[ Test ] Mixed Precision Test Case

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 [ ]Skipped
2. Run test:	 [X]Passed [ ]Failed [ ]Skipped

Signed-off-by: jijoong.moon <[email protected]>

Applications/KNN/jni/meson.build

@@ -15,4 +15,4 @@ e = executable('knn_sample',
   install_dir: application_install_dir
 )
 
-test('app_knn', e, args: [nntr_app_resdir / 'KNN'])
+test('app_knn', e, args: [nntr_app_resdir / 'KNN/'])

test/unittest/models/meson.build

@@ -11,6 +11,10 @@ models_targets = [
   # disable temperally
 ]
 
+if get_option('enable-fp16')
+   models_targets += 'unittest_models_mixed_precision.cpp'
+endif
+
 test_target += models_targets
 exe = executable(
   test_name,

test/unittest/models/unittest_models_mixed_precision.cpp

@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: Apache-2.0
+/**
+ * Copyright (C) 2024 Jijoong Moon <[email protected]>
+ *
+ * @file unittest_models_mixed_precision.cpp
+ * @date 3 May 2024
+ * @brief unittest models to cover mixed precision
+ * @see	https://github.com/nnstreamer/nntrainer
+ * @author Jijoong Moon <[email protected]>
+ * @bug No known bugs except for NYI items
+ */
+
+#include <gtest/gtest.h>
+
+#include <memory>
+
+#include <ini_wrapper.h>
+#include <neuralnet.h>
+#include <nntrainer_test_util.h>
+
+#include <models_golden_test.h>
+
+using namespace nntrainer;
+
+static std::unique_ptr<NeuralNetwork> fc_mixed_training() {
+  std::unique_ptr<NeuralNetwork> nn(new NeuralNetwork());
+  nn->setProperty(
+    {"batch_size=2", "model_tensor_type=FP16-FP16", "loss_scale=128"});
+
+  auto graph = makeGraph({
+    {"input", {"name=in", "input_shape=1:1:3"}},
+    {"Fully_connected", {"name=fc", "input_layers=in", "unit=10"}},
+    {"mse", {"name=loss", "input_layers=fc"}},
+  });
+  for (auto &node : graph) {
+    nn->addLayer(node);
+  }
+
+  nn->setOptimizer(ml::train::createOptimizer("adam", {"learning_rate = 0.1"}));
+
+  return nn;
+}
+
+GTEST_PARAMETER_TEST(
+  MixedPrecision, nntrainerModelTest,
+  ::testing::ValuesIn({
+    mkModelTc_V2(fc_mixed_training, "fc_mixed_training",
+                 ModelTestOption::NO_THROW_RUN_V2),
+    /** ModelTestOption::ALL_V2),
+     * Disabled for now to check
+     */
+  }),
+  [](const testing::TestParamInfo<nntrainerModelTest::ParamType> &info)
+    -> const auto & { return std::get<1>(info.param); });