Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
MindSpore
docs
提交
082e9fda
D
docs
项目概览
MindSpore
/
docs
通知
4
Star
2
Fork
2
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
D
docs
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
提交
082e9fda
编写于
8月 28, 2020
作者:
L
lyvette
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update lit op lists
上级
ed7b6718
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
206 addition
and
232 deletion
+206
-232
lite/docs/source_en/operator_list.md
lite/docs/source_en/operator_list.md
+102
-115
lite/docs/source_zh_cn/operator_list.md
lite/docs/source_zh_cn/operator_list.md
+104
-117
未找到文件。
lite/docs/source_en/operator_list.md
浏览文件 @
082e9fda
...
...
@@ -4,121 +4,108 @@
> √ The checked items are the operators supported by MindSpore Lite。
| Operation | CPU
<br/>
FP16 | CPU
<br/>
FP32 | CPU
<br/>
Int8 | CPU
<br/>
UInt8 | GPU
<br/>
FP16 | GPU
<br/>
FP32 | Operator category | Tensorflow
<br/>
Lite op supported | Caffe
<br/>
Lite op supported | Onnx
<br/>
Lite op supported |
|-----------------------|----------|----------|----------|-----------|----------|----------|------------------|----------|----------|----------|
| Abs | | √ | √ | √ | | | math_ops | Abs | | Abs |
| Add | | | | | | √ | | Add | | Add |
| AddN | | √ | | | | | math_ops | AddN | | |
| Argmax | | √ | √ | √ | | | array_ops | Argmax | ArgMax | ArgMax |
| Argmin | | √ | | | | | array_ops | Argmin | | |
| Asin | | | | | | | | | | Asin |
| Atan | | | | | | | | | | Atan |
| AvgPool | | √ | √ | √ | | √ | nn_ops | MeanPooling | Pooling | AveragePool |
| BatchMatMul | √ | √ | √ | √ | | | math_ops | | | |
| BatchNorm | | √ | | | | √ | nn_ops | | BatchNorm | BatchNormalization |
| BatchToSpace | | | | | | | array_ops | BatchToSpace, BatchToSpaceND | | |
| BatchToSpaceND | | | | | | | | | | |
| BiasAdd | | √ | | √ | | √ | nn_ops | | | BiasAdd |
| Broadcast | | √ | | | | | comm_ops | BroadcastTo | | Expand |
| Cast | | √ | | | | | array_ops | Cast, DEQUANTIZE
*
| | Cast |
| Ceil | | √ | | √ | | | math_ops | Ceil | | Ceil |
| Concat | | √ | √ | √ | | √ | array_ops | Concat | Concat | Concat |
| Constant | | | | | | | | | | Constant |
| Conv1dTranspose | | | | √ | | | layer/conv | | | |
| Conv2d | √ | √ | √ | √ | | √ | layer/conv | Conv2D | Convolution | Conv |
| Conv2dTranspose | | √ | √ | √ | | √ | layer/conv | DeConv2D | Deconvolution | ConvTranspose |
| Cos | | √ | √ | √ | | | math_ops | Cos | | Cos |
| Crop | | | | | | | | | Crop | |
| DeDepthwiseConv2D | | | | | | | | | Deconvolution| ConvTranspose |
| DepthToSpace | | | | | | | | DepthToSpace | | DepthToSpace |
| DepthwiseConv2dNative | √ | √ | √ | √ | | √ | nn_ops | DepthwiseConv2D | Convolution | Convolution |
| Div | | √ | √ | √ | | √ | math_ops | Div | | Div |
| Dropout | | | | | | | | | | Dropout |
| Eltwise | | | | | | | | | Eltwise | |
| Elu | | | | | | | | Elu | | Elu |
| Equal | | √ | √ | √ | | | math_ops | Equal | | Equal |
| Exp | | √ | | | | | math_ops | Exp | | Exp |
| ExpandDims | | √ | | | | | array_ops | | | |
| Fill | | √ | | | | | array_ops | Fill | | |
| Flatten | | | | | | | | | Flatten | |
| Floor | | √ | √ | √ | | | math_ops | flOOR | | Floor |
| FloorDiv | | √ | | | | | math_ops | FloorDiv | | |
