8000 Tags · we0091234/DALI · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content

Tags: we0091234/DALI

Tags

v0.13.0-rc2

Toggle v0.13.0-rc2's commit message
Fix fp16 bug from NVIDIA#1129 and add fp16 test case (NVIDIA#1160)

Initializing member variable `OutputType padding_value = 0;` for `__half` in the host code produced wrong results.

`padding_val` is now a fp32 that is casted to `OuputType` in the CUDA kernel


Signed-off-by: Serge Panev <spanev@nvidia.com>

v0.14.0-dev

Toggle v0.14.0-dev's commit message
Change version to 0.14.0dev

Signed-off-by: Krzysztof Lecki <klecki@nvidia.com>

v0.13.0-rc1

Toggle v0.13.0-rc1's commit message
Change version to 0.13.0

Signed-off-by: Krzysztof Lecki <klecki@nvidia.com>

v0.12.0

Toggle v0.12.0's commit message
Reduced batch size to avoid out of memory condition in 19.07 containe…

…r. (NVIDIA#1089)

Signed-off-by: Michal Zientkiewicz <michalz@nvidia.com>

v0.12.0-rc2

Toggle v0.12.0-rc2's commit message
Reduced batch size to avoid out of memory condition in 19.07 containe…

…r. (NVIDIA#1089)

v0.13.0-dev

Toggle v0.13.0-dev's commit message
Change version to 0.13.0dev

Signed-off-by: Krzysztof Lecki <klecki@nvidia.com>

v0.12.0-rc1

Toggle v0.12.0-rc1's commit message
Change version to 0.12.0

Signed-off-by: Krzysztof Lecki <klecki@nvidia.com>

v0.11.0

Toggle v0.11.0's commit message
Add as_tensor with provided shape method to python API (NVIDIA#953)

- user can cast TensorList to Tensor with provided shape from
  python API, as long as TensorList is continuous and volumes
  matches

Signed-off-by: Janusz Lisiecki <jlisiecki@nvidia.com>

v0.11.0-rc2

Toggle v0.11.0-rc2's commit message
Add as_tensor with provided shape method to python API (NVIDIA#953)

v0.12.0-dev

Toggle v0.12.0-dev's commit message
Change version to 0.12.0dev

0