bigdl.nn.onnx package

Submodules

bigdl.nn.onnx.layer module

class bigdl.nn.onnx.layer.Constant(value, bigdl_type='float')

Bases: bigdl.nn.layer.Layer

>>> value = np.random.random((3, 3))
>>> constant = Constant(value)
creating: createConstant

class bigdl.nn.onnx.layer.Gather(bigdl_type='float')

Bases: bigdl.nn.layer.Layer

>>> constant = Gather()
creating: createGather

class bigdl.nn.onnx.layer.Gemm(matrix_b, matrix_c, alpha=1.0, beta=1.0, trans_a=0, trans_b=0, bigdl_type='float')

Bases: bigdl.nn.layer.Layer

General Matrix multiplication: https://en.wikipedia.org/wiki/Basic_Linear_Algebra_Subprograms#Level_3

A’ = transpose(A) if transA else A B’ = transpose(B) if transB else B

Compute Y = alpha * A’ * B’ + beta * C, where input tensor A has shape (M, K) or (K, M), input tensor B has shape (K, N) or (N, K), input tensor C is broadcastable to shape (M, N), and output tensor Y has shape (M, N). A will be transposed before doing the computation if attribute transA is non-zero, same for B and transB.

>>> matrix_b = np.random.random([2, 2])
>>> matrix_c = np.random.random([2, 2])
>>> gemm = Gemm(matrix_b=matrix_b, matrix_c=matrix_c)
creating: createGemm

class bigdl.nn.onnx.layer.Reshape(shape=None, bigdl_type='float')

Bases: bigdl.nn.layer.Layer

A layer which takes a tensor as input and outputs an 1D tensor containing the shape of the input. >>> shape = (2, 2) >>> reshape = Reshape(shape) creating: createReshape

class bigdl.nn.onnx.layer.Shape(bigdl_type='float')

Bases: bigdl.nn.layer.Layer

A layer which takes a tensor as input and outputs an 1D tensor containing the shape of the input.

>>> shape = Shape()
creating: createShape

Module contents