Matrix doesn't deallocate memory

[nartes]

Memory is not being deallocated, since no destructor is being defined:

nv-wavenet/matrix.h

Line 39 in 03f6957

Matrix(int rows, int cols, bool isTransposed=false);

The only place that is being used in pytorch bindings:

nv-wavenet/pytorch/wavenet_infer.cu

Line 92 in 03f6957

Matrix outputSelectors(batch_size, sample_count);

Softmax sampling shoud not leak that much memory though.

[m-k-S]

Were you able to solve this issue? I am unable to perform inference with even a batch size of 1 as my GPU runs out of memory.