working recursive rnn 2

Author: chen0040

keras_text_summarization/demo/models/recursive-rnn-2-architecture.json

@@ -1 +1 @@
-{"class_name": "Model", "config": {"name": "model_1", "layers": [{"name": "input_2", "class_name": "InputLayer", "config": {"batch_input_shape": [null, 4], "dtype": "float32", "sparse": false, "name": "input_2"}, "inbound_nodes": []}, {"name": "embedding_2", "class_name": "Embedding", "config": {"name": "embedding_2", "trainable": true, "batch_input_shape": [null, null], "dtype": "float32", "input_dim": 2001, "output_dim": 128, "embeddings_initializer": {"class_name": "RandomUniform", "config": {"minval": -0.05, "maxval": 0.05, "seed": null}}, "embeddings_regularizer": null, "activity_regularizer": null, "embeddings_constraint": null, "mask_zero": false, "input_length": null}, "inbound_nodes": [[["input_2", 0, 0, {}]]]}, {"name": "input_1", "class_name": "InputLayer", "config": {"batch_input_shape": [null, 500], "dtype": "float32", "sparse": false, "name": "input_1"}, "inbound_nodes": []}, {"name": "dropout_2", "class_name": "Dropout", "config": {"name": "dropout_2", "trainable": true, "rate": 0.3, "noise_shape": null, "seed": null}, "inbound_nodes": [[["embedding_2", 0, 0, {}]]]}, {"name": "embedding_1", "class_name": "Embedding", "config": {"name": "embedding_1", "trainable": true, "batch_input_shape": [null, null], "dtype": "float32", "input_dim": 5002, "output_dim": 128, "embeddings_initializer": {"class_name": "RandomUniform", "config": {"minval": -0.05, "maxval": 0.05, "seed": null}}, "embeddings_regularizer": null, "activity_regularizer": null, "embeddings_constraint": null, "mask_zero": false, "input_length": null}, "inbound_nodes": [[["input_1", 0, 0, {}]]]}, {"name": "lstm_1", "class_name": "LSTM", "config": {"name": "lstm_1", "trainable": true, "return_sequences": false, "return_state": false, "go_backwards": false, "stateful": false, "unroll": false, "units": 128, "activation": "tanh", "recurrent_activation": "hard_sigmoid", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "recurrent_initializer": {"class_name": "Orthogonal", "config": {"gain": 1.0, "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "unit_forget_bias": true, "kernel_regularizer": null, "recurrent_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "recurrent_constraint": null, "bias_constraint": null, "dropout": 0.0, "recurrent_dropout": 0.0, "implementation": 1}, "inbound_nodes": [[["dropout_2", 0, 0, {}]]]}, {"name": "dropout_1", "class_name": "Dropout", "config": {"name": "dropout_1", "trainable": true, "rate": 0.3, "noise_shape": null, "seed": null}, "inbound_nodes": [[["embedding_1", 0, 0, {}]]]}, {"name": "repeat_vector_1", "class_name": "RepeatVector", "config": {"name": "repeat_vector_1", "trainable": true, "n": 500}, "inbound_nodes": [[["lstm_1", 0, 0, {}]]]}, {"name": "concatenate_1", "class_name": "Concatenate", "config": {"name": "concatenate_1", "trainable": true, "axis": -1}, "inbound_nodes": [[["dropout_1", 0, 0, {}], ["repeat_vector_1", 0, 0, {}]]]}, {"name": "lstm_2", "class_name": "LSTM", "config": {"name": "lstm_2", "trainable": true, "return_sequences": false, "return_state": false, "go_backwards": false, "stateful": false, "unroll": false, "units": 128, "activation": "tanh", "recurrent_activation": "hard_sigmoid", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "recurrent_initializer": {"class_name": "Orthogonal", "config": {"gain": 1.0, "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "unit_forget_bias": true, "kernel_regularizer": null, "recurrent_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "recurrent_constraint": null, "bias_constraint": null, "dropout": 0.0, "recurrent_dropout": 0.0, "implementation": 1}, "inbound_nodes": [[["concatenate_1", 0, 0, {}]]]}, {"name": "dense_1", "class_name": "Dense", "config": {"name": "dense_1", "trainable": true, "units": 2001, "activation": "softmax", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "inbound_nodes": [[["lstm_2", 0, 0, {}]]]}], "input_layers": [["input_1", 0, 0], ["input_2", 0, 0]], "output_layers": [["dense_1", 0, 0]]}, "keras_version": "2.1.2", "backend": "tensorflow"}
