operators
https://github.com/Tencent/ncnn/blob/master/docs/developer-guide/operators.md
- AbsVal
- ArgMax
- BatchNorm
- Bias
- BinaryOp
- BNLL
- Cast
- CELU
- Clip
- Concat
- Convolution
- Convolution1D
- Convolution3D
- ConvolutionDepthWise
- ConvolutionDepthWise1D
- ConvolutionDepthWise3D
- CopyTo
- Crop
- CumulativeSum
- Deconvolution
- Deconvolution1D
- Deconvolution3D
- DeconvolutionDepthWise
- DeconvolutionDepthWise1D
- DeconvolutionDepthWise3D
- DeformableConv2D
- Dequantize
- Diag
- Dropout
- Eltwise
- ELU
- Embed
- Exp
- Flatten
- Fold
- GELU
- GLU
- Gemm
- GridSample
- GroupNorm
- GRU
- HardSigmoid
- HardSwish
- InnerProduct
- Input
- InstanceNorm
- Interp
- LayerNorm
- Log
- LRN
- LSTM
- MemoryData
- Mish
- MultiHeadAttention
- MVN
- Noop
- Normalize
- Packing
- Padding
- Permute
- PixelShuffle
- Pooling
- Pooling1D
- Pooling3D
- Power
- PReLU
- Quantize
- Reduction
- ReLU
- Reorg
- Requantize
- Reshape
- RMSNorm
- RNN
- Scale
- SELU
- Shrink
- ShuffleChannel
- Sigmoid
- Slice
- Softmax
- Softplus
- Split
- Swish
- TanH
- Threshold
- Tile
- UnaryOp
- Unfold
https://github.com/Tencent/ncnn/blob/master/docs/developer-guide/operation-param-weight-table.md
https://blog.csdn.net/p731heminyang/article/details/138496536