npx.npx_functions¶

onnx_array_api.npx.npx_functions.abs(*inputs,**kwargs)¶

Seenumpy.absolute().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.absolute(*inputs,**kwargs)¶

Seenumpy.absolute().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.arccos(*inputs,**kwargs)¶

Seenumpy.arccos().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.arccosh(*inputs,**kwargs)¶

Seenumpy.arccosh().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.amax(*inputs,**kwargs)¶

Seenumpy.amax().

Signature:

(x:TensorType[numerics,'T'],axis:OptParType[int],keepdims:OptParType[int],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.amin(*inputs,**kwargs)¶

Seenumpy.amin().

Signature:

(x:TensorType[numerics,'T'],axis:OptParType[int],keepdims:OptParType[int],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.arange(*inputs,**kwargs)¶

Seenumpy.arange().

Signature:

(start_or_stop:TensorType[{'float64','int16','int64','float32','int32'},(1,),'I'],stop_or_step:OptTensorType[{'float64','int16','int64','float32','int32'},(1,),'I'],step:OptTensorType[{'float64','int16','int64','float32','int32'},(1,),'I'],dtype:OptParType[DType],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.argmax(*inputs,**kwargs)¶

Seenumpy.amax().

Signature:

(x:TensorType[numerics,'T'],axis:OptParType[int],keepdims:OptParType[int],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.argmin(*inputs,**kwargs)¶

Seenumpy.argmin().

Signature:

(x:TensorType[numerics,'T'],axis:OptParType[int],keepdims:OptParType[int],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.arcsin(*inputs,**kwargs)¶

Seenumpy.arcsin().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.arcsinh(*inputs,**kwargs)¶

Seenumpy.arcsinh().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.arctan(*inputs,**kwargs)¶

Seenumpy.arctan().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.arctanh(*inputs,**kwargs)¶

Seenumpy.arctanh().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.cdist(*inputs,**kwargs)¶

Seescipy.special.distance.cdist().

Signature:

(xa:TensorType[numerics,'T'],xb:TensorType[numerics,'T'],metric:OptParType[str],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.ceil(*inputs,**kwargs)¶

Seenumpy.ceil().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.clip(*inputs,**kwargs)¶

Seenumpy.clip().

Signature:

(x:TensorType[numerics,'T'],a_min:TensorType[numerics,'T'],a_max:TensorType[numerics,'T'],):

onnx_array_api.npx.npx_functions.compress(*inputs,**kwargs)¶

Seenumpy.compress().np.compress(condition, x) ornpnx.compress(x, condition).

Signature:

(condition:TensorType['bool_','B'],x:TensorType[numerics,'T'],axis:OptParType[int],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.compute(*inputs,**kwargs)¶

Executes an onnx proto.

param x:

inputs

param proto:

proto to execute

param name:

model name

return:

outputs

Signature:

(x:SequenceType["TensorType[numerics, 'T']"],proto:ParType[typing.Union[onnx.onnx_ml_pb2.FunctionProto,onnx.onnx_ml_pb2.ModelProto,onnx.onnx_ml_pb2.NodeProto]],name:ParType[str],)->TupleType[TensorType[numerics,'T']]:

onnx_array_api.npx.npx_functions.concat(*inputs,**kwargs)¶

Operator concat, handlenumpy.vstack() andnumpy.hstack().

Signature:

(x:SequenceType["TensorType[numerics, 'T']"],axis:ParType[int],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.cos(*inputs,**kwargs)¶

Seenumpy.cos().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.cosh(*inputs,**kwargs)¶

Seenumpy.cosh().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.cumsum(*inputs,**kwargs)¶

Seenumpy.cumsum().

Signature:

(x:TensorType[numerics,'T'],axis:OptTensorType['int64','I'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.det(*inputs,**kwargs)¶

Seenumpy.linalg:det().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.dot(*inputs,**kwargs)¶

Seenumpy.dot()dot is equivalent tonpx.matmul == np.matmul != np.dotwith arrays with more than 3D dimensions.

