Forgot about --yes USE_NEON_INSTRUCTIONS when removing --yes a moment
ago. It's on by default now so now --yes really is unneeded. The dlib
policy on this kind of thing going forward is to always have a cmake
script that tests if a feature like this is available and to enable it
automatically when building python extensions.
* Add python api that generates desciptor(s) from the aligned image(s)
* Remove asserts from face_recognition.py example/tutorial
* In batch_compute_face_descriptors_from_aligned_images, use for-in loop to simplify the code
Improvde the document on binding methods and the error message if the aligned image is not of size 150x150
fixed check for excessive detections in loss_mmod_
Ran into the problem where dets.size() was equal to max_num_initial_dets which then throws a subscript out of range error when accesing: dets[max_num_initial_dets].detection_confidence. This fixes that issue.
* Apply the #1514 fix even on non-Windows platforms
* Try to fix#1513 even more by circumventing the remaining cudaStreamSynchronize calls
* Make the fix apply only if CUDA_VERSION == 10000
* Make the fix apply on CUDA 9.2 also
* CHECK_CUDA(cudaStreamSynchronize(stream));
* Add concat_prev layer, and U-net example for semantic segmentation
* Allow to supply mini-batch size as command-line parameter
* Decrease default mini-batch size from 30 to 24
* Resize t1, if needed
* Use DenseNet-style blocks instead of residual learning
* Increase default mini-batch size to 50
* Increase default mini-batch size from 50 to 60
* Resize even during the backward step, if needed
* Use resize_bilinear_gradient for the backward step
* Fix function call ambiguity problem
* Clear destination before adding gradient
* Works OK-ish
* Add more U-tags
* Tweak default mini-batch size
* Define a simpler network when using Microsoft Visual C++ compiler; clean up the DenseNet stuff (leaving it for a later PR)
* Decrease default mini-batch size from 24 to 23
* Define separate dnn filename for MSVC++ and not
* Add documentation for the resize_to_prev layer; move the implementation so that it comes after mult_prev
* Fix previous typo
* Minor formatting changes
* Reverse the ordering of levels
* Increase the learning-rate stopping criterion back to 1e-4 (was 1e-8)
* Use more U-tags even on Windows
* Minor formatting
* Latest MSVC 2017 builds fast, so there's no need to limit the depth any longer
* Tweak default mini-batch size again
* Even though latest MSVC can now build the extra layers, it does not mean we should add them!
* Fix naming
* Add pointwise_divide operator
* Add tests for pointwise_divide function
* Replace in affine layer pointwise_multiply for division by its equivalent pointwise_divide.