- Add a python wrapper for using the CNN face detector.
- Added last_modified() method to dlib::file. Also, added select_oldest_file() and select_newest_file()
- Added solve_qp_box_constrained_blockdiag()
- Added an overload of mat() that takes a row stride value.
- Added cmake scripts and some related tooling that makes it easy to call C++ code from java. See dlib/java/ folder. Added an object that lets you hold a copyable reference to a java array.
- MATLAB MEX wrapper API
- Made the mex wrapper deal with cell arrays that have null elements.
- Made ctrl+c detection in a mex file work more reliably in newer versions of matlab.
- Added support for cuDNN 6 and 7
- Added cuda_data_ptr, a templated container for GPU memory as well as an untyped cuda_data_void_ptr.
- Added a tt::inv() for computing matrix inversions on the GPU.
- Added tt::log(), tt::exp(), and tt::log10()
- Added tt::multiply_zero_padded()
- Dlib's simd classes will now use ARM NEON instructions. This makes the
HOG based object detector faster on mobile devices running ARM processors.
- Added a simple tool to convert dlib model files, which are saved as XML files, to caffe models. See tools/convert_dlib_nets_to_caffe folder.
- Added visit_layers_until_tag()
- Relaxed the default non-max suppression parameters used by the mmod_options object so that users of the deep learning MMOD tool don't get spurious errors about impossibly labeled objects during training.
- Upgraded loss_mmod_ to support objects of varying aspect ratio. This changes the API for the mmod_options struct slightly.
- Added a .fill() member to curand_generator that can create random 32bit integers.
- Added set_rect_area()
- Added process() and process_batch() to add_loss_layer. These routines let you easily pass arguments to any optional parameters of a loss layer's to_tensor() routine. For instance, it makes it more convenient to set loss_mmod_'s adjust_threshold parameter.
- Added missing input validation to loss_mmod_. Specifically, the loss layer now checks if the user is giving truth boxes that can't be detected because the non-max suppression settings would prevent them from being output at the same time. If this happens then we print a warning message and set one of the offending boxes to "ignore". Changed all the input validation errors to warning messages with auto conversion to ignore boxes rather than killing exceptions.
- Changed the random_cropper's interface so that instead of talking in terms of min and max object height, it's now min and max object size. This way, if you have objects that are short and wide (i.e. objects where the relevant dimension is width rather than height) you will get sensible behavior out of the random cropper.
- Made dnn_trainer sync its state to two separate sync files that it alternates between. This should make syncing more robust to sudden hardware failure that happens right when saving to disk.
- Made it so you can set the number of output filters for con_ layers at runtime.
- Added tt::resize_bilinear() and tt::resize_bilinear_gradient().
- Gave test_object_detection_function() an option to set how ignore box overlap is tested.
- cuDNN convolution algorithms shared workspace. More efficient GPU memory usage, so now set_dnn_prefer_fastest_algorithms() should not be needed.
- Added operator<< for random_cropper and dnn_trainer.
- Made tt::copy_tensor() and concat_ layer a lot faster.
- New DNN layers
- cont_ (transpose convolution, sometimes called "deconvolution")
- loss_multiclass_log_per_pixel_
- loss_multiclass_log_per_pixel_weighted_
- loss_mean_squared_per_pixel_
- mult_prev_
- Added extract_ layer
- Added upsample_ layer that upsamples a tensor using bilinear interpolation.
- Made the dnn_trainer not forget all the previous loss values it knows about when it determines that there have been a lot of steps without progress and shrinks the learning rate. Instead, it removes only the oldest 100. The problem with the old way of removing all the loss values in the history was that if you set the steps without progress threshold to a really high number you would often observe that the last few learning rate values were obviously not making progress, however, since all the previous loss values were forgotten the trainer needed to fully populate it's loss history from scratch before it would figure this out. This new style makes the trainer not waste time running this excessive optimization of obviously useless mini-batches. Changed the default get_test_iterations_without_progress_threshold() from 200 to 500. Now that we have a better history management of loss values in the trainer it's much more sensible to have a larger value here.
Non-Backwards Compatible Changes:
- DNN solver's are now required to declare operator<<.
- Broke backwards compatibility with previous dnn_trainer serialization format.
- Changed random_cropper interface.
- CMake users should link to dlib::dlib instead of dlib (TODO, explain further).
- Changed the XML format output by net_to_xml(). Specifically, the XML tag for affine layers was changed so to use the same conventions as other layers that support convolutional vs fully connected modes.
- Dlib's smart pointers have been deprecated and all of dlib's code has been changed to use the std:: version of these smart pointers. The old dlib smart pointers are still present, allowing users to explicitly include it, but users should migrate to the C++11 standard version of these tools.
Bug fixes:
- Made the input_tensor_to_output_tensor() and output_tensor_to_input_tensor() coordinate mappings work on networks that contain skip layers.
- The input_rgb_image_sized is supposed to be convertible to input_rgb_image, which it was in all ways except you couldn't deserialize directly like you would expect. This has now been fixed.
- There was also a bug in the concat_ layer's backward() method. It was assigning the gradient to previous layers instead of adding the gradient, as required by the layer interface specification.
- Changed the random_cropper so that it samples background patches uniformly across scales regardless of the input image size. Previously, if you gave really large images or really small images it had a bias towards giving only large patches or small patches respectively.
- Fixed name lookup problem for calls to serialize() on network objects.
- Fixed double delete in tokenizer_kernel_1.
- Fixed error in pyramid_down<2> that caused the output image to be a little funny looking in some cases.
- Fixed the visit_layers_backwards() and visit_layers_backwards_range() routines so they visit layers in the correct order.
- Made build scripts work on a wider range of platforms and configurations.
- Worked around global timer cleanup issues that occur on windows when dlib is
used in a dll in some situations.
- Fixed various compiler errors in obscure environments.
Other:
- Added serialization support for the running_stats_decayed object.
- Made the attribute_list of the xml parser a little more friendly by allowing you to ask for attributes that don't exist and get a defined behavior (an exception being thrown) rather than it being a contract violation.
- Additions to imglab
- Added --sort and also the ability to propagate boxes from one image to the next using dlib::correlation_tracker.
- Made it so you can remove images by pressing alt+d.
- Made is so pressing e in imglab toggles between views of the image where the histogram is equalized or unmodified. This way, if you are looking at particularly dark or badly contrasted images you can toggle this mode and maybe get a better view of what you are labeling.
