GitLab

* [DLIB] macro for generating default serialisation functions

* [DLIB]  refactoring

* [DLIB]  refactoring

* Add scale_prev layer

* remove comment and fix gradient

* add test for scale_ and scale_prev_ layers

The const bug was introduced yesterday and caused some layer visiting to
not work on const networks.

Now the user doesn't have to supply a visitor capable of visiting all
layers, but instead just the ones they are interested in.  Also added
visit_computational_layers() and visit_computational_layers_range()
since those capture a very common use case more concisely than
visit_layers().  That is, users generally want to mess with the
computational layers specifically as those are the stateful layers.

* add visitor to remove bias from bn_ inputs (#closes 2155)

* remove unused parameter and make documentation more clear

* remove bias from bn_ layers too and use better name

* let the batch norm keep their bias, use even better name

* be more consistent with impl naming

* remove default constructor

* do not use method to prevent some errors

* add disable bias method to pertinent layers

* update dcgan example

- grammar
- print number of network parameters to be able to check bias is not allocated
- at the end, give feedback to the user about what the discriminator thinks about each generated sample

* fix fc_ logic

* add documentation

* add bias_is_disabled methods and update to_xml

* print use_bias=false when bias is disabled

Make dnn_trainer use robust statistic to determine if the loss is exploding and if it should backtrack.

Previously we used only the non-robust version, and so would mistakenly
not catch sequenes of loss increase that begin with an extremely large
value and then settled down to still large but less extreme values.

* add loss_multilabel_log

* add alias template for loss_multilabel_log

* add missing assert

* increment truth iterator

* rename loss to loss_multibinary_log

* rename loss to loss_multibinary_log

* explicitly capture dims in lambda

Problem: With certain batch size / device count combinations, batches were generated with size = 1, causing problems when using batch normalization. (#2152)

Solution: Divide the mini-batch more uniformly across the different devices.

When consuming dlib headers and building using gcc/clang with flags
'-Werror -Wpedantic', any inclusion involving DLIB_CASSERT triggers
a compilation error: ISO C++11 requires at least one argument for the
"..." in a variadic macro
Co-authored-by: Samuel Aldana <samuel.aldana@cognex.com>

* Added a function for computing a gaussian distributed complex number. The real version is adapted to use the complex version

* Missing header

* missed std:: I was too quick
Co-authored-by: pf <pf@pf-ubuntu-dev>

The recent change to use a dlib/__init__.py file instead of the dlib.so file directly messed it up.

* Added possibility to load PNG images from a data buffer.

* Fixed code not compiling with some versions of libpng that doesn't have const specifier.

* Used FileInfo struct as a single parameter for the read_image method.

error: calling a constexpr host function("log1p") from a device function("cuda_log1pexp") is not allowed. The experimental flag '--expt-relaxed-constexpr' can be used to allow this.

The error only happens with some versions of CUDA.