Download src/train_model.py from mikahniehaus/fist_tensorflow_project: direct link, hf CLI and curl.
- Browser
- Download file 3.87 kB
-
https://huggingface.co/mikahniehaus/fist_tensorflow_project/resolve/main/src/train_model.py
- Command line
-
hf download hf://mikahniehaus/fist_tensorflow_project/src/train_model.py
-
curl -L -o train_model.py https://huggingface.co/mikahniehaus/fist_tensorflow_project/resolve/main/src/train_model.py
3.87 kB
| import tensorflow as tf | |
| import pandas as pd | |
| import numpy as np | |
| import matplotlib.pyplot as plt | |
| from tensorflow.keras.preprocessing.text import Tokenizer | |
| from tensorflow.keras.preprocessing.sequence import pad_sequences | |
| # Ensure TensorFlow uses GPU if available | |
| physical_devices = tf.config.experimental.list_physical_devices('GPU') | |
| if physical_devices: | |
| tf.config.experimental.set_memory_growth(physical_devices[0], True) | |
| print("GPU is available and will be used.") | |
| else: | |
| print("No GPU found. Using CPU.") | |
| # Load IMDb dataset | |
| df = pd.read_csv("dataset/imdb.csv") | |
| # Check column names | |
| print("Dataset columns:", df.columns) | |
| # Rename columns if needed | |
| df.rename(columns={'review': 'text', 'sentiment': 'label'}, inplace=True) | |
| # Convert labels to binary (positive = 1, negative = 0) | |
| df['label'] = df['label'].apply(lambda x: 1 if x.strip().lower() == 'positive' else 0) | |
| # Tokenize text | |
| tokenizer = Tokenizer(num_words=20000, oov_token="<OOV>") # Increased vocab size | |
| tokenizer.fit_on_texts(df['text']) | |
| sequences = tokenizer.texts_to_sequences(df['text']) | |
| padded_sequences = pad_sequences(sequences, maxlen=250) # Increased max length | |
| # Split data | |
| X_train, y_train = padded_sequences[:20000], df['label'][:20000] | |
| X_test, y_test = padded_sequences[20000:], df['label'][20000:] | |
| # Build a more complex neural network model | |
| model = tf.keras.Sequential([ | |
| tf.keras.layers.Embedding(20000, 64, input_length=250), # Larger embedding space | |
| tf.keras.layers.Conv1D(128, 5, activation='relu'), | |
| tf.keras.layers.MaxPooling1D(pool_size=2), | |
| tf.keras.layers.LSTM(128, return_sequences=True), | |
| tf.keras.layers.LSTM(64), | |
| tf.keras.layers.Dense(64, activation='relu'), | |
| tf.keras.layers.Dense(1, activation='sigmoid') | |
| ]) | |
| # Compile model | |
| model.compile(optimizer='adam', loss='binary_crossentropy', metrics=['accuracy']) | |
| # Train model epochs | |
| epochs = 5 | |
| history = model.fit(X_train, y_train, epochs=epochs, validation_data=(X_test, y_test), batch_size=128) | |
| # Save the final trained model | |
| model.save("src/sentiment_model_final.h5") | |
| # Save intermediate models every 10 epochs | |
| for i in range(10, epochs + 1, 10): | |
| model.save(f"src/sentiment_model_epoch_{i}.h5") | |
| # Plot detailed training loss and accuracy with smoothing | |
| def smooth_curve(points, factor=0.8): | |
| """Applies exponential moving average smoothing to a curve.""" | |
| smoothed_points = [] | |
| for point in points: | |
| if smoothed_points: | |
| smoothed_points.append(smoothed_points[-1] * factor + point * (1 - factor)) | |
| else: | |
| smoothed_points.append(point) | |
| return smoothed_points | |
| plt.figure(figsize=(12, 6)) | |
| # Loss Plot | |
| plt.subplot(1, 2, 1) | |
| plt.plot(range(epochs), history.history['loss'], label='Training Loss', marker='o', alpha=0.3) | |
| plt.plot(range(epochs), history.history['val_loss'], label='Validation Loss', marker='o', alpha=0.3) | |
| plt.plot(range(epochs), smooth_curve(history.history['loss']), label='Smoothed Training Loss', linewidth=2) | |
| plt.plot(range(epochs), smooth_curve(history.history['val_loss']), label='Smoothed Validation Loss', linewidth=2) | |
| plt.xlabel("Epochs") | |
| plt.ylabel("Loss") | |
| plt.legend() | |
| plt.title("Training vs. Validation Loss (Detailed)") | |
| # Accuracy Plot | |
| plt.subplot(1, 2, 2) | |
| plt.plot(range(epochs), history.history['accuracy'], label='Training Accuracy', marker='o', alpha=0.3) | |
| plt.plot(range(epochs), history.history['val_accuracy'], label='Validation Accuracy', marker='o', alpha=0.3) | |
| plt.plot(range(epochs), smooth_curve(history.history['accuracy']), label='Smoothed Training Accuracy', linewidth=2) | |
| plt.plot(range(epochs), smooth_curve(history.history['val_accuracy']), label='Smoothed Validation Accuracy', linewidth=2) | |
| plt.xlabel("Epochs") | |
| plt.ylabel("Accuracy") | |
| plt.legend() | |
| plt.title("Training vs. Validation Accuracy (Detailed)") | |
| # Save and show graph | |
| plt.savefig("src/training_results_detailed.png") | |
| plt.show() | |