| FloorMod | | √ | | | | | nn_ops | FloorMod | | |
| FullConnection | | √ | | | | | layer/basic | FullyConnected | InnerProduct | |
| GatherNd | | √ | | | | | array_ops | GatherND | | |
| GatherV2 | | √ | | | | | array_ops | Gather | | Gather |
| Greater | | √ | √ | √ | | | math_ops | Greater | | Greater |
| GreaterEqual | | √ | √ | √ | | | math_ops | GreaterEqual | | |
| Hswish | | | | | | | | HardSwish | | |
| L2norm | | | | | | | | L2_NORMALIZATION | | |
| LeakyReLU | | √ | | | | √ | layer/activation | LeakyRelu | | LeakyRelu |
| Less | | √ | √ | √ | | | math_ops | Less | | Less |
| LessEqual | | √ | √ | √ | | | math_ops | LessEqual | | |
| LocalResponseNorm | | | | | | | | LocalResponseNorm | | Lrn |
| Log | | √ | √ | √ | | | math_ops | Log | | Log |
| LogicalAnd | | √ | | | | | math_ops | LogicalAnd | | |
| LogicalNot | | √ | √ | √ | | | math_ops | LogicalNot | | |
| LogicalOr | | √ | | | | | math_ops | LogicalOr | | |
| LSTM | | √ | | | | | layer/lstm | | | |
| MatMul | √ | √ | √ | √ | | √ | math_ops | | | MatMul |
| Maximum | | | | | | | math_ops | Maximum | | Max |
| MaxPool | | √ | √ | √ | | √ | nn_ops | MaxPooling | Pooling | MaxPool |
| Minimum | | | | | | | math_ops | Minimum | | Min |
| Mul | | √ | √ | √ | | √ | math_ops | Mul | | Mul |
| Neg | | | | | | | math_ops | | | Neg |
| NotEqual | | √ | √ | √ | | | math_ops | NotEqual | | |
| OneHot | | √ | | | | | layer/basic | OneHot | | |
| Pack | | √ | | | | | nn_ops | | | |
| Pad | | √ | √ | √ | | | nn_ops | Pad | | Pad |
| Pow | | √ | √ | √ | | | math_ops | Pow | Power | Power |
| PReLU | | √ | √ | √ | | √ | layer/activation | Prelu | PReLU | PRelu |
| Range | | √ | | | | | layer/basic | Range | | |
| Rank | | √ | | | | | array_ops | Rank | | |
| RealDiv | | √ | √ | √ | | √ | math_ops | RealDiv | | |
| ReduceMax | | √ | √ | √ | | | math_ops | ReduceMax | | ReduceMax |
| ReduceMean | | √ | √ | √ | | | math_ops | Mean | | ReduceMean |
| ReduceMin | | √ | √ | √ | | | math_ops | ReduceMin | | ReduceMin |
| ReduceProd | | √ | √ | √ | | | math_ops | ReduceProd | | |
| ReduceSum | | √ | √ | √ | | | math_ops | Sum | | ReduceSum |
| ReLU | | √ | √ | √ | | √ | layer/activation | Relu | ReLU | Relu |
| ReLU6 | | √ | | | | √ | layer/activation | Relu6 | ReLU6 | Clip
*
|
| Reshape | | √ | √ | √ | | √ | array_ops | Reshape | Reshape | Reshape,Flatten |
| Resize | | | | | | | | ResizeBilinear, NearestNeighbor | Interp | |
| Reverse | | | | | | | | reverse | | |
| ReverseSequence | | √ | | | | | array_ops | ReverseSequence | | |
| Round | | √ | | √ | | | math_ops | Round | | |
| Rsqrt | | √ | √ | √ | | | math_ops | Rsqrt | | |
| Scale | | | | | | | | | Scale | |
| ScatterNd | | √ | | | | | array_ops | ScatterNd | | |
| Shape | | √ | | √ | | | array_ops | Shape | | Shape |
| Sigmoid | | √ | √ | √ | | √ | nn_ops | Logistic | Sigmoid | Sigmoid |
| Sin | | | | | | | | Sin | | Sin |
| Slice | | √ | √ | √ | | √ | array_ops | Slice | | Slice |
| Softmax | | √ | √ | √ | | √ | layer/activation | Softmax | Softmax | Softmax |
| SpaceToBatchND | | √ | | | | | array_ops | SpaceToBatchND | | |
| SpareToDense | | | | | | | | SpareToDense | | |
| SpaceToDepth | | √ | | | | | array_ops | SpaceToDepth | | SpaceToDepth |
