Even if NNtariner runs on device, it provides full functionalities to train models and also utilizes limited device resources efficiently. NNTrainer is able to train various machine learning algorithms such as k-Nearest Neighbor (k-NN), Neural Networks, Logistic Regression, Reinforcement Learning algorithms, Recurrent network and more. We also provide examples for various tasks such as Few-shot learning, ResNet, VGG, Product Rating and more will be added. All of these were tested on Samsung Galaxy smart phone with Android and PC (Ubuntu 18.04/20.04).
-[ NNTraner: Light-Weight On-Device Training Framework ](https://arxiv.org/pdf/2206.04688.pdf), arXiv, 2022 <br />
+[ NNTrainer: Light-Weight On-Device Training Framework ](https://arxiv.org/pdf/2206.04688.pdf), arXiv, 2022 <br />
[ NNTrainer: Towards the on-device learning for personalization ](https://www.youtube.com/watch?v=HWiV7WbIM3E), Samsung Software Developer Conference 2021 (Korean) <br />
[ NNTrainer: Personalize neural networks on devices! ](https://www.youtube.com/watch?v=HKKowY78P1A), Samsung Developer Conference 2021 <br />
[ NNTrainer: "On-device learning" ](https://www.youtube.com/embed/Jy_auavraKg?start=4035&end=4080), Samsung AI Forum 2021
| pooling2D | Pooling2DLayer | Pooling 2D layer |
| input | InputLayer | Input Layer. This is not always required. |
| batch_normalization | BatchNormalizationLayer | Batch normalization layer |
+ | layer_normalization | LayerNormalizationLayer | Layer normalization layer |
| activation | ActivaitonLayer | Set by layer property |
| addition | AdditionLayer | Add input input layers |
| attention | AttentionLayer | Attenstion layer |
| concat | ConcatLayer | Concatenate input layers |
| multiout | MultiOutLayer | Multi-Output Layer |
| backbone_nnstreamer | NNStreamerLayer | Encapsulate NNStreamer layer |
- | backbone_tflite | TfLiteLayer | Encapsulate tflite as an layer |
+ | backbone_tflite | TfLiteLayer | Encapsulate tflite as a layer |
| permute | PermuteLayer | Permute layer for transpose |
| preprocess_flip | PreprocessFlipLayer | Preprocess random flip layer |
| preprocess_l2norm | PreprocessL2NormLayer | Preprocess simple l2norm layer to normalize |
| split | SplitLayer | Split layer |
| dropout | DropOutLayer | Dropout Layer |
| embedding | EmbeddingLayer | Embedding Layer |
+ | positional_encoding | PositionalEncodingLayer | Positional Encoding Layer |
| rnn | RNNLayer | Recurrent Layer |
| rnncell | RNNCellLayer | Recurrent Cell Layer |
| gru | GRULayer | Gated Recurrent Unit Layer |
| lstmcell | LSTMCellLayer | Long Short-Term Memory Cell Layer |
| zoneoutlstmcell | ZoneoutLSTMCellLayer | Zoneout Long Short-Term Memory Cell Layer |
| time_dist | TimeDistLayer | Time distributed Layer |
+ | multi_head_attention | MultiHeadAttentionLayer | Multi Head Attention Layer |
+
### Supported Optimizers
| sgd | Stochastic Gradient Decent | - |
| adam | Adaptive Moment Estimation | - |
+ | Keyword | Leanring Rate | Description |
+ |:-------:|:---:|:---:|
+ | exponential | exponential learning rate decay | - |
+ | constant | constant learning rate | - |
+ | step | step learning rate | - |
+
### Supported Loss Functions
NNTrainer provides
| cross_softmax | CrossEntropySoftmaxLossLayer | Cross entropy softmax loss layer |
| constant_derivative | ConstantDerivativeLossLayer | Constant derivative loss layer |
| mse | MSELossLayer | Mean square error loss layer |
+ | kld | KLDLossLayer | Kullback-Leibler Divergence loss layer |
### Supported Activation Functions
| sigmoid | sigmoid function | set as layer property |
| relu | relu function | set as layer propery |
| softmax | softmax function | set as layer propery |
- | weight_initializer | Weight Initialization | Xavier(Normal/Uniform), LeCun(Normal/Uniform), HE(Normal/Unifor) |
- | weight_regularizer | weight decay ( L2Norm only ) | needs set weight_regularizer_param & type |