+{"class_name": "Model", "config": {"name": "model_1", "layers": [{"name": "input_1", "class_name": "InputLayer", "config": {"batch_input_shape": [null, 500], "dtype": "float32", "sparse": false, "name": "input_1"}, "inbound_nodes": []}, {"name": "input_2", "class_name": "InputLayer", "config": {"batch_input_shape": [null, 50], "dtype": "float32", "sparse": false, "name": "input_2"}, "inbound_nodes": []}, {"name": "embedding_1", "class_name": "Embedding", "config": {"name": "embedding_1", "trainable": true, "batch_input_shape": [null, null], "dtype": "float32", "input_dim": 5002, "output_dim": 128, "embeddings_initializer": {"class_name": "RandomUniform", "config": {"minval": -0.05, "maxval": 0.05, "seed": null}}, "embeddings_regularizer": null, "activity_regularizer": null, "embeddings_constraint": null, "mask_zero": false, "input_length": null}, "inbound_nodes": [[["input_1", 0, 0, {}]]]}, {"name": "embedding_2", "class_name": "Embedding", "config": {"name": "embedding_2", "trainable": true, "batch_input_shape": [null, null], "dtype": "float32", "input_dim": 2001, "output_dim": 128, "embeddings_initializer": {"class_name": "RandomUniform", "config": {"minval": -0.05, "maxval": 0.05, "seed": null}}, "embeddings_regularizer": null, "activity_regularizer": null, "embeddings_constraint": null, "mask_zero": false, "input_length": null}, "inbound_nodes": [[["input_2", 0, 0, {}]]]}, {"name": "lstm_1", "class_name": "LSTM", "config": {"name": "lstm_1", "trainable": true, "return_sequences": false, "return_state": false, "go_backwards": false, "stateful": false, "unroll": false, "units": 128, "activation": "tanh", "recurrent_activation": "hard_sigmoid", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "recurrent_initializer": {"class_name": "Orthogonal", "config": {"gain": 1.0, "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "unit_forget_bias": true, "kernel_regularizer": null, "recurrent_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "recurrent_constraint": null, "bias_constraint": null, "dropout": 0.0, "recurrent_dropout": 0.0, "implementation": 1}, "inbound_nodes": [[["embedding_1", 0, 0, {}]]]}, {"name": "lstm_2", "class_name": "LSTM", "config": {"name": "lstm_2", "trainable": true, "return_sequences": false, "return_state": false, "go_backwards": false, "stateful": false, "unroll": false, "units": 128, "activation": "tanh", "recurrent_activation": "hard_sigmoid", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "recurrent_initializer": {"class_name": "Orthogonal", "config": {"gain": 1.0, "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "unit_forget_bias": true, "kernel_regularizer": null, "recurrent_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "recurrent_constraint": null, "bias_constraint": null, "dropout": 0.0, "recurrent_dropout": 0.0, "implementation": 1}, "inbound_nodes": [[["embedding_2", 0, 0, {}]]]}, {"name": "repeat_vector_1", "class_name": "RepeatVector", "config": {"name": "repeat_vector_1", "trainable": true, "n": 128}, "inbound_nodes": [[["lstm_1", 0, 0, {}]]]}, {"name": "repeat_vector_2", "class_name": "RepeatVector", "config": {"name": "repeat_vector_2", "trainable": true, "n": 128}, "inbound_nodes": [[["lstm_2", 0, 0, {}]]]}, {"name": "concatenate_1", "class_name": "Concatenate", "config": {"name": "concatenate_1", "trainable": true, "axis": -1}, "inbound_nodes": [[["repeat_vector_1", 0, 0, {}], ["repeat_vector_2", 0, 0, {}]]]}, {"name": "lstm_3", "class_name": "LSTM", "config": {"name": "lstm_3", "trainable": true, "return_sequences": false, "return_state": false, "go_backwards": false, "stateful": false, "unroll": false, "units": 128, "activation": "tanh", "recurrent_activation": "hard_sigmoid", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "recurrent_initializer": {"class_name": "Orthogonal", "config": {"gain": 1.0, "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "unit_forget_bias": true, "kernel_regularizer": null, "recurrent_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "recurrent_constraint": null, "bias_constraint": null, "dropout": 0.0, "recurrent_dropout": 0.0, "implementation": 1}, "inbound_nodes": [[["concatenate_1", 0, 0, {}]]]}, {"name": "dense_1", "class_name": "Dense", "config": {"name": "dense_1", "trainable": true, "units": 2001, "activation": "softmax", "use_bias": true, "kernel_initializer": {"class_name": "VarianceScaling", "config": {"scale": 1.0, "mode": "fan_avg", "distribution": "uniform", "seed": null}}, "bias_initializer": {"class_name": "Zeros", "config": {}}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "inbound_nodes": [[["lstm_3", 0, 0, {}]]]}], "input_layers": [["input_1", 0, 0], ["input_2", 0, 0]], "output_layers": [["dense_1", 0, 0]]}, "keras_version": "2.1.2", "backend": "tensorflow"}