| Split | | √ | √ | √ | | | array_ops | Split, SplitV | | |
| Sqrt | | √ | √ | √ | | | math_ops | Sqrt | | Sqrt |
| Square | | √ | √ | √ | | | math_ops | Square | | |
| SquaredDifference | | | | | | | | SquaredDifference | | |
| Squeeze | | √ | √ | √ | | | array_ops | Squeeze | | Squeeze |
| StridedSlice | | √ | √ | √ | | | array_ops | StridedSlice | | |
| Stack | | | | | | | | Stack | | |
| Sub | | √ | √ | √ | | √ | math_ops | Sub | | Sub |
| Tan | | | | | | | | | | Tan |
| Tanh | | √ | | | | | layer/activation | Tanh | TanH | |
| TensorAdd | | √ | √ | √ | | √ | math_ops | | | |
| Tile | | √ | | | | | array_ops | Tile | | Tile |
| TopK | | √ | √ | √ | | | nn_ops | TopKV2 | | |
| Transpose | | √ | √ | √ | | √ | array_ops | Transpose | Permute | Transpose |
| Unique | | | | | | | | Unique | | |
| Unpack | | √ | | | | | nn_ops | | | |
| Unsample | | | | | | | | | | Unsample |
| Unsqueeze | | | | | | | | | | Unsqueeze |
| Unstack | | | | | | | | Unstack | | |
| Where | | | | | | | | Where | | |
| ZerosLike | | √ | | | | | array_ops | ZerosLike | | |
| Operation | CPU
<br/>
FP16 | CPU
<br/>
FP32 | CPU
<br/>
Int8 | CPU
<br/>
UInt8 | GPU
<br/>
FP16 | GPU
<br/>
FP32 | Tensorflow
<br/>
Lite op supported | Caffe
<br/>
Lite op supported | Onnx
<br/>
Lite op supported |
|-----------------------|----------|----------|-----------|----------|----------|------------------|----------|----------|----------|
| Abs | | √ | √ | √ | | | Abs | | Abs |
| Add | √ | √ | √ | √ | | √ | Add | | Add |
| AddN | | √ | | | | | AddN | | |
| Argmax | | √ | √ | √ | | | Argmax | ArgMax | ArgMax |
| Argmin | | √ | √ | √ | | | Argmin | | |
| AvgPool | √ | √ | √ | √ | | √ | MeanPooling| Pooling | AveragePool |
| BatchNorm | √ | √ | √ | √ | | √ | | BatchNorm | BatchNormalization |
| BatchToSpace | | √ | √ | √ | | | BatchToSpace, BatchToSpaceND | | |
| BiasAdd | | √ | √ | √ | | √ | | | BiasAdd |
| Broadcast | | √ | | | | | BroadcastTo | | Expand |
| Cast | √ | √ | | √ | | | Cast, DEQUANTIZE
*
| | Cast |
| Ceil | | √ | √ | √ | | | Ceil | | Ceil |
| Concat | √ | √ | √ | √ | | √ | Concat | Concat | Concat |
| Conv2d | √ | √ | √ | √ | | √ | Conv2D | Convolution | Conv |
| Conv2dTranspose | √ | √ | √ | √ | | √ | DeConv2D | Deconvolution | ConvTranspose |
| Cos | | √ | √ | √ | | | Cos | | Cos |
| Crop | | √ | √ | √ | | | | Crop | |
| DeDepthwiseConv2D | | √ | √ | √ | | | | Deconvolution| ConvTranspose |
| DepthToSpace | | √ | √ | √ | | | DepthToSpace| | DepthToSpace |
| DepthwiseConv2dNative | √ | √ | √ | √ | | √ | DepthwiseConv2D | Convolution | Convolution |
| Div | √ | √ | √ | √ | | √ | Div, RealDiv | | Div |
| Eltwise | √ | √ | | | | | | Eltwise | |
| Elu | | √ | | | | | Elu | | Elu |
| Equal | √ | √ | √ | √ | | | Equal | | Equal |
| Exp | | √ | | | | | Exp | | Exp |
| ExpandDims | | √ | | | | | | | |
| Fill | | √ | | | | | Fill | | |
| Flatten | | √ | | | | | | Flatten | |
| Floor | | √ | √ | √ | | | flOOR | | Floor |
| FloorDiv | √ | √ | | | | | FloorDiv | | |
| FloorMod | √ | √ | | | | | FloorMod | | |
| FullConnection | | √ | √ | √ | | | FullyConnected | InnerProduct | |
| GatherNd | | √ | √ | √ | | | GatherND | | |
| GatherV2 | | √ | √ | √ | | | Gather | | Gather |
