Dot¶

onnx_array_api.plotting.dot_plot.to_dot(proto:ModelProto,recursive:bool=False,prefix:str='',use_onnx:bool=False,add_functions:bool=True,rt_shapes:Dict[str,Tuple[int,...]]|None=None,**params)→str[source]¶

Produces aDOT language string for the graph.

Parameters:

• params – additional params to draw the graph

• recursive – also show subgraphs inside operator likeScan

• prefix – prefix for every node name

• use_onnx – useonnx dot format instead of this one

• add_functions – add functions to the graph

• rt_shapes – indicates shapes obtained from the execution or inference

Returns:

string

Default options for the graph are:

options={'orientation':'portrait','ranksep':'0.25','nodesep':'0.05','width':'0.5','height':'0.1','size':'7',}

One example:

<<<

importnumpyasnp# Bfromonnx_array_api.npximportabsolute,jit_onnxfromonnx_array_api.plotting.dot_plotimportto_dotdefl1_loss(x,y):returnabsolute(x-y).sum()defl2_loss(x,y):return((x-y)**2).sum()defmyloss(x,y):returnl1_loss(x[:,0],y[:,0])+l2_loss(x[:,1],y[:,1])jitted_myloss=jit_onnx(myloss)x=np.array([[0.1,0.2],[0.3,0.4]],dtype=np.float32)y=np.array([[0.11,0.22],[0.33,0.44]],dtype=np.float32)res=jitted_myloss(x,y)print(res)

>>>

0.042

onnx_array_api.plotting.graphviz_helper.plot_dot(dot:str|ModelProto,ax:matplotlib.axis.Axis|None=None,engine:str='dot',figsize:Tuple[int,int]|None=None)→matplotlib.axis.Axis[source]¶

Draws a dot graph into a matplotlib graph.

Parameters:

• dot – dot graph or ModelProto

• image – output image, None, just returns the output

• engine –dot orneato

• figsize – figsize of ax is None

Returns:

Graphviz output or, the dot text ifimage is None

(Sourcecode,png,hires.png,pdf)

Statistics¶

onnx_array_api.plotting.stat_plot.plot_ort_profile(df:DataFrame,ax0:Any|None=None,ax1:Any|None=None,title:str|None=None)→Any[source]¶

Plots time spend in computation based on dataframeproduced by functionort_profile.

Parameters:

• df – dataframe

• ax0 – first axis to draw time

• ax1 – second axis to draw occurences

• title – graph title

Returns:

ax0

SeeProfiling for an example.

Text¶

onnx_array_api.plotting.text_plot.onnx_text_plot_tree(node)[source]¶

Gives a textual representation of a tree ensemble.

Parameters:

node –TreeEnsemble*

Returns:

text

<<<

importnumpyfromsklearn.datasetsimportload_irisfromsklearn.treeimportDecisionTreeRegressorfromskl2onnximportto_onnxfromonnx_array_api.plotting.text_plotimportonnx_text_plot_treeiris=load_iris()X,y=iris.data.astype(numpy.float32),iris.targetclr=DecisionTreeRegressor(max_depth=3)clr.fit(X,y)onx=to_onnx(clr,X)res=onnx_text_plot_tree(onx.graph.node[0])print(res)

>>>

n_targets=1n_trees=1----treeid=0nX3<=np.float32(0.8)-nX3<=np.float32(1.75)-nX2<=np.float32(4.85)-f0:2+f0:1.67+nX2<=np.float32(4.95)-f0:1.67+f0:1.02+f0:0

onnx_array_api.plotting.text_plot.onnx_text_plot_io(model,verbose=False,att_display=None)[source]¶

Displays information about input and output types.

Parameters:

• model – ONNX graph

• verbose – display debugging information

Returns:

str

An ONNX graph is printed the following way:

<<<

importnumpyfromsklearn.clusterimportKMeansfromskl2onnximportto_onnxfromonnx_array_api.plotting.text_plotimportonnx_text_plot_iox=numpy.random.randn(10,3)y=numpy.random.randn(10)model=KMeans(3)model.fit(x,y)onx=to_onnx(model,x.astype(numpy.float32),target_opset=15)text=onnx_text_plot_io(onx,verbose=False)print(text)

>>>

opset:domain=''version=15input:name='X'type=dtype('float32')shape=['',3]init:name='Ad_Addcst'type=float32shape=(3,)init:name='Ge_Gemmcst'type=float32shape=(3,3)init:name='Mu_Mulcst'type=float32shape=(1,)output:name='label'type=dtype('int64')shape=['']output:name='scores'type=dtype('float32')shape=['',3]

onnx_array_api.plotting.text_plot.onnx_simple_text_plot(model,verbose=False,att_display=None,add_links=False,recursive=False,functions=True,raise_exc=True,sub_graphs_names=None,level=1,indent=True)[source]¶

Displays an ONNX graph into text.

