Tensorflow GPU example (code)

The deep learning developer use pytorch a lot when coding deep learning, but I also use tensorflow a lot.

Sometimes I want to see if tensorflow works well on GPU after setting up the GPU,
If you paste the code below and run it, you can see if tensorflow works well.

Python code (below)

import tensorflow as tf
print("TensorFlow version:", tf.__version__)

mnist = tf.keras.datasets.mnist

(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0

model = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dropout(0.2),
  tf.keras.layers.Dense(10, activation='softmax')
])

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

predictions = model(x_train[:1]).numpy()
predictions

tf.nn.softmax(predictions).numpy()

loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)

loss_fn(y_train[:1], predictions).numpy()

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

model.fit(x_train, y_train, epochs=5)

model.evaluate(x_test,  y_test, verbose=2)

probability_model = tf.keras.Sequential([
  model,
  tf.keras.layers.Softmax()
])

probability_model(x_test[:5])

You can also use the command below to monitor if your data is being served to the GPU.

$ nvidia-smi -l
$ watch -n.5 nvidia-smi