Bugfix for NumPyBinLoader with SubTensor output. (#345)

* Bugfix for NumPyBinLoader with SubTensor output.

When a SubTensor is used as output from a NumPyBinLoader, data should
not be written to the begining of the buffer.

Change-Id: I6ed4b24710ac09b41ca92c7e21f24d44a3ed2881

* Reduce the buffer size with the same amount

Change-Id: Id260f58209ce2fbee877f7d6f4afbe95c6c74036

* SubTensor's has to be accessed through execution windows
1 file changed
tree: 9a3986264ce0985da84a1388b03606d9e42ec0af
  1. arm_compute/
  2. data/
  3. docs/
  4. documentation/
  5. examples/
  6. include/
  7. opencl-1.2-stubs/
  8. opengles-3.1-stubs/
  9. scripts/
  10. src/
  11. support/
  12. tests/
  13. utils/
  14. .clang-format
  15. documentation.xhtml
  16. LICENSE
  17. README.md
  18. SConscript
  19. SConstruct
README.md

Please report issues here: https://github.com/ARM-software/ComputeLibrary/issues Make sure you are using the latest version of the library before opening an issue. Thanks

Related projects:

Documentation available here:

Binaries available here:

Support: developer@arm.com

License & Contributions: The software is provided under MIT license. Contributions to this project are accepted under the same license.