TensorFlow Setup

Install the Google TensorFlow machine learning library and create your first model.

Advanced30 min

Setup Steps

1. Python 3.9-3.12 is required

2. Install TensorFlow:

pip install tensorflow

3. For GPU support (NVIDIA CUDA required):

pip install tensorflow[and-cuda]

4. Verify installation:

python3 -c "import tensorflow as tf; print(tf.__version__)"

5. GPU check:

python3 -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"

6. Simple model example:

python
import tensorflow as tf
from tensorflow import keras

model = keras.Sequential([
    keras.layers.Dense(128, activation='relu', input_shape=(784,)),
    keras.layers.Dropout(0.2),
    keras.layers.Dense(10, activation='softmax')
])

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

# Train with MNIST dataset
(x_train, y_train), (x_test, y_test) = keras.datasets.mnist.load_data()
x_train = x_train.reshape(-1, 784) / 255.0
model.fit(x_train, y_train, epochs=5)

7. Save model:

model.save('model.keras')

Related Guides

Python Setup and pip

Install the Python programming language and pip package manager.

Jupyter Notebook Setup

Install Jupyter Notebook and use the interactive Python development environment.

PyTorch Setup

Install the Meta PyTorch deep learning library and learn basic usage.

Conda/Miniconda Setup

Install the Miniconda package and environment manager. Isolate Python environments.