cuv::allocator | |
cuv::default_allocator | Allocator allows allocation, deallocation and copying depending on memory_space_type |
cuv::cuda_allocator | Allocator that uses cudaMallocHost for allocations in host_memory_space |
cuv::pooled_cuda_allocator | Allocator that naively pools device and host memory |
curfil::utils::Average | A simple class used for averaging |
cuv::column_major | Tag for column major matrices |
curfil::ConfusionMatrix | Helper class to maintain a n×n confusion matrix |
curfil::Depth | Wrapper class that represent a depth value as it occurs in RGB-D images |
cuv::dev_memory_space | Tag for device memory |
curfil::DeviceCache | Abstract base class that implements a simple LRU cache on GPU |
curfil::ImageCache | A simple LRU cache of RGB-D images on GPU |
curfil::TreeCache | A simple LRU cache of trees on GPU |
cuv::EnableIfC< B, T > | Enable-if controlled creation of SFINAE conditions |
cuv::EnableIfC< Cond::value, T > | |
cuv::EnableIf< Cond, T > | |
cuv::EnableIfC< false, T > | |
cuv::EnableIfC<!Cond::value, T > | |
cuv::DisableIf< Cond, T > | |
cuv::FalseType | Defines "False" |
cuv::host_memory_space | Tag for host memory |
curfil::HyperoptClient | Client that does a hyperopt parameter search |
cuv::If< Condition, Then, Else > | Switch result depending on Condition |
cuv::If< false, Then, Else > | |
curfil::ImageFeatureEvaluation | Helper class for the four phases in the cost-intensive best-split evaluation during random forest training |
curfil::ImageFeatureFunction | Parametrized visual image feature |
curfil::ImageFeaturesAndThresholds< memory_space > | Helper class to store a list of features and a list of threshold per feature in a compact mannersuch that it can be transferred between CPU and GPU |
curfil::InformationGainScore | Information Gain calculation using Shannon entropy of the parent and child nodes |
curfil::NormalizedInformationGainScore | Information gain normalized by the sum of the classification and split entropies see formula (11) in [Wehenkel1991] and appendix A in [Geurts2006] |
cuv::IsDifferent< T1, T2 > | Checks whether two types are different |
cuv::IsDifferent< T, T > | |
cuv::IsSame< T1, T2 > | Checks whether two types are equal |
cuv::IsSame< T, T > | |
curfil::LabeledRGBDImage | A tuple of a RGBD image and an according labeling |
curfil::LabelImage | A labelling that usually belongs to a RGBImage |
cuv::linear_memory_tag | Tag for linear memory |
cuv::memory< V, M > | Simply keeps a pointer and deallocates it when destroyed |
cuv::linear_memory< V, M > | Contiguous memory |
cuv::pitched_memory< V, M > | 2D non-contiguous ("pitched") memory |
cuv::ndarray< V, M, L > | N-dimensional array on GPU or CPU |
cuv::ndarray_view< V, M, L > | Primarily used as result of ndarray::operator[] |
cuv::ndarray_info< M, L > | Infos about shape and stride on host and in the ndarray data space |
cuv::pitched_memory_tag | Tag for pitched memory |
curfil::PixelInstance | Represents a single-pixel sample in a RGB-D image |
curfil::utils::Profile | Used to profile different stages of training and prediction |
curfil::RandomForestImage | A random forest for RGB-D images |
curfil::RandomSource | Used to get a uniform sampler after incrementing the seed |
curfil::RandomTree< Instance, FeatureFunction > | A sub-tree with histograms and pointers to the parent and children |
curfil::RandomTreeExport | Helper class to export a random tree or random forest to disk in compressed (gzip) JSON format |
curfil::RandomTreeImage | A random tree in a random forest, for RGB-D images |
curfil::RandomTreeImport | Helper class to import a random tree or random forest from disk in compressed (gzip) JSON format |
curfil::RandomTreeTrain< Instance, FeatureEvaluation, FeatureFunction > | Class that does the actual training of a tree |
cuv::reference< T, M > | This objects acts like a reference to the object stored at the wrapped pointer |
curfil::ReservoirSampler< T > | Stores samples (images or pixel instances), if max size is reached, a sample replaces another chosen at random |
curfil::Result | Class that stores the results of a hyperopt run |
curfil::RGBColor | A tuple of three 8-bit uints that represent a RGB color value |
curfil::RGBDImage | An RGB-D image that contains four channels for the RGB color and the depth |
cuv::row_major | Tag for row major matrices |
curfil::Sampler | A uniform distribution sampler |
curfil::Samples< memory_space > | Helper class to store a list of pixel instances in a compact mannersuch that it can be transferred between CPU and GPU |
curfil::SplitFunction< Instance, FeatureFunction > | Class used to get the splitting score for a given feature and threshold |
cuv::switch_memory_layout_type< Mat, NewML > | Create a ndarray type with the same template parameters, but with switched memory_layout_type |
cuv::switch_memory_space_type< Mat, NewMS > | Create a ndarray type with the same template parameters, but with switched memory_space_type |
cuv::switch_value_type< Mat, NewVT > | Create a ndarray type with the same template parameters, but with switched value type |
curfil::utils::Timer | Used to get seconds or milliseconds passed for profiling purposes |
curfil::TrainingConfiguration | Parameters used for training, most of which are provided by the user |
curfil::TreeNodeData | Helper class for the unit test |
curfil::TreeNodes | Helper class to map random forest data to texture cache on GPU |
cuv::TrueType | Defines "True" |
cuv::unconst< T > | Remove "const" from a type |
cuv::unconst< const T > | |
curfil::XY | A simple 2D tuple |