fix unit test.

src/TensorFlowNET.Core/Keras/Engine/Layer.cs

@@ -138,10 +138,6 @@ namespace Tensorflow.Keras.Engine
             {
                 nameScope = name;
             }
-            else
-            {
-                throw new NotImplementedException("");
-            }
 
             // using var graph = tf.keras.backend.get_graph().as_default();
             if (!inputs.IsEagerTensor)

src/TensorFlowNET.Core/Layers/Layer.cs

@@ -83,20 +83,19 @@ namespace Tensorflow.Layers
                     auxiliary_name_scope: false);
             }
 
-            Tensor[] outputs = null;
+            Tensor outputs = null;
             tf_with(scope_context_manager, scope2 =>
             {
                 _current_scope = scope2;
                 // Actually call layer
-                /*outputs = base.Apply(new Tensor[] { inputs }, 
-                    is_training: training);*/
+                outputs = base.Apply(inputs);
             });
 
 
             // Update global default collections.
             _add_elements_to_collection(updates.ToArray(), new string[] { tf.GraphKeys.UPDATE_OPS });
 
-            return outputs;
+            return new Tensor[] { outputs };
         }
 
         protected virtual void _add_elements_to_collection(Operation[] elements, string[] collection_list)

src/TensorFlowNET.Core/Operations/NnOps/BasicLSTMCell.cs

@@ -87,8 +87,8 @@ namespace Tensorflow
                 // array_ops.split(value: state, num_or_size_splits: 2, axis: one);
                 throw new NotImplementedException("BasicLstmCell call");
             }
-            var gate_inputs = math_ops.matmul(array_ops.concat(new[] { inputs, h }, 1), _kernel as RefVariable);
-            gate_inputs = nn_ops.bias_add(gate_inputs, _bias as RefVariable);
+            var gate_inputs = math_ops.matmul(array_ops.concat(new[] { inputs, h }, 1), _kernel.AsTensor());
+            gate_inputs = nn_ops.bias_add(gate_inputs, _bias.AsTensor());
 
             // i = input_gate, j = new_input, f = forget_gate, o = output_gate
             var tensors = array_ops.split(value: gate_inputs, num_split: 4, axis: one);

test/TensorFlowNET.UnitTest/Keras/LayersTest.cs

@@ -52,7 +52,7 @@ namespace TensorFlowNET.UnitTest.Keras
             // Create a `Sequential` model and add a Dense layer as the first layer.
             var model = tf.keras.Sequential();
             model.add(tf.keras.Input(shape: 16));
-            model.add(tf.keras.layers.Dense(32, activation: tf.keras.activations.Relu));
+            model.add(tf.keras.layers.Dense(32, activation: "relu"));
             // Now the model will take as input arrays of shape (None, 16)
             // and output arrays of shape (None, 32).
             // Note that after the first layer, you don't need to specify