Fix Model.build.

Author: Oceania2018

src/TensorFlowNET.Console/SimpleRnnTest.cs

@@ -12,20 +12,16 @@ public class SimpleRnnTest
     {
         public void Run()
         {
-            tf.keras = new KerasInterface();
-            var inputs = np.random.random((32, 10, 8)).astype(np.float32);
-            var simple_rnn = tf.keras.layers.SimpleRNN(4);
-            var output = simple_rnn.Apply(inputs);  // The output has shape `[32, 4]`.
-            if (output.shape == (32, 4))
-            {
+            tf.UseKeras<KerasInterface>();
+            var inputs = np.random.random((6, 10, 8)).astype(np.float32);
+            //var simple_rnn = tf.keras.layers.SimpleRNN(4);
+            //var output = simple_rnn.Apply(inputs);  // The output has shape `[32, 4]`.
 
-            }
-            /*simple_rnn = tf.keras.layers.SimpleRNN(
-                4, return_sequences = True, return_state = True)
+            var simple_rnn = tf.keras.layers.SimpleRNN(4, return_sequences: true, return_state: true);
 
-            # whole_sequence_output has shape `[32, 10, 4]`.
-            # final_state has shape `[32, 4]`.
-            whole_sequence_output, final_state = simple_rnn(inputs)*/
+            // whole_sequence_output has shape `[32, 10, 4]`.
+            // final_state has shape `[32, 4]`.
+            var (whole_sequence_output, final_state) = simple_rnn.Apply(inputs);
         }
     }
 }

src/TensorFlowNET.Core/Keras/Layers/ILayer.cs

@@ -9,6 +9,7 @@ public interface ILayer
         string Name { get; }
         bool Trainable { get; }
         bool Built { get; }
+        void build(Shape input_shape);
         List<ILayer> Layers { get; }
         List<INode> InboundNodes { get; }
         List<INode> OutboundNodes { get; }

src/TensorFlowNET.Core/Keras/Layers/ILayersApi.cs

@@ -163,7 +163,9 @@ public ILayer SimpleRNN(int units,
             string activation = "tanh",
             string kernel_initializer = "glorot_uniform",
             string recurrent_initializer = "orthogonal",
-            string bias_initializer = "zeros");
+            string bias_initializer = "zeros",
+            bool return_sequences = false,
+            bool return_state = false);
 
         public ILayer Subtract();
     }

src/TensorFlowNET.Core/Operations/Initializers/Orthogonal.cs

@@ -1,12 +1,32 @@
 using System;
+using System.Linq;
+using static Tensorflow.TensorShapeProto.Types;
 
 namespace Tensorflow.Operations.Initializers
 {
     public class Orthogonal : IInitializer
     {
+        float _gain = 0f;
+
+        public Orthogonal(float gain = 1.0f, int? seed = null)
+        {
+
+        }
+
         public Tensor Apply(InitializerArgs args)
         {
-            throw new NotImplementedException();
+            return _generate_init_val(args.Shape, args.DType);
+        }
+
+        private Tensor _generate_init_val(Shape shape, TF_DataType dtype)
+        {
+            var num_rows = 1L;
+            foreach (var dim in shape.dims.Take(shape.ndim - 1))
+                num_rows *= dim;
+            var num_cols = shape.dims.Last();
+            var flat_shape = (Math.Max(num_cols, num_rows), Math.Min(num_cols, num_rows));
+
+            throw new NotImplementedException("");
         }
     }
 }

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

@@ -147,5 +147,10 @@ public LayerArgs get_config()
         {
             throw new NotImplementedException();
         }
+
+        public void build(Shape input_shape)
+        {
+            throw new NotImplementedException();
+        }
     }
 }

src/TensorFlowNET.Core/tensorflow.cs

@@ -65,6 +65,11 @@ public tensorflow()
             InitGradientEnvironment();
         }
 
+        public void UseKeras<T>() where T : IKerasApi, new()
+        {
+            keras = new T();
+        }
+
         public string VERSION => c_api.StringPiece(c_api.TF_Version());
 
         private void InitGradientEnvironment()

src/TensorFlowNET.Keras/Engine/Functional.cs

@@ -65,7 +65,12 @@ protected void _init_graph_network(Tensors inputs, Tensors outputs)
             }
 
             // Keep track of the network's nodes and layers.
-            (NetworkNodes, NodesByDepth, _self_tracked_trackables, _) = MapGraphNetwork(inputs, outputs);
+            (NetworkNodes, NodesByDepth, var layers, _) = MapGraphNetwork(inputs, outputs);
+
+            if (!_self_tracked_trackables.Any())
+            {
+                _self_tracked_trackables = layers;
+            }
 
             // Build self.input_names and self.output_names.
             _set_output_names();

src/TensorFlowNET.Keras/Engine/Model.Build.cs

@@ -1,9 +1,6 @@
 using System;
 using System.Linq;
 using Tensorflow.Graphs;
-using Tensorflow.Keras.ArgsDefinition;
-using Tensorflow.Keras.Losses;
-using Tensorflow.Keras.Optimizers;
 using static Tensorflow.Binding;
 using static Tensorflow.KerasApi;
 
@@ -13,6 +10,12 @@ public partial class Model
     {
         public override void build(Shape input_shape)
         {
+            if (this is Functional || this is Sequential)
+            {
+                base.build(input_shape);
+                return;
+            }
+
             var graph = tf.executing_eagerly() ? new FuncGraph("build_graph") : keras.backend.get_graph();
 
             graph.as_default();

src/TensorFlowNET.Keras/Engine/Sequential.cs

@@ -122,15 +122,9 @@ public void add(ILayer layer)
             else
             {
                 _self_tracked_trackables.add(layer);
-                _handle_deferred_layer_dependencies(layer);
             }
         }
 
-        void _handle_deferred_layer_dependencies(params ILayer[] layers)
-        {
-            _self_tracked_trackables.AddRange(layers);
-        }
-
         protected override Tensors Call(Tensors inputs, Tensor state = null, bool? training = null)
         {
             if (!_has_explicit_input_shape)
@@ -156,7 +150,7 @@ void _build_graph_network_for_inferred_shape(Shape input_shape, TF_DataType inpu
             ops.init_scope();
             var inputs = keras.Input(batch_input_shape: input_shape,
                 dtype: input_dtype,
-                name: $"{_self_tracked_trackables[0].Name}_input");
+                name: _self_tracked_trackables[0].Name.EndsWith("_input") ? _self_tracked_trackables[0].Name : $"{_self_tracked_trackables[0].Name}_input");
             Tensors layer_input = inputs;
             Tensors layer_output = null;
             Tensors outputs = null;

src/TensorFlowNET.Keras/Layers/LayersApi.cs

@@ -658,14 +658,18 @@ public ILayer SimpleRNN(int units,
             string activation = "tanh",
             string kernel_initializer = "glorot_uniform",
             string recurrent_initializer = "orthogonal",
-            string bias_initializer = "zeros")
+            string bias_initializer = "zeros",
+            bool return_sequences = false,
+            bool return_state = false)
                 => new SimpleRNN(new SimpleRNNArgs
                 {
                     Units = units,
                     Activation = GetActivationByName(activation),
                     KernelInitializer = GetInitializerByName(kernel_initializer),
-                    RecurrentInitializer= GetInitializerByName(recurrent_initializer),
-                    BiasInitializer= GetInitializerByName(bias_initializer)
+                    RecurrentInitializer = GetInitializerByName(recurrent_initializer),
+                    BiasInitializer = GetInitializerByName(bias_initializer),
+                    ReturnSequences = return_sequences,
+                    ReturnState = return_state
                 });
 
         /// <summary>

src/TensorFlowNET.Keras/Layers/Rnn/RNN.cs

@@ -18,7 +18,7 @@ public class RNN : Layer
         private int _num_constants = 0;
         protected IVariableV1 kernel;
         protected IVariableV1 bias;
-
+        protected ILayer cell;
         public RNN(RNNArgs args) : base(PreConstruct(args))
         {
             this.args = args;
@@ -37,6 +37,14 @@ public RNN(RNNArgs args) : base(PreConstruct(args))
             //}
         }
 
+        public override void build(Shape input_shape)
+        {
+            if (!cell.Built)
+            {
+                cell.build(input_shape);
+            }
+        }
+
         private static RNNArgs PreConstruct(RNNArgs args)
         {
             if (args.Kwargs == null)

src/TensorFlowNET.Keras/Layers/Rnn/SimpleRNN.cs

@@ -9,22 +9,10 @@ namespace Tensorflow.Keras.Layers.Rnn
     public class SimpleRNN : RNN
     {
         SimpleRNNArgs args;
-        SimpleRNNCell cell;
         public SimpleRNN(SimpleRNNArgs args) : base(args)
         {
             this.args = args;
-        }
-
-        public override void build(Shape input_shape)
-        {
-            var input_dim = input_shape[-1];
-
-            kernel = add_weight("kernel", (input_shape[-1], args.Units),
-                initializer: args.KernelInitializer
-                //regularizer = self.kernel_regularizer,
-                //constraint = self.kernel_constraint,
-                //caching_device = default_caching_device,
-            );
+            cell = new SimpleRNNCell(args);
         }
     }
 }

src/TensorFlowNET.Keras/Layers/Rnn/SimpleRNNCell.cs

@@ -8,14 +8,36 @@ namespace Tensorflow.Keras.Layers.Rnn
 {
     public class SimpleRNNCell : Layer
     {
+        SimpleRNNArgs args;
+        IVariableV1 kernel;
+        IVariableV1 recurrent_kernel;
+        IVariableV1 bias;
+
         public SimpleRNNCell(SimpleRNNArgs args) : base(args)
         {
-
+            this.args = args;
         }
 
         public override void build(Shape input_shape)
         {
-            
+            var input_dim = input_shape[-1];
+
+            kernel = add_weight("kernel", (input_shape[-1], args.Units),
+                initializer: args.KernelInitializer
+            );
+
+            recurrent_kernel = add_weight("recurrent_kernel", (args.Units, args.Units),
+                initializer: args.RecurrentInitializer
+            );
+
+            if (args.UseBias)
+            {
+                bias = add_weight("bias", (args.Units),
+                    initializer: args.RecurrentInitializer
+                );
+            }
+
+            built = true;
         }
     }
 }

test/TensorFlowNET.Keras.UnitTest/Layers/LayersTest.cs

@@ -150,10 +150,13 @@ public void EinsumDense()
         [TestMethod]
         public void SimpleRNN()
         {
-            var inputs = np.random.random((32, 10, 8)).astype(np.float32);
-            var simple_rnn = keras.layers.SimpleRNN(4);
+            tf.UseKeras<KerasInterface>();
+            var inputs = np.arange(6 * 10 * 8).reshape((6, 10, 8)).astype(np.float32);
+            /*var simple_rnn = keras.layers.SimpleRNN(4);
             var output = simple_rnn.Apply(inputs);
-            Assert.AreEqual((32, 4), output.shape);
+            Assert.AreEqual((32, 4), output.shape);*/
+            var simple_rnn = tf.keras.layers.SimpleRNN(4, return_sequences: true, return_state: true);
+            var (whole_sequence_output, final_state) = simple_rnn.Apply(inputs);
         }
 
         [TestMethod]

test/TensorFlowNET.UnitTest/Tensorflow.Binding.UnitTest.csproj

@@ -47,7 +47,7 @@
 
   <ItemGroup>
     <PackageReference Include="FluentAssertions" Version="5.10.3" />
-    <PackageReference Include="MethodBoundaryAspect.Fody" Version="2.0.144" />
+    <PackageReference Include="MethodBoundaryAspect.Fody" Version="2.0.148" />
     <PackageReference Include="Microsoft.NET.Test.Sdk" Version="17.0.0" />
     <PackageReference Include="MSTest.TestAdapter" Version="2.2.8" />
     <PackageReference Include="MSTest.TestFramework" Version="2.2.8" />