|
tiny_dnn 1.0.0
A header only, dependency-free deep learning framework in C++11
|
| ▼Nmodels | |
| Calexnet | |
| ▼Ntiny_dnn | |
| ►Nactivation | |
| ►Ncore | |
| ►Ndetail | |
| ►Nweight_init | |
| Cabsolute | |
| Cabsolute_eps | |
| Cadagrad | Adaptive gradient method |
| Cadam | [a new optimizer (2015)] |
| ►Caligned_allocator | |
| Caverage_pooling_layer | Average pooling with trainable weights |
| Caverage_unpooling_layer | Average pooling with trainable weights |
| Cbatch_normalization_layer | Batch Normalization |
| Cblocked_range | |
| Cconcat_layer | Concat N layers along depth |
| CConv2dGradOp | |
| CConv2dLibDNNBackwardOp | |
| CConv2dLibDNNForwardOp | |
| CConv2dOp | |
| CConv2dOpenCLBackwardOp | |
| CConv2dOpenCLForwardOp | |
| Cconvolutional_layer | 2D convolution layer |
| Ccross_entropy | |
| Ccross_entropy_multiclass | |
| Cdeconvolutional_layer | 2D deconvolution layer |
| Cdeserialization_helper | |
| CDevice | |
| Cdropout_layer | Applies dropout to the input |
| Cedge | Class containing input/output data |
| Celementwise_add_layer | Element-wise add N vectors y_i = x0_i + x1_i + ... + xnum_i |
| Cfeedforward_layer | Single-input, single-output network with activation function |
| Cfully_connected_layer | Compute fully-connected(matmul) operation |
| CFullyConnectedGradOp | |
| CFullyConnectedOp | |
| Cgradient_descent | SGD without momentum |
| Cgraph | Generic graph network |
| Cgraph_visualizer | Utility for graph visualization |
| Cimage | Simple image utility class |
| Cindex3d | |
| Cinput_layer | |
| Clayer | Base class of all kind of NN layers |
| Clinear_layer | Element-wise operation: f(x) = h(scale*x+bias) |
| Clrn_layer | Local response normalization |
| Cmax_pooling_layer | Applies max-pooing operaton to the spatial data |
| Cmax_unpooling_layer | Applies max-pooing operaton to the spatial data |
| CMaxPoolGradOp | |
| CMaxPoolOp | |
| Cmomentum | SGD with momentum |
| Cmse | |
| Cnetwork | A model of neural networks in tiny-dnn |
| Cnn_error | Error exception class for tiny-dnn |
| Cnn_info | Info class for tiny-dnn (for debug) |
| Cnn_not_implemented_error | |
| Cnn_warn | Warning class for tiny-dnn (for debug) |
| Cnode | Base class of all kind of tinny-cnn data |
| Cnode_tuple | |
| Cnodes | Basic class of various network types (sequential, multi-in/multi-out) |
| Coptimizer | Base class of optimizer usesHessian : true if an optimizer uses hessian (2nd order derivative of loss function) |
| Cpartial_connected_layer | |
| Cpower_layer | Element-wise pow: y = scale*x^factor |
| CProgram | |
| CProgramHash | |
| CProgramManager | |
| Cprogress_display | |
| Cquantized_convolutional_layer | 2D convolution layer |
| Cquantized_deconvolutional_layer | 2D deconvolution layer |
| Cquantized_fully_connected_layer | Compute fully-connected(matmul) operation |
| Crandom_generator | |
| Cresult | |
| CRMSprop | RMSprop |
| Csequential | Single-input, single-output feedforward network |
| Cserialization_helper | |
| Cslice_layer | Slice an input data into multiple outputs along a given slice dimension |
| Cstateful_optimizer | |
| CTensor | |
| Ctimer | |
| ▼Nvectorize | |
| ►Ndetail | |
| Cfoobar |
1.9.8