|
|
|
@ -11,6 +11,23 @@
|
|
|
|
|
<!-- ************************************************************************************** -->
|
|
|
|
|
|
|
|
|
|
<current>
|
|
|
|
|
New Features and Improvements:
|
|
|
|
|
- Added support for cuDNN 8.0
|
|
|
|
|
- Added support for CUDA in Python 3.8 on Windows.
|
|
|
|
|
- Allow forwarding initial function evaluations into find_max_global()
|
|
|
|
|
|
|
|
|
|
Non-Backwards Compatible Changes:
|
|
|
|
|
|
|
|
|
|
Bug fixes:
|
|
|
|
|
- Improved error messages for python users trying to install dlib
|
|
|
|
|
with CUDA enabled or who are using windows.
|
|
|
|
|
- Fix random forest regression not doing quite the right thing.
|
|
|
|
|
|
|
|
|
|
</current>
|
|
|
|
|
|
|
|
|
|
<!-- ************************************************************************************** -->
|
|
|
|
|
|
|
|
|
|
<old name="19.20" date="Jun 06, 2020">
|
|
|
|
|
New Features and Improvements:
|
|
|
|
|
- Added CUDA implementation for loss_mean_squared_per_channel_and_pixel.
|
|
|
|
|
- Added DCGAN example in examples/dnn_dcgan_train_ex.cpp
|
|
|
|
@ -33,8 +50,7 @@ Bug fixes:
|
|
|
|
|
- Fix DLIB_ISO_CPP_ONLY not working
|
|
|
|
|
- Fix build errors in C++20 build mode.
|
|
|
|
|
- Fixed function_evaluation_request::set() invalidating function_evaluation_request::x()
|
|
|
|
|
|
|
|
|
|
</current>
|
|
|
|
|
</old>
|
|
|
|
|
|
|
|
|
|
<!-- ************************************************************************************** -->
|
|
|
|
|
|
|
|
|
|