- | learnig_rate_decay | learning rate decay | need to set step |
### Tensor
| Keyword | Loss Name | Description |
|:-------:|:---:|:---|
| weight_initializer | Weight Initialization | Xavier(Normal/Uniform), LeCun(Normal/Uniform), HE(Normal/Unifor) |
- | weight_regularizer | weight decay ( L2Norm only ) | needs set weight_regularizer_constant & type |
- | learnig_rate_decay | learning rate decay | need to set step |
+ | weight_regularizer | weight decay ( L2Norm only ) | needs set weight_regularizer_param & type |
### APIs
Currently, we provide [C APIs](https://github.com/nnstreamer/nntrainer/blob/master/api/capi/include/nntrainer.h) for Tizen. [C++ APIs](https://github.com/nnstreamer/nntrainer/blob/master/api/ccapi/include) are also provided for other platform. Java & C# APIs will be provided soon.
-### Examples for NNTrainer
-
-#### [Custom Shortcut Application](https://github.com/nnstreamer/nntrainer/tree/main/Applications/Tizen_native/CustomShortcut)
-
-
-A demo application which enable user defined custom shortcut on galaxy watch.
-
-#### [MNIST Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/MNIST)
-
-An example to train mnist dataset. It consists two convolution 2d layer, 2 pooling 2d layer, flatten layer and fully connected layer.
-
-#### [Reinforcement Learning Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/ReinforcementLearning/DeepQ)
-
-A reinforcement learning example with cartpole game. It is using DeepQ algorithm.
-
-#### [Transfer Learning Examples](https://github.com/nnstreamer/nntrainer/tree/main/Applications/TransferLearning)
-
-Transfer learning examples with for image classification using the Cifar 10 dataset and for OCR. TFlite is used for feature extractor and modify last layer (fully connected layer) of network.
-
-#### [ResNet Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/Resnet)
-
-An example to train resnet18 network.
-
-#### [VGG Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/VGG)
-
-An example to train vgg16 network.
-
-#### [ProductRating Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/ProductRatings)
-
-This application contains a simple embedding-based model that predicts ratings given a user and a product.
-
-#### [SimpleShot Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/SimpleShot)
-
-An example to demonstrate few-shot learning : SimpleShot
-
-#### [Custom Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/Custom)
-
-An example to demonstrate how to create custom layers, optimizers or other supported objects.
-
-<!-- #### Tizen CAPI Example -->
-
-<!-- An example to demonstrate c api for Tizen. It is same transfer learing but written with tizen c api.~ -->
-<!-- Deleted instead moved to a [test](https://github.com/nnstreamer/nntrainer/blob/master/test/tizen_capi/unittest_tizen_capi.cpp) -->
-
-#### [KNN Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/KNN)
-
-A transfer learning example with for image classification using the Cifar 10 dataset. TFlite is used for feature extractor and compared with KNN.
-
-#### [Logistic Regression Example](https://github.com/nnstreamer/nntrainer/tree/main/Applications/LogisticRegression)
-
-A logistic regression example using NNTrainer.
-
## [Getting Started](https://github.com/nnstreamer/nntrainer/blob/main/docs/getting-started.md)
Instructions for installing NNTrainer.
Instructions for preparing NNTrainer for execution
+### [Examples for NNTrainer](https://github.com/nnstreamer/nntrainer/tree/main/Applications)
+
+NNTrainer example for a variety of networks
+
## Open Source License
-The nntrainer is an open source project released under the terms of the Apache License version 2.0.
+The NNtrainer is an open source project released under the terms of the Apache License version 2.0.
## Contributing
projects / platform / core / ml / nntrainer.git / blobdiff