keras_text_summarization/demo/models/recursive-rnn-2-weights.h5

@@ -0,0 +1,52 @@
+from __future__ import print_function
+
+import pandas as pd
+from sklearn.model_selection import train_test_split
+from keras_text_summarization.library.utility.plot_utils import plot_and_save_history
+from keras_text_summarization.library.rnn import RecursiveRNN3
+from keras_text_summarization.library.applications.fake_news_loader import fit_text
+import numpy as np
+
+LOAD_EXISTING_WEIGHTS = False
+
+
+def main():
+    np.random.seed(42)
+    data_dir_path = './data'
+    report_dir_path = './reports'
+    model_dir_path = './models'
+
+    print('loading csv file ...')
+    df = pd.read_csv(data_dir_path + "/fake_or_real_news.csv")
+
+    # df = df.loc[df.index < 1000]
+
+    print('extract configuration from input texts ...')
+    Y = df.title
+    X = df['text']
+    config = fit_text(X, Y)
+
+    print('configuration extracted from input texts ...')
+
+    summarizer = RecursiveRNN3(config)
+
+    if LOAD_EXISTING_WEIGHTS:
+        weight_file_path = RecursiveRNN2.get_weight_file_path(model_dir_path=model_dir_path)
+        summarizer.load_weights(weight_file_path=weight_file_path)
+
+    Xtrain, Xtest, Ytrain, Ytest = train_test_split(X, Y, test_size=0.2, random_state=42)
+
+    print('demo size: ', len(Xtrain))
+    print('testing size: ', len(Xtest))
+
+    print('start fitting ...')
+    history = summarizer.fit(Xtrain, Ytrain, Xtest, Ytest, epochs=20, batch_size=256)
+
+    history_plot_file_path = report_dir_path + '/' + RecursiveRNN2.model_name + '-history.png'
+    if LOAD_EXISTING_WEIGHTS:
+        history_plot_file_path = report_dir_path + '/' + RecursiveRNN2.model_name + '-history-v' + str(summarizer.version) + '.png'
+    plot_and_save_history(history, summarizer.model_name, history_plot_file_path, metrics={'loss', 'acc'})
+
+
+if __name__ == '__main__':
+    main()