| Greater | √ | √ | √ | √ | | | Greater | | Greater |
| GreaterEqual | √ | √ | √ | √ | | | GreaterEqual| | |
| Hswish | √ | √ | √ | √ | | | HardSwish | | |
| LeakyReLU | √ | √ | | | | √ | LeakyRelu | | LeakyRelu |
| Less | √ | √ | √ | √ | | | Less | | Less |
| LessEqual | √ | √ | √ | √ | | | LessEqual | | |
| LRN | | √ | | | | | LocalResponseNorm | | Lrn |
| Log | | √ | √ | √ | | | Log | | Log |
| LogicalAnd | √ | √ | | | | | LogicalAnd | | |
| LogicalNot | | √ | √ | √ | | | LogicalNot | | |
| LogicalOr | √ | √ | | | | | LogicalOr | | |
| LSTM | | √ | | | | | | | |
| MatMul | | √ | √ | √ | | √ | | | MatMul |
| Maximum | √ | √ | | | | | Maximum | | Max |
| MaxPool | √ | √ | √ | √ | | √ | MaxPooling | Pooling | MaxPool |
| Minimum | √ | √ | | | | | Minimum | | Min |
| Mul | √ | √ | √ | √ | | √ | Mul | | Mul |
| NotEqual | √ | √ | √ | √ | | | NotEqual | | |
| OneHot | | √ | | | | | OneHot | | |
| Pad | | √ | √ | √ | | | Pad | | Pad |
| Pow | | √ | √ | √ | | | Pow | Power | Power |
| PReLU | | √ | | | | √ | Prelu | PReLU | PRelu |
| Range | | √ | | | | | Range | | |
| Rank | | √ | | | | | Rank | | |
| ReduceMax | √ | √ | √ | √ | | | ReduceMax | | ReduceMax |
| ReduceMean | √ | √ | √ | √ | | | Mean | | ReduceMean |
| ReduceMin | √ | √ | √ | √ | | | ReduceMin | | ReduceMin |
| ReduceProd | √ | √ | √ | √ | | | ReduceProd | | |
| ReduceSum | √ | √ | √ | √ | | | Sum | | ReduceSum |
| ReduceSumSquare | √ | √ | √ | √ | | | | | |
| ReLU | √ | √ | √ | √ | | √ | Relu | ReLU | Relu |
| ReLU6 | √ | √ | √ | √ | | √ | Relu6 | ReLU6 | Clip
*
|
| Reshape | √ | √ | √ | √ | | √ | Reshape | Reshape | Reshape,Flatten |
| Resize | | √ | √ | √ | | | ResizeBilinear, NearestNeighbor | Interp | |
| Reverse | | √ | | | | | reverse | | |
| ReverseSequence | | √ | | | | | ReverseSequence | | |
| Round | | √ | √ | √ | | | Round | | |
| Rsqrt | | √ | √ | √ | | | Rsqrt | | |
| Scale | | √ | | | | | | Scale | |
| ScatterNd | | √ | | | | | ScatterNd | | |
| Shape | | √ | | | | | Shape | | Shape |
| Sigmoid | √ | √ | √ | √ | | √ | Logistic | Sigmoid | Sigmoid |
| Sin | | √ | √ | √ | | | Sin | | Sin |
| Slice | | √ | √ | √ | | √ | Slice | | Slice |
| Softmax | √ | √ | √ | √ | | √ | Softmax | Softmax | Softmax |
| SpaceToBatch | | √ | | | | | | | |
| SpaceToBatchND | | √ | | | | | SpaceToBatchND | | |
| SpaceToDepth | | √ | | | | | SpaceToDepth | | SpaceToDepth |
| SparseToDense | | √ | | | | | SpareToDense | | |
| Split | √ | √ | √ | √ | | | Split, SplitV | | |
| Sqrt | | √ | √ | √ | | | Sqrt | | Sqrt |
| Square | | √ | √ | √ | | | Square | | |
| SquaredDifference | | √ | | | | | SquaredDifference | | |
| Squeeze | | √ | √ | √ | | | Squeeze | | Squeeze |
| StridedSlice | | √ | √ | √ | | | StridedSlice| | |
| Stack | | √ | | | | | Stack | | |
| Sub | √ | √ | √ | √ | | √ | Sub | | Sub |
| Tanh | √ | √ | | | | | Tanh | TanH | |
| Tile | | √ | | | | | Tile | | Tile |
| TopK | | √ | √ | √ | | | TopKV2 | | |
| Transpose | √ | √ | | | | √ | Transpose | Permute | Transpose |
| Unique | | √ | | | | | Unique | | |
| Unsqueeze | | √ | √ | √ | | | | | Unsqueeze |
| Unstack | | √ | | | | | Unstack | | |
| Where | | √ | | | | | Where | | |
| ZerosLike | | √ | | | | | ZerosLike | | |
*
Clip: only support convert clip(0, 6) to Relu6.
*
DEQUANTIZE: only support to convert fp16 to fp32.
lite/docs/source_zh_cn/operator_list.md
浏览文件 @
082e9fda
...
...
@@ -4,121 +4,108 @@
> √勾选的项为MindSpore Lite所支持的算子。
| 操作名 | CPU
<br/>
FP16 | CPU
<br/>
FP32 | CPU
<br/>
Int8 | CPU
<br/>
UInt8 | GPU
<br/>
FP16 | GPU
<br/>
FP32 | 算子类别 | 支持的Tensorflow
<br/>
Lite op | 支持的Caffe
<br/>
Lite op | 支持的Onnx
<br/>
Lite op |
|-----------------------|----------|----------|----------|-----------|----------|----------|------------------|----------|----------|----------|
| Abs | | √ | √ | √ | | | math_ops | Abs | | Abs |
| Add | | | | | | √ | | Add | | Add |
| AddN | | √ | | | | | math_ops | AddN | | |
| Argmax | | √ | √ | √ | | | array_ops | Argmax | ArgMax | ArgMax |
| Argmin | | √ | | | | | array_ops | Argmin | | |
| Asin | | | | | | | | | | Asin |
| Atan | | | | | | | | | | Atan |
| AvgPool | | √ | √ | √ | | √ | nn_ops | MeanPooling | Pooling | AveragePool |
| BatchMatMul | √ | √ | √ | √ | | | math_ops | | | |
| BatchNorm | | √ | | | | √ | nn_ops | | BatchNorm | BatchNormalization |
| BatchToSpace | | | | | | | array_ops | BatchToSpace, BatchToSpaceND | | |
| BatchToSpaceND | | | | | | | | | | |
| BiasAdd | | √ | | √ | | √ | nn_ops | | | BiasAdd |
| Broadcast | | √ | | | | | comm_ops | BroadcastTo | | Expand |
| Cast | | √ | | | | | array_ops | Cast, DEQUANTIZE
*
| | Cast |
| Ceil | | √ | | √ | | | math_ops | Ceil | | Ceil |
| Concat | | √ | √ | √ | | √ | array_ops | Concat | Concat | Concat |
| Constant | | | | | | | | | | Constant |
| Conv1dTranspose | | | | √ | | | layer/conv | | | |
| Conv2d | √ | √ | √ | √ | | √ | layer/conv | Conv2D | Convolution | Conv |
| Conv2dTranspose | | √ | √ | √ | | √ | layer/conv | DeConv2D | Deconvolution | ConvTranspose |
| Cos | | √ | √ | √ | | | math_ops | Cos | | Cos |
| Crop | | | | | | | | | Crop | |
| DeDepthwiseConv2D | | | | | | | | | Deconvolution| ConvTranspose |
| DepthToSpace | | | | | | | | DepthToSpace | | DepthToSpace |
| DepthwiseConv2dNative | √ | √ | √ | √ | | √ | nn_ops | DepthwiseConv2D | Convolution | Convolution |
| Div | | √ | √ | √ | | √ | math_ops | Div | | Div |
| Dropout | | | | | | | | | | Dropout |
| Eltwise | | | | | | | | | Eltwise | |
| Elu | | | | | | | | Elu | | Elu |
| Equal | | √ | √ | √ | | | math_ops | Equal | | Equal |
| Exp | | √ | | | | | math_ops | Exp | | Exp |
| ExpandDims | | √ | | | | | array_ops | | | |
| Fill | | √ | | | | | array_ops | Fill | | |
| Flatten | | | | | | | | | Flatten | |
| Floor | | √ | √ | √ | | | math_ops | flOOR | | Floor |
| FloorDiv | | √ | | | | | math_ops | FloorDiv | | |
| FloorMod | | √ | | | | | nn_ops | FloorMod | | |
| FullConnection | | √ | | | | | layer/basic | FullyConnected | InnerProduct | |
| GatherNd | | √ | | | | | array_ops | GatherND | | |
| GatherV2 | | √ | | | | | array_ops | Gather | | Gather |
| Greater | | √ | √ | √ | | | math_ops | Greater | | Greater |
| GreaterEqual | | √ | √ | √ | | | math_ops | GreaterEqual | | |
| Hswish | | | | | | | | HardSwish | | |
| L2norm | | | | | | | | L2_NORMALIZATION | | |
| LeakyReLU | | √ | | | | √ | layer/activation | LeakyRelu | | LeakyRelu |
