From df5ec213457c5572095d079c68c30d9f3ec40d8d Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E5=AE=A6=E6=99=93=E7=8E=B2?= <3174348550@qq.com> Date: Tue, 23 Sep 2025 08:57:12 +0800 Subject: [PATCH] update en files --- .../source_en/reference/operator_list_lite.md | 4 +- .../reference/operator_list_lite_for_caffe.md | 31 +++++ .../reference/operator_list_lite_for_onnx.md | 100 +++++++++++++++ .../operator_list_lite_for_tflite.md | 116 ++++++++++++++++++ .../source_en/reference/operator_lite.rst | 15 +++ .../reference/operator_list_lite.md | 2 +- .../reference/operator_list_lite_for_onnx.md | 38 +++--- .../operator_list_lite_for_tensorflow.md | 2 +- .../operator_list_lite_for_tflite.md | 2 +- .../source_zh_cn/reference/operator_lite.rst | 2 +- 10 files changed, 287 insertions(+), 25 deletions(-) create mode 100644 docs/lite/docs/source_en/reference/operator_list_lite_for_caffe.md create mode 100644 docs/lite/docs/source_en/reference/operator_list_lite_for_onnx.md create mode 100644 docs/lite/docs/source_en/reference/operator_list_lite_for_tflite.md create mode 100644 docs/lite/docs/source_en/reference/operator_lite.rst diff --git a/docs/lite/docs/source_en/reference/operator_list_lite.md b/docs/lite/docs/source_en/reference/operator_list_lite.md index 64d43ca2c1..c40ee97af7 100644 --- a/docs/lite/docs/source_en/reference/operator_list_lite.md +++ b/docs/lite/docs/source_en/reference/operator_list_lite.md @@ -121,7 +121,7 @@ MindSpore Lite supports operator lists for different hardware backends: | NLLLoss | | ✅ | | | | | | | | | | | ✅ | | NLLLossGrad | | ✅ | | | | | | | | | | | | | NotEqual | ✅ | ✅ | ✅ | ✅ | ✅ | | ✅ | ✅ | | | ✅ | | | -| NonMaxSupppression | | ✅ | | | | | | | | | | | ✅ | +| NonMaxSuppression | | ✅ | | | | | | | | | | | ✅ | | NonZero | | | | | | ✅ | | | | | | | ✅ | | OneHot | ✅ | ✅ | ✅ | | | | ✅ | ✅ | ✅ | | | | | | OnesLike | ✅ | ✅ | ✅ | | | | | | | | | ✅ | ✅ | @@ -291,7 +291,7 @@ MindSpore Lite conversion tool supports operator lists for third-party framework | MulGrad | | | | | | Neg | Neg | | Neg | Neg | | NotEqual | NotEqual | | | NotEqual | -| NonMaxSupppression | NonMaxSupppression | | NonMaxSupppression | NonMaxSupppression | +| NonMaxSuppression | NonMaxSuppression | | NonMaxSuppression | NonMaxSuppression | | NonZero | NonZero | | NonZero | NonZero | | OneHot | OneHot | | OneHot | OneHot | | OnesLike | OnesLike | | | OnesLike | diff --git a/docs/lite/docs/source_en/reference/operator_list_lite_for_caffe.md b/docs/lite/docs/source_en/reference/operator_list_lite_for_caffe.md new file mode 100644 index 0000000000..3aaff6542e --- /dev/null +++ b/docs/lite/docs/source_en/reference/operator_list_lite_for_caffe.md @@ -0,0 +1,31 @@ +# List of Caffe Operators Supported by MindSpore Lite + +[![View Source On Gitee](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source_en.svg)](https://gitee.com/mindspore/docs/blob/master/docs/lite/docs/source_en/reference/operator_list_lite_for_caffe.md) + +| MindSpore Lite Operator Names | Corresponding Caffe Operators | +| ---------------------- | -------------------------------- | +| Activation | ReLU, ReLU6, Sigmoid, TanH, Elu | +| ArgmaxFusion | ArgMax | +| AvgPoolFusion | Pooling | +| BatchNorm | BatchNorm | +| Concat | Concat | +| Conv2DFusion | Convolution | +| Conv2dTransposeFusion | Deconvolution | +| Crop | Crop | +| Eltwise | Eltwise | +| Elu | ELU | +| ExpFusion | Exp | +| Flatten | Flatten | +| FullConnection | InnerProduct | +| MaxPoolFusion | Pooling | +| PowFusion | Power | +| PReLUFusion | PReLU | +| ReduceFusion | Reduction | +| Reshape | Reshape | +| Resize | Interp | +| ScaleFusion | Scale | +| SGD | SGD | +| SliceFusion | Slice | +| Softmax | Softmax | +| TileFusion | Tile | +| Transpose | Permute | diff --git a/docs/lite/docs/source_en/reference/operator_list_lite_for_onnx.md b/docs/lite/docs/source_en/reference/operator_list_lite_for_onnx.md new file mode 100644 index 0000000000..0ba6ff0cc0 --- /dev/null +++ b/docs/lite/docs/source_en/reference/operator_list_lite_for_onnx.md @@ -0,0 +1,100 @@ +# List of ONNX Operators Supported by MindSpore Lite + +[![View Source On Gitee](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source_en.svg)](https://gitee.com/mindspore/docs/blob/master/docs/lite/docs/source_en/reference/operator_list_lite_for_onnx.md) + +> - None of the following operators support int64 type input. +> - Currently, you can use the environment variable `export KEEP_ORIGIN_DTYPE=1` to preserve the data type as int64. Consider using this option when overflow occurs with the int32 data type. However, this is currently an experimental option and will be removed in future updates. + +| MindSpore Lite Operator Names | Operator Functions | Corresponding ONNX Operators | Operator Specifications | +| ---------------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | +| Abs | Element-wise calculate the absolute value | Abs | Does not support the uint8 type. Does not support empty input tensor quantization parameters. | +| Activation | Activation functions | Relu, LeakyRelu, PRelu, Elu, Tanh, Sigmoid, HardSigmoid, Softplus, Gelu | - | +| AddFusion | Element-wise addition computation | Add, Int8Add | - | +| AdderFusion | Element-wise addition computation | adder_f | - | +| ArgmaxFusion | Find the maximum value in a given dimension | ArgMax | Does not support the uint8 type. Does not support empty input tensor quantization parameters. | +| ArgminFusion | Find the minimum value in a given dimension | ArgMin | - | +| AvgPoolFusion | Average pooling | AveragePool, GlobalAveragePool, Int8AveragePool | - | +| BatchNorm | Batch normalization | BatchNormalization | - | +| BiasAdd | Add the bias vector to the input tensor | BiasAdd | - | +| BroadcastTo | Expansion of dimensions | Expand | - | +| Cast | Data type conversion | Cast | The following numeric type conversions are not supported: fp32 to int8, fp32 to uint32, int32 to int8, int32 to uint32, int32 to uint8, int8 to bool, and int8 to uint8. | +| Ceil | Round up to the nearest integer | Ceil | - | +| Clip | Restrict element ranges | Clip | Only supports converting clip(0, 6) to Relu6. | +| Concat | Concatenated Tensor | Concat | - | +| ConstantOfShape | Generate a tensor with the same shape as the input and fill it with the specified constant. | ConstantOfShape | - | +| Conv2DFusion | 2D convolution | Conv, Int8Conv, ConvRelu, Int8ConvRelu | - | +| Conv2dTransposeFusion | Perform transposed convolution operations | ConvTranspose | - | +| Cos | Element-wise cosine calculation | Cos | - | +| CumSum | Cumulative sum of elements | CumSum | - | +| DepthToSpace | Rearrange deep data into spatial dimensions | DepthToSpace | Does not support the uint8 type. Does not support inputs with unknown dimensions. | +| DivFusion | Element-wise division | Div | Does not support division by zero. | +| Dropout | Randomly set some elements of the input tensor to zero. | Dropout | - | +| DynamicQuant | Dynamically quantize floating-point tensors to uint8 type | DynamicQuantizeLinear | - | +| Eltwise | Element-level operations | Sum, Max | Only supports input counts of 2. | +| Elu | Activation function, applying exponential correction to negative inputs | Elu, NonMaxSuppression | - | +| Equal | Determine whether inputs are equal | Equal | Uint8 input is not supported; int8 input does not support bool output. | +| Erf | Error functions | Erf | - | +| ExpFusion | Element-wise exponentiation | Exp | - | +| Flatten | Data is expanded by dimension | Flatten | Does not support the uint8 type. | +| Floor | Round down to the nearest integer | Floor | - | +| FusedBatchNorm | Standardize the input | BatchNormalization | - | +| GatherNd | Collect elements from the input tensor at specified positions based on the index tensor. | GatherND | - | +| Gather | Collect elements at specified index positions along a single dimension | Gather | Does not support the uint8 type. Does not support the QuantType_QUANT_NONE quantization type. | +| GatherD | Collect elements from the input tensor based on the index tensor. | GatherElements | - | +| GatherNd | Aggregate slices of the input tensor into a new tensor with dimensions specified by indices. | GatherND | - | +| Greater | Perform element-wise comparison between two tensors, returning a logical result (True/False) indicating whether A > B. | Greater | - | +| GreaterEqual | Perform element-wise comparison between two tensors, returning a logical result indicating whether A ≥ B. | GreaterOrEqual | - | +| InstanceNorm | Instance normalization | InstanceNormalization | - | +| LeakyReLU | Leaky ReLU activation function, which assigns a small slope to negative inputs. | LeakyRelu | - | +| Less | Perform element-wise comparison between two tensors, returning a logical result indicating whether A < B. | Less | - | +| LRN | Local response normalization | Lrn, LRN | - | +| Log | Element-wise calculate the logarithm | Log | Does not accept negative numbers. | +| LogicalAnd | Element-wise logical AND operation | And | - | +| LogicalNot | Element-level logical NOT operation | Not | - | +| LogicalOr | Element-wise logical OR operation | Or | - | +| LogSoftmax | Perform a softmax operation on the input vector, then take the logarithm of the softmax result. | LogSoftmax | Does not support inf input. | +| LRN | Local response normalization to prevent data overfitting | LRN | - | +| LSTM | Long-term and short-term memory network Unit | LSTM | - | +| MatMulFusion | Perform matrix multiplication on two inputs; compute the inner product using the input tensors and a set of learned weights, and add a bias. | MatMul, Gemm | - | +| Maximum | Find the maximum value at the element level | Max | - | +| MaxPoolFusion | Maximum pooling | MaxPool, GlobalMaxPool | - | +| Minimum | Find the minimum value at the element level | Min | - | +| Mod | Return the remainder of the division operation | Mod | - | +| MulFusion | Element-wise multiplication | Mul | - | +| Neg | Element-wise find negative numbers | Neg | - | +| NonMaxSuppression | Non-maximum suppression | NonMaxSuppression | - | +| NonZero | Return the indices of all non-zero elements in the input tensor. | NonZero | - | +| OneHot | Convert integer index tensors to one-hot encoding representations | OneHot | - | +| PadFusion | Add specified padding to the input tensor, to achieve the desired size. | Pad | Does not support the int32 type. | +| PowFusion | Element-wise exponentiation | Pow | Only supports indices as single constants. | +| PReLUFusion | PRelu activation function | PRelu | - | +| RandomNormal | Generate a tensor whose values are randomly sampled from a normal distribution (Gaussian distribution). | RandomNormal | - | +| Range | Generate elements within a specified range | Range | - | +| Reciprocal | Return reciprocals | Reciprocal | - | +| ReduceFusion | Reduction operation | ReduceMean, ReduceMax, ReduceMin, ReduceProd, ReduceSum, ReduceSumSquare, ReduceL2, ReduceL1, ReduceLogSum | - | +| Reshape | Changing the shape of a tensor while keeping the total number of elements unchanged | Reshape, Flatten | - | +| Resize | Upsample or resize the input tensor | Resize, Upsample | - | +| ReverseSequence | Partially reverse the variable-length sequence of the input tensor. | ReverseSequence | - | +| Round | Round to the nearest whole number | Round | - | +| ScatterNd | Scatter values from the input tensor to specified positions in the output tensor based on the index. | ScatterND | - | +| ScatterNdUpdate | Update the value of the input data using the given value and the input index. | ScatterNdUpdate | - | +| Shape | Obtain the tensor shape | Shape | - | +| Sin | Element-wise calculation of sine | Sin | - | +| Size | Obtain tensor dimension size | Size | - | +| SliceFusion | Tensor slicing operation | Slice | - | +| Softmax | Normalization operation | Softmax | - | +| SpaceToDepth | Move the values of the height and width dimensions to the depth dimension. | SpaceToDepth | - | +| Splice | Connect multiple slices or ranges of the input tensor along the specified axis. | Splice | - | +| Split | Split the input tensor into multiple smaller output tensors along the specified axis. | Split | - | +| Sqrt | Element-wise take the square root | Sqrt | - | +| Squeeze | Remove dimension 1 | Squeeze | - | +| StridedSlice | Tensor slicing | Slice, DynamicSlice | - | +| SubFusion | Element-wise subtraction | Sub | - | +| TileFusion | Flatten the given matrix | Tile | Does not support the int8 type. | +| TopKFusion | Return the top K elements from the input tensor. | TopK | - | +| Transpose | Tensor transpose | Transpose, Int8Transpose | - | +| Tril | Lower triangular matrix | Trilu (attribute upper=0) | - | +| Triu | Upper triangular matrix | Trilu (attribute upper=1) | - | +| Unsqueeze | Add a new dimension to the input tensor | Unsqueeze | - | +| Where | Element selection | NonZero, Where | - | +| Other operators supported by the conversion tool | - | Constant, Atan, Asin, Tan, Loop, Dropout, If, Identity, Int8GivenIntTensorFill, Int8GivenTensorFill, Int8Quantize, Int8Dequantize, LpNormalization | Operators supported by conversion tools but not requiring specific implementation are typically optimized away during conversion—either fused or replaced by other operators. | diff --git a/docs/lite/docs/source_en/reference/operator_list_lite_for_tflite.md b/docs/lite/docs/source_en/reference/operator_list_lite_for_tflite.md new file mode 100644 index 0000000000..065e3f157f --- /dev/null +++ b/docs/lite/docs/source_en/reference/operator_list_lite_for_tflite.md @@ -0,0 +1,116 @@ +# List of TensorFlow Lite Operators Supported by MindSpore Lite + +[![View Source On Gitee](https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source_en.svg)](https://gitee.com/mindspore/docs/blob/master/docs/lite/docs/source_en/reference/operator_list_lite_for_tflite.md) + +| MindSpore Lite Operator Names | Corresponding TensorFlow Lite Operators | +| ---------------------- | ------------------------------------------------------------ | +| Abs | Abs | +| Activation | Activation, ReLU, ReLU6, PReLU,
LeakyReLU, Tanh, HardSwish, Logistic | +| Adam | Adam | +| AddFusion | Add | +| AddN | AddN | +| All | All | +| ApplyMomentum | ApplyMomentum | +| Assign | Assign | +| ArgmaxFusion | Argmax | +| ArgminFusion | Argmin | +| AvgPoolFusion | MeanPooling | +| BatchToSpace | BatchToSpace | +| BatchToSpaceND | BatchToSpaceND | +| BinaryCrossEntropy | BinaryCrossEntropy | +| BroadcastTo | BroadcastTo | +| Cast | Cast,
QUANTIZE,
DEQUANTIZE | +| Ceil | Ceil | +| Clip | Clip | +| Concat | Concat | +| Conv2DFusion | Conv2D | +| Conv2dTransposeFusion | DeConv2D | +| Cos | Cos | +| CustomExtractFeatures | ExtractFeatures | +| CustomNormalize | Normalize | +| CustomPredict | Predict | +| DepthToSpace | DepthToSpace | +| DetectionPostProcess | Custom | +| DivFusion | Div, RealDiv | +| Dropout | Dropout | +| Equal | Equal | +| Erf | Erf | +| ExpFusion | Exp | +| ExpandDims | ExpandDims | +| Fill | Fill | +| Floor | flOOR | +| FloorDiv | FloorDiv | +| FloorMod | FloorMod | +| FullConnection | FullyConnected | +| FusedBatchNorm | FusedBatchNorm | +| GatherNd | GatherND | +| Gather | Gather | +| Greater | Greater | +| GreaterEqual | GreaterEqual | +| HashtableLookup | HashtableLookup | +| InstanceNorm | InstanceNorm | +| IsFinite | IsFinite | +| LeakyReLU | LeakyRelu | +| Less | Less | +| LessEqual | LessEqual | +| LRN | LocalResponseNorm | +| Log | Log | +| Log1p | Log1p | +| LogicalAnd | LogicalAnd | +| LogicalNot | LogicalNot | +| LogicalOr | LogicalOr | +| LogSoftmax | LogSoftmax | +| LshProjection | LshProjection | +| MatMulFusion | BatchMatMul | +| Maximum | Maximum | +| MaxPoolFusion | MaxPooling | +| Minimum | Minimum | +| Mod | Mod | +| MulFusion | Mul | +| Neg | Neg | +| NotEqual | NotEqual | +| NonMaxSuppression | NonMaxSuppression | +| NonZero | NonZero | +| OneHot | OneHot | +| OnesLike | OnesLike | +| PadFusion | Pad, MirrorPad, PadV2 | +| PowFusion | Pow | +| PReLUFusion | PRELU | +| RandomNormal | RandomNormal | +| Range | Range | +| Rank | Rank | +| ReduceFusion | Sum, Mean, ReduceMax, ReduceMin, ReduceProd | +| Reshape | Reshape | +| Resize | ResizeBilinear,
