Jijoong Moon

[Wait for #2574] [ Context ] Add loss scale in Context & using mse loss

1

## In this PR This PR add loss scale parameter in RunLayerContext and use it to update mse loss. . Add Loss Scale Parameter in RunLayerContext Constructor . Add applyLossScale...

[Wait for #2568] [ Tensor ] add is_NaN check in Tensor @open sesame 05/10 14:17

9

## In this PR This PR adds the is_NaN function to check if the tensor has a NaN value. This is for the check of NaN during mixed precision training....

[Wait for #2567] [ Test ] Mixed Precision Test Case

3

## In this PR This PR includes the mixed precision test case. . Input - FC - MSE : "batch_size=2", "model_tensor_type=FP16-FP16", "loss_scale=128" **Self evaluation:** 1. Build test: [X]Passed [ ]Failed...

[Wait for #2566] [ Layers ] Update Layers to support FP16 @open sesame 05/07 15:58

2

## In this PR This PR enables the FP16 support for the layers below: . input layer . mse loss layer Resolves: **Self evaluation:** 1. Build test: [X]Passed [ ]Failed...

[Wait for #2615] Enable Mixed Precision Training in NNTrainer @open sesame 07/04 21:44

6

## In this PR This PR finalizes the mixed precision support in NNTrainer. It modifies the network grap and layer node, and layer implementations. However, it does not support mixed...

[Wait for #2607] [ Layer ] Mixed Precision support for BN Layer

2

## In this PR This PR modify conv2d, lstm, batch normalization layer to support mixed precision. We need FP16 to read and copy to FP32 tensors to support inference and...

[Wait for #2591] [ TEST ] Add more unittest and fixes for mixed precision

7

## In this PR This PR includes more unittest and fixes for mixed precision. . Model Unittest . 2 fc layer which generates NaN or Inf Gradient from Troch. ....

[Wait for #2584] [ TEST ] add torch input and output test data for mixed precision

11

## In this PR This PR adds torch mixed precision golden data generation and input and output for the test. . some fixes to test. Resolves: **Self evaluation:** 1. Build...

[ RMSProp ] add rms prop optimizer

2

## In this PR This PR implements rms prop optimizer. unittest for rms prop is required. . implementation of RMSProp Class . Separate the optimizer properties into optimizer common properties....

[ GPGPU ] enable X86 OpenCL with some fixes

4

This PR enables meson build with opencl for X86. Also, fix some unittest case errors and types. Resolves: **Self evaluation:** 1. Build test: [X]Passed [ ]Failed [ ]Skipped 2. Run...