| Less | | √ | √ | √ | | | math_ops | Less | | Less |
| LessEqual | | √ | √ | √ | | | math_ops | LessEqual | | |
| LocalResponseNorm | | | | | | | | LocalResponseNorm | | Lrn |
| Log | | √ | √ | √ | | | math_ops | Log | | Log |
| LogicalAnd | | √ | | | | | math_ops | LogicalAnd | | |
| LogicalNot | | √ | √ | √ | | | math_ops | LogicalNot | | |
| LogicalOr | | √ | | | | | math_ops | LogicalOr | | |
| LSTM | | √ | | | | | layer/lstm | | | |
| MatMul | √ | √ | √ | √ | | √ | math_ops | | | MatMul |
| Maximum | | | | | | | math_ops | Maximum | | Max |
| MaxPool | | √ | √ | √ | | √ | nn_ops | MaxPooling | Pooling | MaxPool |
| Minimum | | | | | | | math_ops | Minimum | | Min |
| Mul | | √ | √ | √ | | √ | math_ops | Mul | | Mul |
| Neg | | | | | | | math_ops | | | Neg |
| NotEqual | | √ | √ | √ | | | math_ops | NotEqual | | |
| OneHot | | √ | | | | | layer/basic | OneHot | | |
| Pack | | √ | | | | | nn_ops | | | |
| Pad | | √ | √ | √ | | | nn_ops | Pad | | Pad |
| Pow | | √ | √ | √ | | | math_ops | Pow | Power | Power |
| PReLU | | √ | √ | √ | | √ | layer/activation | Prelu | PReLU | PRelu |
| Range | | √ | | | | | layer/basic | Range | | |
| Rank | | √ | | | | | array_ops | Rank | | |
| RealDiv | | √ | √ | √ | | √ | math_ops | RealDiv | | |
| ReduceMax | | √ | √ | √ | | | math_ops | ReduceMax | | ReduceMax |
| ReduceMean | | √ | √ | √ | | | math_ops | Mean | | ReduceMean |
| ReduceMin | | √ | √ | √ | | | math_ops | ReduceMin | | ReduceMin |
| ReduceProd | | √ | √ | √ | | | math_ops | ReduceProd | | |
| ReduceSum | | √ | √ | √ | | | math_ops | Sum | | ReduceSum |
| ReLU | | √ | √ | √ | | √ | layer/activation | Relu | ReLU | Relu |
| ReLU6 | | √ | | | | √ | layer/activation | Relu6 | ReLU6 | Clip
*
|
| Reshape | | √ | √ | √ | | √ | array_ops | Reshape | Reshape | Reshape,Flatten |
| Resize | | | | | | | | ResizeBilinear, NearestNeighbor | Interp | |
| Reverse | | | | | | | | reverse | | |
| ReverseSequence | | √ | | | | | array_ops | ReverseSequence | | |
| Round | | √ | | √ | | | math_ops | Round | | |
| Rsqrt | | √ | √ | √ | | | math_ops | Rsqrt | | |
| Scale | | | | | | | | | Scale | |
| ScatterNd | | √ | | | | | array_ops | ScatterNd | | |
| Shape | | √ | | √ | | | array_ops | Shape | | Shape |
| Sigmoid | | √ | √ | √ | | √ | nn_ops | Logistic | Sigmoid | Sigmoid |
| Sin | | | | | | | | Sin | | Sin |
| Slice | | √ | √ | √ | | √ | array_ops | Slice | | Slice |
| Softmax | | √ | √ | √ | | √ | layer/activation | Softmax | Softmax | Softmax |
| SpaceToBatchND | | √ | | | | | array_ops | SpaceToBatchND | | |
| SpareToDense | | | | | | | | SpareToDense | | |
| SpaceToDepth | | √ | | | | | array_ops | SpaceToDepth | | SpaceToDepth |
| Split | | √ | √ | √ | | | array_ops | Split, SplitV | | |
| Sqrt | | √ | √ | √ | | | math_ops | Sqrt | | Sqrt |
| Square | | √ | √ | √ | | | math_ops | Square | | |
| SquaredDifference | | | | | | | | SquaredDifference | | |
| Squeeze | | √ | √ | √ | | | array_ops | Squeeze | | Squeeze |
| StridedSlice | | √ | √ | √ | | | array_ops | StridedSlice | | |
| Stack | | | | | | | | Stack | | |