NearestNeighbor | +| ReverseV2 | reverse | +| ReverseSequence | ReverseSequence | +| Round | Round | +| Rsqrt | Rsqrt | +| ScatterNd | ScatterNd | +| ScatterNdUpdate | ScatterNdUpdate | +| SGD | SGD | +| Shape | Shape | +| Sin | Sin | +| SliceFusion | Slice | +| SkipGram | SKipGram | +| Softmax | Softmax | +| SpaceToBatch | SpaceToBatch | +| SpaceToBatchND | SpaceToBatchND | +| SpaceToDepth | SpaceToDepth | +| SparseToDense | SpareToDense | +| Split | Split, SplitV | +| Sqrt | Sqrt | +| Square | Square | +| SquaredDifference | SquaredDifference | +| Squeeze | Squeeze | +| StridedSlice | StridedSlice | +| Stack | Stack | +| SubFusion | Sub | +| TensorScatterAdd | TensorScatterAdd | +| TileFusion | Tile | +| TopKFusion | TopKV2 | +| Transpose | Transpose | +| Unique | Unique | +| Unstack | Unstack | +| Where | Where | +| ZerosLike | ZerosLike | diff --git a/docs/lite/docs/source_en/reference/operator_lite.rst b/docs/lite/docs/source_en/reference/operator_lite.rst new file mode 100644 index 0000000000..d46e23a4c0 --- /dev/null +++ b/docs/lite/docs/source_en/reference/operator_lite.rst @@ -0,0 +1,15 @@ +Lite Operator Support +======================= + +.. image:: https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source_en.svg + :target: https://gitee.com/mindspore/docs/blob/master/docs/lite/docs/source_en/reference/operateor_list.rst + :alt: View Source On Gitee + +.. toctree:: + :maxdepth: 1 + + operator_list_lite + operator_list_lite_for_onnx + operator_list_lite_for_tflite + operator_list_lite_for_tensorflow + operator_list_lite_for_caffe \ No newline at end of file diff --git a/docs/lite/docs/source_zh_cn/reference/operator_list_lite.md b/docs/lite/docs/source_zh_cn/reference/operator_list_lite.md index a276d3a0d2..f3e50d415b 100644 --- a/docs/lite/docs/source_zh_cn/reference/operator_list_lite.md +++ b/docs/lite/docs/source_zh_cn/reference/operator_list_lite.md @@ -119,7 +119,7 @@ | NLLLoss | 计算负对数似然损失 | FP32 | - | - | | NLLLossGrad | 计算NLLLoss的梯度 | FP32 | - | - | | NotEqual | 逐元素比较两个张量，返回 A != B的逻辑结果 | FP16
FP32
Int32
Int8
UInt8 | FP16 | FP16
FP32 | -| NonMaxSupppression | 非极大值抑制 | FP32 | - | - | +| NonMaxSuppression | 非极大值抑制 | FP32 | - | - | | NonZero | 返回输入张量中所有非零元素的索引 | Bool | - | - | | OneHot | 将整数索引张量转换为独热编码表示 | FP16
FP32
Int32 | - | FP16
FP32
Int32 | | OnesLike | 创建一个与输入张量 X形状完全相同但所有元素值均为1的新张量 | FP16
FP32
Int32 | - | - | diff --git a/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_onnx.md b/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_onnx.md index 2ec2250b7a..bd85b16e3a 100644 --- a/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_onnx.md +++ b/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_onnx.md @@ -8,12 +8,12 @@ | MindSpore Lite算子名称 | 算子功能 | 对应ONNX算子名称 | 算子规格 | | ---------------------- | ------------------------------------------------------------ | ------------------------------------------------------------ | ------------------------------------------------------------ | | Abs | 逐元素计算绝对值 | Abs | 不支持uint8类型。不支持输入张量量化参数为空。 | -| Activation | 激活函数 | Relu, LeakyRelu, PRelu, Elu, Tanh, Sigmoid, HardSigmoid, Softplus,Gelu | - | -| AddFusion | 逐元素计算加法 | Add, Int8Add | - | +| Activation | 激活函数 | Relu、LeakyRelu、PRelu、Elu、Tanh、Sigmoid、HardSigmoid、Softplus、Gelu | - | +| AddFusion | 逐元素计算加法 | Add、Int8Add | - | | AdderFusion | 逐元素加法 | adder_f | - | | ArgmaxFusion | 求某一维度最大值 | ArgMax | 不支持uint8类型。不支持输入张量量化参数为空。 | | ArgminFusion | 求某一维度最小值 | ArgMin | - | -| AvgPoolFusion | 平均池化 | AveragePool, GlobalAveragePool, Int8AveragePool | - | +| AvgPoolFusion | 平均池化 | AveragePool、GlobalAveragePool、Int8AveragePool | - | | BatchNorm | 批量归一化 | BatchNormalization | - | | BiasAdd | 将偏置向量（bias）添加到输入张量 | BiasAdd | - | | BroadcastTo | 扩维 | Expand | - | @@ -22,7 +22,7 @@ | Clip | 限制元素范围 | Clip | 仅支持将clip(0, 6)转换为Relu6。 | | Concat | 拼接张量 | Concat | - | | ConstantOfShape | 生成一个与输入形状相同的张量，并用指定常量填充 | ConstantOfShape | - | -| Conv2DFusion | 2D卷积 | Conv, Int8Conv, ConvRelu, Int8ConvRelu | - | +| Conv2DFusion | 2D卷积 | Conv、Int8Conv、ConvRelu、Int8ConvRelu | - | | Conv2dTransposeFusion | 执行转置卷积运算 | ConvTranspose | - | | Cos | 逐元素计算余弦 | Cos | - | | CumSum | 累计元素和 | CumSum | - | @@ -30,8 +30,8 @@ | DivFusion | 逐元素除法 | Div | 不支持除数为0。 | | Dropout | 随机将输入张量的部分元素置 0 | Dropout | - | | DynamicQuant | 动态将浮点张量量化为 uint8类型 | DynamicQuantizeLinear | - | -| Eltwise | 元素级运算 | Sum, Max | 仅支持输入个数为2。 | -| Elu | 激活函数，对负输入使用指数修正 | Elu, NonMaxSuppression | - | +| Eltwise | 元素级运算 | Sum、Max | 仅支持输入个数为2。 | +| Elu | 激活函数，对负输入使用指数修正 | Elu、NonMaxSuppression | - | | Equal | 判断输入是否相等 | Equal | 不支持uint8输入；int8输入不支持bool输出。 | | Erf | 误差函数 | Erf | - | | ExpFusion | 逐元素取指数 | Exp | - | @@ -47,33 +47,33 @@ | InstanceNorm | 实例归一化 | InstanceNormalization | - | | LeakyReLU | 带泄漏的 ReLU激活函数，对负输入给予微小斜率 | LeakyRelu | - | | Less | 逐元素比较两个张量，返回 A < B的逻辑结果。 | Less | - | -| LRN | 局部响应归一化 | Lrn, LRN | - | +| LRN | 局部响应归一化 | Lrn、LRN | - | | Log | 逐元素求对数 | Log | 不支持负数输入。 | | LogicalAnd | 逐元素逻辑与（AND）运算 | And | - | -| LogicalNot | 元素级逻辑非 | Not | - | +| LogicalNot | 元素级逻辑非运算 | Not | - | | LogicalOr | 逐元素逻辑或（OR）运算 | Or | - | | LogSoftmax | 对输入向量进行softmax操作，然后再对softmax结果取对数 | LogSoftmax | 不支持inf输入。 | | LRN | 局部响应标准化，用于防止数据过度拟合 | LRN | - | | LSTM | 长短期记忆网络单元 | LSTM | - | -| MatMulFusion | 对2个输入做矩阵乘法运算；使用输入张量、一组学习的权重计算内积，并添加偏差 | MatMul, Gemm | - | +| MatMulFusion | 对2个输入做矩阵乘法运算；使用输入张量、一组学习的权重计算内积，并添加偏差 | MatMul、Gemm | - | | Maximum | 取元素级最大值 | Max | - | -| MaxPoolFusion | 最大池化 | MaxPool, GlobalMaxPool | - | +| MaxPoolFusion | 最大池化 | MaxPool、GlobalMaxPool | - | | Minimum | 取元素级最小值 | Min | - | | Mod | 返回除法元素的余数 | Mod | - | | MulFusion | 逐元素乘法 | Mul | - | | Neg | 逐元素求负数 | Neg | - | -| NonMaxSupppression | 非极大值抑制 | NonMaxSupppression | - | +| NonMaxSuppression | 非极大值抑制 | NonMaxSuppression | - | | NonZero | 返回输入张量中所有非零元素的索引 | NonZero | - | | OneHot | 将整数索引张量转换为独热编码（One-Hot）表示 | OneHot | - | | PadFusion | 将输入张量加上指定的 padding，使其达到指定的大小 | Pad | 不支持int32类型。 | | PowFusion | 逐元素求幂 | Pow | 仅支持指数为单个常数。 | | PReLUFusion | PRelu激活函数 | PRelu | - | -| RandomNormal | 生成一个张量，其中的值从正态分布（高斯分布） 中随机采样 | RandomNormal | - | +| RandomNormal | 生成一个张量，其中的值从正态分布（高斯分布）中随机采样 | RandomNormal | - | | Range | 生成某个区间内的元素 | Range | - | | Reciprocal | 返回倒数 | Reciprocal | - | -| ReduceFusion | 归约操作 | ReduceMean, ReduceMax, ReduceMin, ReduceProd, ReduceSum, ReduceSumSquare, ReduceL2,ReduceL1,ReduceLogSum | - | -| Reshape | 改变张量形状，总元素个数不变 | Reshape, Flatten | - | -| Resize | 对输入张量进行上采样或调整大小 | Resize, Upsample | - | +| ReduceFusion | 归约操作 | ReduceMean、ReduceMax、ReduceMin、ReduceProd、ReduceSum、ReduceSumSquare、ReduceL2,ReduceL1、ReduceLogSum | - | +| Reshape | 改变张量形状，总元素个数不变 | Reshape、Flatten | - | +| Resize | 对输入张量进行上采样或调整大小 | Resize、Upsample | - | | ReverseSequence | 对输入张量的可变长度序列进行部分反转 | ReverseSequence | - | | Round | 四舍五入到最接近的整数数值 | Round | - | | ScatterNd | 根据索引将更新张量中的值散射到输出张量的指定位置 | ScatterND | - | @@ -88,13 +88,13 @@ | Split | 将输入张量沿指定轴分割成多个较小的输出张量。 | Split | - | | Sqrt | 逐元素开根号 | Sqrt | - | | Squeeze | 移除维度为1的维度 | Squeeze | - | -| StridedSlice | Tensor切片 | Slice, DynamicSlice | - | +| StridedSlice | Tensor切片 | Slice、DynamicSlice | - | | SubFusion | 逐元素相减 | Sub | - | | TileFusion | 平铺给定矩阵 | Tile | 不支持int8类型。 | | TopKFusion | 从输入张量中返回top K个元素 | TopK | - | -| Transpose | Tensor转置 | Transpose, Int8Transpose | - | +| Transpose | Tensor转置 | Transpose、Int8Transpose | - | | Tril | 下三角矩阵 | Trilu（属性upper=0） | - | | Triu | 上三角矩阵 | Trilu（属性upper=1） | - | | Unsqueeze | 将输入张量添加一个新的维度 | Unsqueeze | - | -| Where | 元素选择 | NonZero, Where | - | -| 转换工具支持的其他算子 | - | Constant, Atan, Asin, Tan, Loop, Dropout, If, Identity, Int8GivenIntTensorFill, Int8GivenTensorFill, Int8Quantize, Int8Dequantize, LpNormalization | 转换工具支持，但不需要具体实现的算子，一般这类算子在转化工具中被优化而消失，如被融合掉或者使用其他算子代替。 | +| Where | 元素选择 | NonZero、Where | - | +| 转换工具支持的其他算子 | - | Constant、Atan、Asin、Tan、Loop、Dropout、If、Identity、Int8GivenIntTensorFill、Int8GivenTensorFill、Int8Quantize、Int8Dequantize、LpNormalization | 转换工具支持，但不需要具体实现的算子，一般这类算子在转化工具中被优化而消失，如被融合掉或者使用其他算子代替。 | diff --git a/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_tensorflow.md b/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_tensorflow.md index 719ddd10e7..ad5a7ad4ea 100644 --- a/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_tensorflow.md +++ b/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_tensorflow.md @@ -65,7 +65,7 @@ | MulFusion | Mul | | Neg | Neg | | NotEqual | NotEqual | -| NonMaxSupppression | NonMaxSupppression | +| NonMaxSuppression | NonMaxSuppression | | NonZero | NonZero | | OneHot | OneHot | | OnesLike | OnesLike | diff --git a/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_tflite.md b/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_tflite.md index a5a2b429b2..40913e5466 100644 --- a/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_tflite.md +++ b/docs/lite/docs/source_zh_cn/reference/operator_list_lite_for_tflite.md @@ -69,7 +69,7 @@ | MulFusion | Mul | | Neg | Neg | | NotEqual | NotEqual | -| NonMaxSupppression | NonMaxSupppression | +| NonMaxSuppression | NonMaxSuppression | | NonZero | NonZero | | OneHot | OneHot | | OnesLike | OnesLike | diff --git a/docs/lite/docs/source_zh_cn/reference/operator_lite.rst b/docs/lite/docs/source_zh_cn/reference/operator_lite.rst index ca4fcd1c46..4e1156c23c 100644 --- a/docs/lite/docs/source_zh_cn/reference/operator_lite.rst +++ b/docs/lite/docs/source_zh_cn/reference/operator_lite.rst @@ -2,7 +2,7 @@ Lite算子支持 =================== .. image:: https://mindspore-website.obs.cn-north-4.myhuaweicloud.com/website-images/master/resource/_static/logo_source.svg - :target: https://gitee.com/mindspore/docs/blob/master/docs/lite/docs/source_zh_cn/reference/operateor_list.rst + :target: https://gitee.com/mindspore/docs/blob/master/docs/lite/docs/source_zh_cn/reference/operator_list.rst :alt: 查看源文件 .. toctree:: -- Gitee