 17, 2020 •
edited
Loading

Framework:
ONNX (Pytorch)

Not supported OPs:
Atan
Nonzero
GRU

@FrankyCao
Copy link

Not Supported OP:
Tensorflow::ComplexAbs
Tensorflow::IRFFT
Tensorflow::If
Tensorflow::PlaceholderWithDefault
Tensorflow::RFFT

Framework:
tensorflow

@649453932
Copy link

tensorflow lite
NOT_SUPPORTED_OP: [ EXPAND_DIMS ]

@NiuCY
Copy link
Contributor

NiuCY commented Aug 11, 2022

Framework:
ONNX (Pytorch)

Not supported OPs:
ConvTranspose 3D

@friskyliu
Copy link

Framework:
TensorflowLite

Not Supported OP:
PRELU

1 similar comment
@lvZic
Copy link

lvZic commented Oct 8, 2022

Framework:
TensorflowLite

Not Supported OP:
PRELU

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
pinned
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests