- Notifications
You must be signed in to change notification settings - Fork0
Array APIs to write ONNX Graphs
License
sdpython/onnx-array-api
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
onnx-array-api implements APIs to create custom ONNX graphs.The objective is to speed up the implementation of converter libraries.The library is released onpypi/onnx-array-apiand its documentation is published atAPIs to create ONNX Graphs.
The first one matchesnumpy API.It gives the user the ability to convert functions writtenfollowing the numpy API to convert that function into ONNX aswell as to execute it.
importnumpyasnpfromonnx_array_api.npximportabsolute,jit_onnxfromonnx_array_api.plotting.text_plotimportonnx_simple_text_plotdefl1_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)print(onnx_simple_text_plot(jitted_myloss.get_onnx()))
[0.042]opset: domain='' version=18input: name='x0' type=dtype('float32') shape=['', '']input: name='x1' type=dtype('float32') shape=['', '']Sub(x0, x1) -> r__0 Abs(r__0) -> r__1 ReduceSum(r__1, keepdims=0) -> r__2output: name='r__2' type=dtype('float32') shape=NoneIt supports eager mode as well:
importnumpyasnpfromonnx_array_api.npximportabsolute,eager_onnxdefl1_loss(x,y):err=absolute(x-y).sum()print(f"l1_loss={err.numpy()}")returnerrdefl2_loss(x,y):err= ((x-y)**2).sum()print(f"l2_loss={err.numpy()}")returnerrdefmyloss(x,y):returnl1_loss(x[:,0],y[:,0])+l2_loss(x[:,1],y[:,1])eager_myloss=eager_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=eager_myloss(x,y)print(res)
l1_loss=[0.04]l2_loss=[0.002][0.042]
The second API orLight API tends to do every thing in one line.It is inspired from theReverse Polish Notation.The euclidean distance looks like the following:
importnumpyasnpfromonnx_array_api.light_apiimportstartfromonnx_array_api.plotting.text_plotimportonnx_simple_text_plotmodel= (start() .vin("X") .vin("Y") .bring("X","Y") .Sub() .rename("dxy") .cst(np.array([2],dtype=np.int64),"two") .bring("dxy","two") .Pow() .ReduceSum() .rename("Z") .vout() .to_onnx())
Almost every converting library (converting a machine learned model to ONNX) is implementingits own graph builder and customizes it for its needs.It handles some frequent tasks such as giving names to intermediateresults, loading, saving onnx models. It can be used as well to extend an existing graph.
importnumpyasnpfromonnx_array_api.graph_apiimportGraphBuilderg=GraphBuilder()g.make_tensor_input("X",np.float32, (None,None))g.make_tensor_input("Y",np.float32, (None,None))r1=g.make_node("Sub", ["X","Y"])# the name given to the output is given by the class,# it ensures the name is uniqueinit=g.make_initializer(np.array([2],dtype=np.int64))# the class automatically# converts the array to a tensorr2=g.make_node("Pow", [r1,init])g.make_node("ReduceSum", [r2],outputs=["Z"])# the output name is given because# the user wants to choose the nameg.make_tensor_output("Z",np.float32, (None,None))onx=g.to_onnx()# final conversion to onnx
About
Array APIs to write ONNX Graphs
Topics
Resources
License
Code of conduct
Uh oh!
There was an error while loading.Please reload this page.
Stars
Watchers
Forks
Packages0
Uh oh!
There was an error while loading.Please reload this page.
Contributors2
Uh oh!
There was an error while loading.Please reload this page.