1个不稳定版本
0.1.0 | 2022年10月15日 |
---|
#711 在 机器学习
105KB
2.5K SLoC
您的ONNX模型分析一站式CLI。
具有图可视化、FLOP计数、内存指标等功能!
⚡️ 快速开始
首先,下载并安装DOT。 可以通过 cargo
来安装。
cargo install steelix
MacOS用户也可以通过HomeBrew安装。
brew tap FL33TW00D/steelix
brew install steelix
⚙️ 命令与选项
Steelix有2个核心功能 - 模型摘要和模型可视化。
摘要
CLI命令用于总结您模型的核心方面。
steelix summary --model-path ./my-model.onnx
选项 | 描述 | 类型 | 默认 | 必需? |
---|---|---|---|---|
--model-path |
您模型所在的路径。 | bool |
false |
否 |
plot
CLI命令将您的模型作为SVG文件绘制 - 包含推断的形状。
steelix plot --model-path ./my-model.onnx --open
选项 | 描述 | 类型 | 默认 | 必需? |
---|---|---|---|---|
--model-path |
您模型所在的路径。 | string |
None | 是 |
--output-path |
您的SVG将被保存的路径。 | string |
./model.svg |
否 |
--open |
在生成后,在浏览器中打开SVG。 | boolean |
false |
否 |
--disable-shapes |
禁用形状推断。 | boolean |
false |
否 |
支持的操作符(参考 ONNX IR)
操作符 | 实现 |
---|---|
Abs | ✅ |
Acos | |
Acosh | |
Add | ✅ |
And | |
ArgMax | |
ArgMin | |
Asin | |
Asinh | |
Atan | |
Atanh | |
AveragePool | |
BatchNormalization | ✅ |
BitShift | |
Cast | |
Ceil | |
Clip | |
Compress | |
Concat | ✅ |
ConcatFromSequence | |
Constant | |
ConstantOfShape | |
Conv | ✅ |
ConvInteger | |
ConvTranspose | |
Cos | |
Cosh | |
CumSum | |
DepthToSpace | |
DequantizeLinear | |
Det | |
Div | |
Dropout | |
Einsum | |
Elu | |
Equal | |
Erf | ✅ |
Exp | |
Expand | |
EyeLike | |
Flatten | |
Floor | |
GRU | |
Gather | ✅ |
GatherElements | |
GatherND | |
Gemm | ✅ |
GlobalAveragePool | |
GlobalLpPool | |
GlobalMaxPool | |
Greater | |
GridSample | |
HardSigmoid | |
Hardmax | |
Identity | |
If | |
InstanceNormalization | |
IsInf | |
IsNaN | |
LRN | |
LSTM | |
LeakyRelu | ✅ |
Less | |
Log | |
Loop | |
LpNormalization | |
LpPool | |
MatMul | ✅ |
MatMulInteger | |
Max | |
MaxPool | ✅ |
MaxRoiPool | |
MaxUnpool | |
Mean | |
Min | |
Mod | |
Mul | ✅ |
Multinomial | |
Neg | |
NonMaxSuppression | |
NonZero | |
Not | ✅ |
OneHot | |
Optional | |
OptionalGetElement | |
OptionalHasElement | |
Or | |
PRelu | |
Pad | ✅ (mode=constant, pads≥0) |
Pow | |
QLinearConv | |
QLinearMatMul | |
QuantizeLinear | |
RNN | |
RandomNormal | |
RandomNormalLike | |
RandomUniform | |
RandomUniformLike | |
Reciprocal | |
ReduceL1 | |
ReduceL2 | |
ReduceLogSum | |
ReduceLogSumExp | |
ReduceMax | |
ReduceMean | |
ReduceMin | |
ReduceProd | |
ReduceSum | |
ReduceSumSquare | |
Relu | ✅ |
Reshape | ✅ |
Resize | |
ReverseSequence | |
RoiAlign | |
Round | |
Scan | |
Scatter (已弃用) | |
ScatterElements | |
ScatterND | |
Selu | |
SequenceAt | |
SequenceConstruct | |
SequenceEmpty | |
SequenceErase | |
SequenceInsert | |
SequenceLength | |
Shape | |
Shrink | |
Sigmoid | ✅ |
Sign | |
Sin | |
Sinh | |
Size | |
Slice | |
Softplus | |
Softsign | |
SpaceToDepth | |
Split | |
SplitToSequence | |
Sqrt | |
Squeeze | ✅ |
StringNormalizer | |
Sub | |
Sum | |
Tan | |
Tanh | |
TfIdfVectorizer | |
ThresholdedRelu | |
Tile | |
TopK | |
Transpose | |
Trilu | |
Unique | |
Unsqueeze | ✅ |
Upsample (已弃用) | |
Where | |
Xor | |
Function | |
Bernoulli | |
CastLike | |
Celu | |
DynamicQuantizeLinear | |
GreaterOrEqual | |
HardSwish | |
LessOrEqual | |
LogSoftmax | |
MeanVarianceNormalization | |
NegativeLogLikelihoodLoss | |
Range | |
Softmax | ✅ |
SoftmaxCrossEntropyLoss |
Credit
依赖关系
~12–23MB
~353K SLoC