Created
March 7, 2025 18:35
-
-
Save nithyadurai87/62c94526e4b8ab25b6c54633ce1036b9 to your computer and use it in GitHub Desktop.
08_Modelbuilding_on_GPU.py
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import numpy as np | |
import tensorflow as tf | |
from tensorflow.keras.preprocessing.text import Tokenizer | |
from tensorflow.keras.models import Sequential | |
from tensorflow.keras.layers import Embedding, LSTM, Dense | |
from tensorflow.keras.preprocessing.sequence import pad_sequences | |
import pickle | |
files = [r'/content/இசை_ஜீனியஸ்_ராஜா_ரவி_நடராஜன்.txt',r'/content/தமிழின்_எதிர்காலமும்_தகவல்_தொழில்நுட்பமும்_இரா_அசோகன்.txt',r'/content/திறந்த_மூல_மென்பொருளில்_முதல்_அடி_எடுத்து_வைக்கலாம்_வாங்க_இரா_அசோகன்.txt',r'/content/தொழிலியல்_விஞ்ஞானி_ஜி_டி_நாயுடு_என்_வி_கலைமணி.txt',r'/content/நான்_இந்துவல்ல_நீங்கள்_தொ_பரமசிவம்.txt'] | |
x = "" | |
for i in files: | |
x += open(i, 'rb').read().decode(encoding='utf-8') | |
x = x.replace('\n', '').replace('\r', '').replace('\ufeff', '').replace('“','').replace('”','') | |
tokens = Tokenizer() | |
tokens.fit_on_texts([x]) | |
pickle.dump(tokens, open('தமிழ்_புத்தகங்கள்_டோக்கன்.pkl', 'wb')) | |
dictionary = tokens.word_index | |
x_n_grams = [] | |
for line in x.split('.'): | |
line_tokens = tokens.texts_to_sequences([line])[0] | |
for i in range(1, len(line_tokens)): | |
n_grams = line_tokens[:i+1] | |
x_n_grams.append(n_grams) | |
max_line_len = max([len(i) for i in x_n_grams]) | |
training_data = np.array(pad_sequences(x_n_grams, maxlen=max_line_len, padding='pre')) | |
train_X = training_data[:, :-1] | |
train_y = training_data[:, -1] | |
total_words = len(dictionary) + 1 | |
print (total_words) | |
y = np.array(tf.keras.utils.to_categorical(train_y, num_classes=total_words)) | |
model = Sequential() | |
model.add(Embedding(total_words, 100, input_length=max_line_len-1)) | |
model.add(LSTM(150)) | |
model.add(Dense(total_words, activation='softmax')) | |
model.build(input_shape=(None, max_line_len-1)) | |
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy']) | |
model.fit(train_X, y, epochs=500, verbose=1) | |
books_model = {'model_json': model.to_json(),'model_weights': model.get_weights()} | |
pickle.dump(books_model, open('தமிழ்_புத்தகங்கள்_மாடல்.pkl', 'wb')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment