Tensorflow

import tensorflow as tf

mnist = tf.keras.datasets.mnist

(xTrain, yTrain), (xTest, yTest) = mnist.load_data()

xTrain, xTest = xTrain / 255, xTest / 255

network = tf.keras.models.Sequential([
  tf.keras.layers.Flatten(input_shape=(28, 28)),
  tf.keras.layers.Dense(128, activation='relu'),
  tf.keras.layers.Dense(10, activation="sigmoid")
])

predictions = network(xTrain[:1]).numpy()

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

loss(yTrain[:1], predictions).numpy()

network.compile("adam", loss, ["accuracy"])

network.fit(xTrain, yTrain, epochs=5)

network.evaluate(xTest, yTest, verbose=2)

Tensorflow

python3 -m pip install --upgrade https://storage.googleapis.com/tensorflow/mac/cpu/tensorflow-1.12.0-py3-none-any.whl

Similar codes

0 vote381 views1 answer
A new PowerShell stable release is available
Shell/Bash
0 vote380 views1 answer
To configure msmtp, let’s create a file .msmtprc in the current user home directory:
Shell/Bash
0 vote347 views1 answer
GetCityNameByLatitudeLongitude
Shell/Bash
25 votes386 views6 answers
Git push existing repo
Shell/Bash
0 vote348 views1 answer
Kubernetes get crd and their namespaces
Shell/Bash
37 votes376 views2 answers
Ubuntu pip3
Shell/Bash
0 vote386 views1 answer
Hp probook 6560b hackintosh
Shell/Bash
1 vote333 views1 answer
Kubernetes combine logs all replicas
Shell/Bash
1 vote376 views1 answer
Dos2unix recursive
Shell/Bash
8 votes365 views3 answers
Error: Node Sass does not yet support your current environment: Linux 64-bit with Unsupported runtime (83)
Shell/Bash