tkonolige commented on a change in pull request #6685:
URL: https://github.com/apache/incubator-tvm/pull/6685#discussion_r507877890
##########
File path: python/tvm/relay/frontend/tensorflow.py
##########
@@ -890,6 +890,44 @@ def _impl(inputs, attr, params, mod):
return _impl
+def _sparse_tensor_dense_matmul():
+ # Sparse utility from Numpy
+ from scipy import sparse
+
+ def _impl(inputs, attr, params, mod):
+ assert len(inputs) == 4, "There should be 4 input tensors"
+
+ indices_tensor = _infer_value(inputs[0], params, mod).asnumpy()
+ values_tensor = _infer_value(inputs[1], params, mod).asnumpy()
+ dense_shape_tensor = _infer_value(inputs[2], params, mod).asnumpy()
+
+ data = inputs[3]
+
+ rows = [x[0] for x in indices_tensor]
+ cols = [x[1] for x in indices_tensor]
+
+ # Create Numpy sparse Tensor(CSR)
+ weight_sp = sparse.csr_matrix(
+ (values_tensor, (rows, cols)),
shape=tuple(dense_shape_tensor.tolist())
+ )
+ weight_sp = sparse.csr_matrix(weight_sp.transpose())
+
+ weight_data = _expr.const(weight_sp.data, weight_sp.data.dtype)
+ weight_indptrs = _expr.const(weight_sp.indptr, weight_sp.indptr.dtype)
+ weight_indices = _expr.const(weight_sp.indices,
weight_sp.indices.dtype)
+
+ ret = _op.nn.sparse_dense(data, [weight_data, weight_indices,
weight_indptrs])
Review comment:
In the code you have here, it looks like you are computing B (A^T)^T.
(A^T is from the transpose you've applied, and B (A^T)^T is from the sparse
dense). You should be computing A B because this is what tensorflow computes. I
think what you want to do here is 1. transpose B, 2. sparse_dense with the
transposed B and _untransposed_ A, 3. transpose the result. This is if
`adjoint_a` and `adjoint_b` are false.
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
us...@infra.apache.org
