GitLab

* Add instance segmentation example - first version of training code

* Add MMOD options; get rid of the cache approach, and instead load all MMOD rects upfront

* Improve console output

* Set filter count

* Minor tweaking

* Inference - first version, at least compiles!

* Ignore overlapped boxes

* Ignore even small instances

* Set overlaps_ignore

* Add TODO remarks

* Revert "Set overlaps_ignore"

This reverts commit 65adeff1f89af62b10c691e7aa86c04fc358d03e.

* Set result size

* Set label image size

* Take ignore-color into account

* Fix the cropping rect's aspect ratio; also slightly expand the rect

* Draw the largest findings last

* Improve masking of the current instance

* Add some perturbation to the inputs

* Simplify ground-truth reading; fix random cropping

* Read even class labels

* Tweak default minibatch size

* Learn only one class

* Really train only instances of the selected class

* Remove outdated TODO remark

* Automatically skip images with no detections

* Print to console what was found

* Fix class index problem

* Fix indentation

* Allow to choose multiple classes

* Draw rect in the color of the corresponding class

* Write detector window classes to ostream; also group detection windows by class (when ostreaming)

* Train a separate instance segmentation network for each classlabel

* Use separate synchronization file for each seg net of each class

* Allow more overlap

* Fix sorting criterion

* Fix interpolating the predicted mask

* Improve bilinear interpolation: if output type is an integer, round instead of truncating

* Add helpful comments

* Ignore large aspect ratios; refactor the code; tweak some network parameters

* Simplify the segmentation network structure; make the object detection network more complex in turn

* Problem: CUDA errors not reported properly to console
Solution: stop and join data loader threads even in case of exceptions

* Minor parameters tweaking

* Loss may have increased, even if prob_loss_increasing_thresh > prob_loss_increasing_thresh_max_value

* Add previous_loss_values_dump_amount to previous_loss_values.size() when deciding if loss has been increasing

* Improve behaviour when loss actually increased after disk sync

* Revert some of the earlier change

* Disregard dumped loss values only when deciding if learning rate should be shrunk, but *not* when deciding if loss has been going up since last disk sync

* Revert "Revert some of the earlier change"

This reverts commit 6c852124efe6473a5c962de0091709129d6fcde3.

* Keep enough previous loss values, until the disk sync

* Fix maintaining the dumped (now "effectively disregarded") loss values count

* Detect cats instead of aeroplanes

* Add helpful logging

* Clarify the intention and the code

* Review fixes

* Add operator== for the other pixel types as well; remove the inline

* If available, use constexpr if

* Revert "If available, use constexpr if"

This reverts commit 503d4dd3355ff8ad613116e3ffcc0fa664674f69.

* Simplify code as per review comments

* Keep estimating steps_without_progress, even if steps_since_last_learning_rate_shrink < iter_without_progress_thresh

* Clarify console output

* Revert "Keep estimating steps_without_progress, even if steps_since_last_learning_rate_shrink < iter_without_progress_thresh"

This reverts commit 9191ebc7762d17d81cdfc334a80ca9a667365740.

* To keep the changes to a bare minimum, revert the steps_since_last_learning_rate_shrink change after all (at least for now)

* Even empty out some of the previous test loss values

* Minor review fixes

* Can't use C++14 features here

* Do not use the struct name as a variable name

* 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 example of semantic segmentation using the PASCAL VOC2012 dataset

* Add note about Debug Information Format when using MSVC

* Make the upsampling layers residual as well

* Fix declaration order

* Use a wider net

* trainer.set_iterations_without_progress_threshold(5000); // (was 20000)

* Add residual_up

* Process entire directories of images (just easier to use)

* Simplify network structure so that builds finish even on Visual Studio (faster, or at all)

* Remove the training example from CMakeLists, because it's too much for the 32-bit MSVC++ compiler to handle

* Remove the probably-now-unnecessary set_dnn_prefer_smallest_algorithms call

* Review fix: remove the batch normalization layer from right before the loss

* Review fix: point out that only the Visual C++ compiler has problems.
Also expand the instructions how to run MSBuild.exe to circumvent the problems.

* Review fix: use dlib::match_endings

* Review fix: use dlib::join_rows. Also add some comments, and instructions where to download the pre-trained net from.

* Review fix: make formatting comply with dlib style conventions.

* Review fix: output training parameters.

* Review fix: remove #ifndef __INTELLISENSE__

* Review fix: use std::string instead of char*

* Review fix: update interpolation_abstract.h to say that extract_image_chips can now take the interpolation method as a parameter

* Fix whitespace formatting

* Add more comments

* Fix finding image files for inference

* Resize inference test output to the size of the input; add clarifying remarks

* Resize net output even in calculate_accuracy

* After all crop the net output instead of resizing it by interpolation

* For clarity, add an empty line in the console output