update with model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+results/Lukashenko_tarakan/variables/variables.data-00000-of-00001 filter=lfs diff=lfs merge=lfs -text

model_from_saved.py

@@ -0,0 +1,77 @@
+import tensorflow as tf
+import copy
+import numpy as np
+
+
+def generate_from_saved():
+    # add the start generation of the lukashenko speech from the simple seed
+    seed_text = 'я не глядя поддержу'
+    weights_path = 'results/weights_lukash.h5'
+    model_path = 'results/Lukashenko_tarakan'
+
+    model = tf.keras.models.load_model(model_path)
+    model.load_weights(weights_path)
+    # Show the Model summary
+    model.summary()
+
+    with open('data/source_text_lukash.txt', 'r') as source_text_file:
+        data = source_text_file.read().splitlines()
+
+    tmp_data = copy.deepcopy(data)
+    sent_length = 0
+    for idx, line in enumerate(data):
+        if len(line) < 5:
+            tmp_data.pop(idx)
+        else:
+            sent_length += len(line.split())
+    data = tmp_data
+    lstm_length = int(sent_length / len(data))
+
+    token = tf.keras.preprocessing.text.Tokenizer()
+    token.fit_on_texts(data)
+    encoded_text = token.texts_to_sequences(data)
+    # Vocabular size
+    vocab_size = len(token.word_counts) + 1
+
+    datalist = []
+    for d in encoded_text:
+        if len(d) > 1:
+            for i in range(2, len(d)):
+                datalist.append(d[:i])
+
+    max_length = 20
+    sequences = tf.keras.preprocessing.sequence.pad_sequences(datalist, maxlen=max_length, padding='pre')
+
+    # X - input data, y - target data
+    X = sequences[:, :-1]
+    y = sequences[:, -1]
+
+    y = tf.keras.utils.to_categorical(y, num_classes=vocab_size)
+    seq_length = X.shape[1]
+    print(f"Sequence length: {seq_length}")
+
+    generated_text = ''
+    number_lines = 3
+    for i in range(number_lines):
+        text_word_list = []
+        for _ in range(lstm_length * 2):
+            encoded = token.texts_to_sequences([seed_text])
+            encoded = tf.keras.preprocessing.sequence.pad_sequences(encoded, maxlen=seq_length, padding='pre')
+
+            y_pred = np.argmax(model.predict(encoded), axis=-1)
+
+            predicted_word = ""
+            for word, index in token.word_index.items():
+                if index == y_pred:
+                    predicted_word = word
+                    break
+
+            seed_text = seed_text + ' ' + predicted_word
+            text_word_list.append(predicted_word)
+
+        seed_text = text_word_list [-1]
+        generated_text = ' '.join(text_word_list)
+        generated_text += '\n'
+
+    print(f"Lukashenko are saying: {generated_text}")
+    return generated_text

results/Lukashenko_tarakan/fingerprint.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:079dd29ab6262d35662d96e408bf00d508ad36dbfc9017de7d82436c2985b8c7
+size 55

results/Lukashenko_tarakan/keras_metadata.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec6e4a91836f74caa79e8ec8c6801ad84930127148d209fe9135ece7039ba1aa
+size 17234

results/Lukashenko_tarakan/saved_model.pb

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:828577b478f24668800d2c8340b3b37142c5111effd706f21de4c9e44b544c29
+size 898564

results/Lukashenko_tarakan/variables/variables.data-00000-of-00001

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2d041fdd8e26762137da4a033b417ae7e4fff0b5be76089e5cdc112ff7553c2
+size 7674664

results/config_lukash.json

@@ -0,0 +1 @@
+{"name": "sequential", "layers": [{"module": "keras.layers", "class_name": "InputLayer", "config": {"batch_input_shape": [null, 19], "dtype": "float32", "sparse": false, "ragged": false, "name": "embedding_input"}, "registered_name": null}, {"module": "keras.layers", "class_name": "Embedding", "config": {"name": "embedding", "trainable": true, "dtype": "float32", "batch_input_shape": [null, 19], "input_dim": 6269, "output_dim": 48, "embeddings_initializer": {"module": "keras.initializers", "class_name": "RandomUniform", "config": {"minval": -0.05, "maxval": 0.05, "seed": null}, "registered_name": null}, "embeddings_regularizer": null, "activity_regularizer": null, "embeddings_constraint": null, "mask_zero": false, "input_length": 19}, "registered_name": null, "build_config": {"input_shape": [null, 19]}}, {"module": "keras.layers", "class_name": "LSTM", "config": {"name": "lstm", "trainable": true, "dtype": "float32", "return_sequences": true, "return_state": false, "go_backwards": false, "stateful": false, "unroll": false, "time_major": false, "units": 48, "activation": "tanh", "recurrent_activation": "sigmoid", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "recurrent_initializer": {"module": "keras.initializers", "class_name": "Orthogonal", "config": {"gain": 1.0, "seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "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": 2}, "registered_name": null, "build_config": {"input_shape": [null, 19, 48]}}, {"module": "keras.layers", "class_name": "LSTM", "config": {"name": "lstm_1", "trainable": true, "dtype": "float32", "return_sequences": false, "return_state": false, "go_backwards": false, "stateful": false, "unroll": false, "time_major": false, "units": 32, "activation": "relu", "recurrent_activation": "sigmoid", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "recurrent_initializer": {"module": "keras.initializers", "class_name": "Orthogonal", "config": {"gain": 1.0, "seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "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": 2}, "registered_name": null, "build_config": {"input_shape": [null, 19, 48]}}, {"module": "keras.layers", "class_name": "Dense", "config": {"name": "dense", "trainable": true, "dtype": "float32", "units": 48, "activation": "relu", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "registered_name": null, "build_config": {"input_shape": [null, 32]}}, {"module": "keras.layers", "class_name": "Dense", "config": {"name": "dense_1", "trainable": true, "dtype": "float32", "units": 6269, "activation": "softmax", "use_bias": true, "kernel_initializer": {"module": "keras.initializers", "class_name": "GlorotUniform", "config": {"seed": null}, "registered_name": null}, "bias_initializer": {"module": "keras.initializers", "class_name": "Zeros", "config": {}, "registered_name": null}, "kernel_regularizer": null, "bias_regularizer": null, "activity_regularizer": null, "kernel_constraint": null, "bias_constraint": null}, "registered_name": null, "build_config": {"input_shape": [null, 48]}}]}

results/weights_lukash.h5

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e370d4a3df876823e059affbd2f4a3ce3756cb9c841e4d2c82d206d5ce5dcdc
+size 7721620