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.

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

pnnx load dynamo onnx of segmentation models #5458

Merged
merged 1 commit into from
May 13, 2024

Conversation

nihui
Copy link
Member

@nihui nihui commented May 11, 2024

model

  • DeepLabV3
  • FCN
  • LRASPP
    - [ ] Faster R-CNN
    - [ ] FCOS
    - [ ] RetinaNet
    - [ ] SSD
    - [ ] SSDlite
    - [ ] Mask R-CNN
    - [ ] Keypoint R-CNN
    - [ ] RAFT

misc

  • build minimal onnxruntime
  • disable onnx2pnnx by default

onnx native op

  • Abs
  • Acos
  • Add
  • Asin
  • Atan
  • AveragePool
  • BatchNormalization
  • CeLU
  • Ceil
  • Clip
  • Concat
  • Constant
  • Conv
  • ConvTranspose
  • Cos
  • DepthToSpace
  • Div
  • Dropout
  • Elu
  • Erf
  • Exp
  • Flatten
  • Floor
  • GRU
  • Gelu
  • Gemm
  • GlobalAveragePool
  • GlobalMaxPool
  • GroupNorm
  • HardSigmoid
  • HardSwish
  • ImageScaler
  • InstanceNormalization
  • LRN
  • LSTM
  • LayerNorm
  • LeakyRelu
  • Log
  • MatMul
  • Max
  • MaxPool
  • Min
  • Mul
  • Neg
  • PRelu
  • Pad
  • Pow
  • RNN
  • Reciprocal
  • ReduceL1
  • ReduceL2
  • ReduceLogSum
  • ReduceLogSumExp
  • ReduceMax
  • ReduceMean
  • ReduceMin
  • ReduceProd
  • ReduceSum
  • ReduceSumSquare
  • Reshape
  • Resize
  • Shrink
  • Sigmoid
  • Sin
  • Slice
  • Softmax
  • Split
  • Sqrt
  • Squeeze
  • Sub
  • Sum
  • Tan
  • Tanh
  • Transpose
  • Unsqueeze
  • Upsample

@nihui nihui changed the title [WIP] pnnx load dynamo onnx part2 pnnx load dynamo onnx of segmentation models May 13, 2024
@nihui nihui merged commit 1b7e635 into Tencent:master May 13, 2024
8 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

1 participant