| Sub | | √ | √ | √ | | √ | math_ops | Sub | | Sub |
| Tan | | | | | | | | | | Tan |
| Tanh | | √ | | | | | layer/activation | Tanh | TanH | |
| TensorAdd | | √ | √ | √ | | √ | math_ops | | | |
| Tile | | √ | | | | | array_ops | Tile | | Tile |
| TopK | | √ | √ | √ | | | nn_ops | TopKV2 | | |
| Transpose | | √ | √ | √ | | √ | array_ops | Transpose | Permute | Transpose |
| Unique | | | | | | | | Unique | | |
| Unpack | | √ | | | | | nn_ops | | | |
| Unsample | | | | | | | | | | Unsample |
| Unsqueeze | | | | | | | | | | Unsqueeze |
| Unstack | | | | | | | | Unstack | | |
| Where | | | | | | | | Where | | |
| ZerosLike | | √ | | | | | array_ops | ZerosLike | | |
| 操作名 | CPU
<br/>
FP16 | CPU
<br/>
FP32 | CPU
<br/>
Int8 | CPU
<br/>
UInt8 | GPU
<br/>
FP16 | GPU
<br/>
FP32 | 支持的Tensorflow
<br/>
Lite op | 支持的Caffe
<br/>
Lite op | 支持的Onnx
<br/>
Lite op |
|-----------------------|----------|----------|----------|-----------|----------|-------------------|----------|----------|---------|
| Abs | | √ | √ | √ | | | Abs | | Abs |
| Add | √ | √ | √ | √ | | √ | Add | | Add |
| AddN | | √ | | | | | AddN | | |
| Argmax | | √ | √ | √ | | | Argmax | ArgMax | ArgMax |
| Argmin | | √ | √ | √ | | | Argmin | | |
| AvgPool | √ | √ | √ | √ | | √ | MeanPooling| Pooling | AveragePool |
| BatchNorm | √ | √ | √ | √ | | √ | | BatchNorm | BatchNormalization |
| BatchToSpace | | √ | √ | √ | | | BatchToSpace, BatchToSpaceND | | |
| BiasAdd | | √ | √ | √ | | √ | | | BiasAdd |
| Broadcast | | √ | | | | | BroadcastTo | | Expand |
| Cast | √ | √ | | √ | | | Cast, DEQUANTIZE
*
| | Cast |
| Ceil | | √ | √ | √ | | | Ceil | | Ceil |
| Concat | √ | √ | √ | √ | | √ | Concat | Concat | Concat |
| Conv2d | √ | √ | √ | √ | | √ | Conv2D | Convolution | Conv |
| Conv2dTranspose | √ | √ | √ | √ | | √ | DeConv2D | Deconvolution | ConvTranspose |
| Cos | | √ | √ | √ | | | Cos | | Cos |
| Crop | | √ | √ | √ | | | | Crop | |
| DeDepthwiseConv2D | | √ | √ | √ | | | | Deconvolution| ConvTranspose |
| DepthToSpace | | √ | √ | √ | | | DepthToSpace| | DepthToSpace |
| DepthwiseConv2dNative | √ | √ | √ | √ | | √ | DepthwiseConv2D | Convolution | Convolution |
| Div | √ | √ | √ | √ | | √ | Div, RealDiv | | Div |
| Eltwise | √ | √ | | | | | | Eltwise | |
| Elu | | √ | | | | | Elu | | Elu |
| Equal | √ | √ | √ | √ | | | Equal | | Equal |
| Exp | | √ | | | | | Exp | | Exp |
| ExpandDims | | √ | | | | | | | |
| Fill | | √ | | | | | Fill | | |
| Flatten | | √ | | | | | | Flatten | |
| Floor | | √ | √ | √ | | | flOOR | | Floor |
| FloorDiv | √ | √ | | | | | FloorDiv | | |
| FloorMod | √ | √ | | | | | FloorMod | | |
| FullConnection | | √ | √ | √ | | | FullyConnected | InnerProduct | |
| GatherNd | | √ | √ | √ | | | GatherND | | |
| GatherV2 | | √ | √ | √ | | | Gather | | Gather |
| Greater | √ | √ | √ | √ | | | Greater | | Greater |
| GreaterEqual | √ | √ | √ | √ | | | GreaterEqual| | |
| Hswish | √ | √ | √ | √ | | | HardSwish | | |
| LeakyReLU | √ | √ | | | | √ | LeakyRelu | | LeakyRelu |
| Less | √ | √ | √ | √ | | | Less | | Less |
| LessEqual | √ | √ | √ | √ | | | LessEqual | | |
| LRN | | √ | | | | | LocalResponseNorm | | Lrn |