Signature:

(a:TensorType[numerics,'T'],b:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.einsum(*inputs,**kwargs)¶

Seenumpy.einsum().

Signature:

(x:SequenceType["TensorType[numerics, 'T']"],equation:ParType[str],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.erf(*inputs,**kwargs)¶

Seescipy.special.erf().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.exp(*inputs,**kwargs)¶

Seenumpy.exp().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.expand_dims(*inputs,**kwargs)¶

Seenumpy.expand_dims().

Signature:

(x:TensorType[numerics,'T'],axis:TensorType['int64','I'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.expit(*inputs,**kwargs)¶

Seescipy.special.expit().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.floor(*inputs,**kwargs)¶

Seenumpy.floor().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.hstack(*inputs,**kwargs)¶

Seenumpy.hstack().

Signature:

(x:SequenceType["TensorType[numerics, 'T']"],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.copy(*inputs,**kwargs)¶

Makes a copy.

Signature:

(x:TensorType[allowed,'T'],)->TensorType[allowed,'T']:

onnx_array_api.npx.npx_functions.identity(*inputs,**kwargs)¶

Makes a copy.

Signature:

(n:ParType[int],dtype:OptParType[DType],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.isnan(*inputs,**kwargs)¶

Seenumpy.isnan().

Signature:

(x:TensorType[numerics,'T'],)->TensorType['bool_','T1']:

onnx_array_api.npx.npx_functions.log(*inputs,**kwargs)¶

Seenumpy.log().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.log1p(*inputs,**kwargs)¶

Seenumpy.log1p().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.matmul(*inputs,**kwargs)¶

Seenumpy.matmul().

Signature:

(a:TensorType[numerics,'T'],b:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.pad(*inputs,**kwargs)¶

It does not implementnumpy.pad() but the ONNX version.

Signature:

(x:TensorType[numerics,'T'],pads:TensorType['int64','I'],constant_value:OptTensorType[numerics,'T'],axes:OptTensorType['int64','I'],mode:ParType[str],):

onnx_array_api.npx.npx_functions.reciprocal(*inputs,**kwargs)¶

Seenumpy.reciprocal().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.relu(*inputs,**kwargs)¶

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.round(*inputs,**kwargs)¶

Seenumpy.round().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.sigmoid(*inputs,**kwargs)¶

Seescipy.special.expit().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.sign(*inputs,**kwargs)¶

Seenumpy.sign().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.sin(*inputs,**kwargs)¶

Seenumpy.sin().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.sinh(*inputs,**kwargs)¶

Seenumpy.sinh().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.squeeze(*inputs,**kwargs)¶

Seenumpy.squeeze().

Signature:

(x:TensorType[numerics,'T'],axis:OptTensorType['int64','I'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.tan(*inputs,**kwargs)¶

Seenumpy.tan().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.tanh(*inputs,**kwargs)¶

Seenumpy.tanh().

Signature:

(x:TensorType[numerics,'T'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.topk(*inputs,**kwargs)¶

Seenumpy.argsort().

Signature:

(x:TensorType[numerics,'T'],k:TensorType['int64',(1,),'I'],axis:OptParType[int],largest:OptParType[int],sorted:OptParType[int],)->TupleType[TensorType[numerics,'T'],TensorType['int64','I']]:

onnx_array_api.npx.npx_functions.transpose(*inputs,**kwargs)¶

Seenumpy.transpose().

Signature:

(x:TensorType[numerics,'T'],perm:ParType[typing.Tuple[int,...]],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.unsqueeze(*inputs,**kwargs)¶

Seenumpy.expand_dims().

Signature:

(x:TensorType[numerics,'T'],axis:TensorType['int64','I'],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.vstack(*inputs,**kwargs)¶

Seenumpy.vstack().

Signature:

(x:SequenceType["TensorType[numerics, 'T']"],)->TensorType[numerics,'T']:

onnx_array_api.npx.npx_functions.where(*inputs,**kwargs)¶

Seenumpy.where().

Signature:

(cond:TensorType['bool_','B'],x:TensorType[numerics,'T'],y:TensorType[numerics,'T'],)->TensorType[numerics,'T']: