Keras examples for single input and multiple inputs have been added.

examples/keras_multiple_inputs_saved_model.rs

@@ -0,0 +1,51 @@
+use tensorflow::{SessionRunArgs, Graph, SessionOptions, Tensor, SavedModelBundle};
+
+fn main() {
+    // In this file test_in_input is being used while in the python script,
+    // that generates the saved model from Keras model it has a name "test_in".
+    // For multiple inputs _input is not being appended to the op name.
+    let input_1_op_name = "test_in1";
+    let input_2_op_name = "test_in2";
+    let output_op_name = "test_out";
+    let save_dir = "examples/keras_multiple_inputs_saved_model";
+    let v1: Vec<f32> = vec![0.1, 0.2, 0.3, 0.4, 0.5];
+    let v2 = vec![0.6, 0.7, 0.8, 0.9, 0.1];
+    let tensor1 = vector_to_tensor(&v1);
+    let tensor2 = vector_to_tensor(&v2);
+    let mut graph = Graph::new();
+
+    let bundle = SavedModelBundle::load(
+        &SessionOptions::new(),
+        &["serve"],
+        &mut graph,
+        save_dir,
+    ).expect("Can't load saved model");
+
+    let session = &bundle.session;
+
+    let signature = bundle.meta_graph_def().get_signature("serving_default").unwrap();
+    let input_info1 = signature.get_input(input_1_op_name).unwrap();
+    let input_info2 = signature.get_input(input_2_op_name).unwrap();
+    let output_info = signature.get_output(output_op_name).unwrap();
+
+    let input_op1 = graph.operation_by_name_required(&input_info1.name().name).unwrap();
+    let input_op2 = graph.operation_by_name_required(&input_info2.name().name).unwrap();
+    let output_op = graph.operation_by_name_required(&output_info.name().name).unwrap();
+    let mut args = SessionRunArgs::new();
+    args.add_feed(&input_op1, 0, &tensor1);
+    args.add_feed(&input_op2, 0, &tensor2);
+    let out = args.request_fetch(&output_op, 0);
+
+    let result = session.run(&mut args);
+    if result.is_err() {
+        panic!("Error occured during calculations: {:?}", result);
+    }
+    let out_res:f32 = args.fetch(out).unwrap()[0];
+    println!("Results: {:?}", out_res);
+}
+
+pub fn vector_to_tensor(v: &Vec<f32>) -> Tensor<f32> {
+    let dimension = v.len();
+    let tensor = Tensor::new(&[1, dimension as u64]).with_values(&v[..]).unwrap();
+    return tensor;
+}

examples/keras_multiple_inputs_saved_model/keras_multiple_inputs_saved_model.py

@@ -0,0 +1,39 @@
+import tensorflow as tf;
+from tensorflow.python import keras
+from tensorflow.keras import Sequential
+from tensorflow.keras.layers import Dense
+from tensorflow.keras.layers import Input
+from tensorflow.keras.layers import Flatten
+from tensorflow.keras.layers import Concatenate
+from tensorflow.keras import Model
+import numpy as np
+
+
+input = Input((5))
+x = Flatten()(input)
+x = Dense(3,'relu')(x)
+dense = Model(input, x) 
+
+input1 = Input((5), name='test_in1')
+input2 = Input((5), name='test_in2') 
+
+dense1 = dense(input1)
+dense2 = dense(input2) 
+
+merge_layer = Concatenate()([dense1, dense2]) 
+dense_layer = Dense(1, activation="sigmoid", name='test_out')(merge_layer) 
+
+model = Model(inputs=[input1, input2], outputs=dense_layer)
+
+v1 = np.array([[0.1, 0.2, 0.3, 0.4, 0.5]])
+v2 = np.array([[0.6, 0.7, 0.8, 0.9, 0.1]])
+print(v1.shape)
+x1, x2 = np.random.randn(100, 5), np.random.randn(100, 5)
+print(x1.shape)
+y = np.random.randn(100, 1)
+# print(v1.shape)
+# print(v2.shape)
+outputs = np.array([1.0]);
+model.compile(optimizer ='adam',loss='binary_crossentropy', metrics = ['accuracy'])
+model.fit([v1, v2], outputs, epochs=1, batch_size=1)
+model.save('examples/keras_multiple_inputs_saved_model', save_format='tf')

examples/keras_signle_input_saved_model.rs

@@ -0,0 +1,45 @@
+use tensorflow::{SessionRunArgs, Graph, SessionOptions, Tensor, SavedModelBundle};
+
+fn main() {
+    // In this file test_in_input is being used while in the python script,
+    // that generates the saved model from Keras model it has a name "test_in".
+    // For multiple inputs _input is not being appended to the op name.
+    let input_op_name = "test_in_input";
+    let output_op_name = "test_out";
+    let save_dir = "examples/keras_signle_input_saved_model";
+    let v: Vec<f32> = vec![0.1, 0.2, 0.3, 0.4, 0.5];
+
+    let tensor = vector_to_tensor(&v);
+    let mut graph = Graph::new();
+
+    let bundle = SavedModelBundle::load(
+        &SessionOptions::new(),
+        &["serve"],
+        &mut graph,
+        save_dir,
+    ).expect("Can't load saved model");
+
+    let session = &bundle.session;
+
+    let signature = bundle.meta_graph_def().get_signature("serving_default").unwrap();
+    let input_info = signature.get_input(input_op_name).unwrap();
+    let output_info = signature.get_output(output_op_name).unwrap();
+    let input_op = graph.operation_by_name_required(&input_info.name().name).unwrap();
+    let output_op = graph.operation_by_name_required(&output_info.name().name).unwrap();
+    let mut args = SessionRunArgs::new();
+    args.add_feed(&input_op, 0, &tensor);
+    let out = args.request_fetch(&output_op, 0);
+
+    let result = session.run(&mut args);
+    if result.is_err() {
+        panic!("Error occured during calculations: {:?}", result);
+    }
+    let out_res:f32 = args.fetch(out).unwrap()[0];
+    println!("Results: {:?}", out_res);
+}
+
+pub fn vector_to_tensor(v: &Vec<f32>) -> Tensor<f32> {
+    let dimension = v.len();
+    let tensor = Tensor::new(&[1, dimension as u64]).with_values(&v[..]).unwrap();
+    return tensor;
+}

examples/keras_signle_input_saved_model/keras_signle_input_saved_model.py

@@ -0,0 +1,32 @@
+import tensorflow as tf;
+import tensorboard;
+from tensorflow.python import keras
+from tensorflow.keras import Sequential
+from tensorflow.keras.layers import Dense
+
+import json;
+import numpy as np;
+
+
+tensorboard_callback = keras.callbacks.TensorBoard(log_dir="/tmp/logs")
+
+classifier = Sequential()
+classifier.add(Dense(5, activation='relu', kernel_initializer='random_normal', name="test_in", input_dim=5))
+classifier.add(Dense(5, activation='relu'))
+classifier.add(Dense(1, activation='sigmoid', name="test_out"))
+
+
+
+classifier.compile(optimizer ='adam',loss='binary_crossentropy', metrics = ['accuracy'])
+
+
+classifier.fit([[0.1, 0.2, 0.3, 0.4, 0.5]], [[1]], batch_size=1, epochs=1, callbacks=[tensorboard_callback]);
+result = classifier.predict([[0.1, 0.2, 0.3, 0.4, 0.5]])
+
+print(result);
+classifier.summary();
+
+for layer in classifier.layers:
+    print(layer.name)
+
+classifier.save('examples/keras_signle_input_saved_model', save_format='tf')