| Log | | √ | √ | √ | | | Log | | Log |
| LogicalAnd | √ | √ | | | | | LogicalAnd | | |
| LogicalNot | | √ | √ | √ | | | LogicalNot | | |
| LogicalOr | √ | √ | | | | | LogicalOr | | |
| LSTM | | √ | | | | | | | |
| MatMul | | √ | √ | √ | | √ | | | MatMul |
| Maximum | √ | √ | | | | | Maximum | | Max |
| MaxPool | √ | √ | √ | √ | | √ | MaxPooling | Pooling | MaxPool |
| Minimum | √ | √ | | | | | Minimum | | Min |
| Mul | √ | √ | √ | √ | | √ | Mul | | Mul |
| NotEqual | √ | √ | √ | √ | | | NotEqual | | |
| OneHot | | √ | | | | | OneHot | | |
| Pad | | √ | √ | √ | | | Pad | | Pad |
| Pow | | √ | √ | √ | | | Pow | Power | Power |
| PReLU | | √ | | | | √ | Prelu | PReLU | PRelu |
| Range | | √ | | | | | Range | | |
| Rank | | √ | | | | | Rank | | |
| ReduceMax | √ | √ | √ | √ | | | ReduceMax | | ReduceMax |
| ReduceMean | √ | √ | √ | √ | | | Mean | | ReduceMean |
| ReduceMin | √ | √ | √ | √ | | | ReduceMin | | ReduceMin |
| ReduceProd | √ | √ | √ | √ | | | ReduceProd | | |
| ReduceSum | √ | √ | √ | √ | | | Sum | | ReduceSum |
| ReduceSumSquare | √ | √ | √ | √ | | | | | |
| ReLU | √ | √ | √ | √ | | √ | Relu | ReLU | Relu |
| ReLU6 | √ | √ | √ | √ | | √ | Relu6 | ReLU6 | Clip
*
|
| Reshape | √ | √ | √ | √ | | √ | Reshape | Reshape | Reshape,Flatten |
| Resize | | √ | √ | √ | | | ResizeBilinear, NearestNeighbor | Interp | |
| Reverse | | √ | | | | | reverse | | |
| ReverseSequence | | √ | | | | | ReverseSequence | | |
| Round | | √ | √ | √ | | | Round | | |
| Rsqrt | | √ | √ | √ | | | Rsqrt | | |
| Scale | | √ | | | | | | Scale | |
| ScatterNd | | √ | | | | | ScatterNd | | |
| Shape | | √ | | | | | Shape | | Shape |
| Sigmoid | √ | √ | √ | √ | | √ | Logistic | Sigmoid | Sigmoid |
| Sin | | √ | √ | √ | | | Sin | | Sin |
| Slice | | √ | √ | √ | | √ | Slice | | Slice |
| Softmax | √ | √ | √ | √ | | √ | Softmax | Softmax | Softmax |
| SpaceToBatch | | √ | | | | | | | |
| SpaceToBatchND | | √ | | | | | SpaceToBatchND | | |
| SpaceToDepth | | √ | | | | | SpaceToDepth | | SpaceToDepth |
| SparseToDense | | √ | | | | | SpareToDense | | |
| Split | √ | √ | √ | √ | | | Split, SplitV | | |
| Sqrt | | √ | √ | √ | | | Sqrt | | Sqrt |
| Square | | √ | √ | √ | | | Square | | |
| SquaredDifference | | √ | | | | | SquaredDifference | | |
| Squeeze | | √ | √ | √ | | | Squeeze | | Squeeze |
| StridedSlice | | √ | √ | √ | | | StridedSlice| | |
| Stack | | √ | | | | | Stack | | |
| Sub | √ | √ | √ | √ | | √ | Sub | | Sub |
| Tanh | √ | √ | | | | | Tanh | TanH | |
| Tile | | √ | | | | | Tile | | Tile |
| TopK | | √ | √ | √ | | | TopKV2 | | |
| Transpose | √ | √ | | | | √ | Transpose | Permute | Transpose |
| Unique | | √ | | | | | Unique | | |
| Unsqueeze | | √ | √ | √ | | | | | Unsqueeze |
| Unstack | | √ | | | | | Unstack | | |
| Where | | √ | | | | | Where | | |
| ZerosLike | | √ | | | | | ZerosLike | | |
*
Clip:
only support convert clip(0, 6) to
Relu6.
*
DEQUANTIZE:
only support to convert fp16 to
fp32.
*
Clip:
仅支持将clip(0, 6)转换为
Relu6.
*
DEQUANTIZE:
仅支持将fp16转换为
fp32.
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑！
取消
想要评论请
注册
或
登录