Parameters:

• model – ONNX graph

• verbose – display debugging information

• att_display – list of attributes to display, if None,a default list if used

• add_links – displays links of the right side

• recursive – display subgraphs as well

• functions – display functions as well

• raise_exc – raises an exception if the model is not valid,otherwise tries to continue

• sub_graphs_names – list of sub-graphs names

• level – sub-graph level

• indent – use indentation or not

Returns:

str

An ONNX graph is printed the following way:

<<<

importnumpyfromsklearn.clusterimportKMeansfromskl2onnximportto_onnxfromonnx_array_api.plotting.text_plotimportonnx_simple_text_plotx=numpy.random.randn(10,3)y=numpy.random.randn(10)model=KMeans(3)model.fit(x,y)onx=to_onnx(model,x.astype(numpy.float32),target_opset=15)text=onnx_simple_text_plot(onx,verbose=False)print(text)

>>>

opset:domain=''version=15input:name='X'type=dtype('float32')shape=['',3]init:name='Ad_Addcst'type=float32shape=(3,)--array([1.994,1.628,3.194],dtype=float32)init:name='Ge_Gemmcst'type=float32shape=(3,3)init:name='Mu_Mulcst'type=float32shape=(1,)--array([0.],dtype=float32)ReduceSumSquare(X,axes=[1],keepdims=1)->Re_reduced0Mul(Re_reduced0,Mu_Mulcst)->Mu_C0Gemm(X,Ge_Gemmcst,Mu_C0,alpha=-2.00,transB=1)->Ge_Y0Add(Re_reduced0,Ge_Y0)->Ad_C01Add(Ad_Addcst,Ad_C01)->Ad_C0ArgMin(Ad_C0,axis=1,keepdims=0)->labelSqrt(Ad_C0)->scoresoutput:name='label'type=dtype('int64')shape=['']output:name='scores'type=dtype('float32')shape=['',3]

The same graphs with links.

<<<

importnumpyfromsklearn.clusterimportKMeansfromskl2onnximportto_onnxfromonnx_array_api.plotting.text_plotimportonnx_simple_text_plotx=numpy.random.randn(10,3)y=numpy.random.randn(10)model=KMeans(3)model.fit(x,y)onx=to_onnx(model,x.astype(numpy.float32),target_opset=15)text=onnx_simple_text_plot(onx,verbose=False,add_links=True)print(text)

>>>

opset:domain=''version=15input:name='X'type=dtype('float32')shape=['',3]-------------------------------------------+-+init:name='Ad_Addcst'type=float32shape=(3,)--array([0.959,0.651,6.432],dtype=float32)|-|-----------+init:name='Ge_Gemmcst'type=float32shape=(3,3)------------------------------------+|||init:name='Mu_Mulcst'type=float32shape=(1,)--array([0.],dtype=float32)-----+||||ReduceSumSquare(X,axes=[1],keepdims=1)->Re_reduced0<--+----------------------|-+-|--------+||Mul(Re_reduced0,Mu_Mulcst)->Mu_C0<-------------------+----------------------+||||Gemm(X,Ge_Gemmcst,Mu_C0,alpha=-2.00,transB=1)->Ge_Y0<-------------------|-+----------+|Add(Re_reduced0,Ge_Y0)->Ad_C01<-----------------------------------------------+|Add(Ad_Addcst,Ad_C01)->Ad_C0----------------+-+------------------------------------------------------+ArgMin(Ad_C0,axis=1,keepdims=0)->label<--+-|--+Sqrt(Ad_C0)->scores<-------------------------+--|-----+output:name='label'type=dtype('int64')shape=['']<----+|output:name='scores'type=dtype('float32')shape=['',3]<----+

Visually, it looks like the following: