CoCalc Logo Icon
StoreFeaturesDocsShareSupportNewsAboutSign UpSign In
better-data-science

CoCalc provides the best real-time collaborative environment for Jupyter Notebooks, LaTeX documents, and SageMath, scalable from individual users to large groups and classes!

GitHub Repository: better-data-science/TensorFlow
 Path: blob/main/001_TensorFlow_Test.ipynb
Views: 47
Kernel: Python 3 (ipykernel)

001 - TensorFlow Installation Test

Imports

import tensorflow as tf
tf.__version__
Init Plugin
'2.5.0'
Init Graph Optimizer Init Kernel

Available devices for training

tf.config.list_physical_devices()
[PhysicalDevice(name='/physical_device:CPU:0', device_type='CPU'), PhysicalDevice(name='/physical_device:GPU:0', device_type='GPU')]

Dummy dataset

import numpy as np

X = np.arange(1, 101, step=0.1)
y = [x**2 for x in X]

X = tf.cast(tf.constant(X), dtype=tf.float32)
y = tf.cast(tf.constant(y), dtype=tf.float32)
Metal device set to: Apple M1
2021-09-28 07:37:00.881092: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:305] Could not identify NUMA node of platform GPU ID 0, defaulting to 0. Your kernel may not have been built with NUMA support. 2021-09-28 07:37:00.881867: I tensorflow/core/common_runtime/pluggable_device/pluggable_device_factory.cc:271] Created TensorFlow device (/job:localhost/replica:0/task:0/device:GPU:0 with 0 MB memory) -> physical PluggableDevice (device: 0, name: METAL, pci bus id: <undefined>)

Model and training

model = tf.keras.Sequential([
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(1)
])

model.compile(
    loss=tf.keras.losses.mean_absolute_error,
    optimizer=tf.keras.optimizers.Adam(learning_rate=0.1),
    metrics=['mean_absolute_error']
)

model.fit(X, y, epochs=100)
Epoch 1/100 32/32 [==============================] - 0s 4ms/step - loss: 1397.4844 - mean_absolute_error: 1397.4844 Epoch 2/100 1/32 [..............................] - ETA: 0s - loss: 1186.0442 - mean_absolute_error: 1186.0442
2021-09-28 07:40:28.525871: I tensorflow/core/grappler/optimizers/custom_graph_optimizer_registry.cc:112] Plugin optimizer for device_type GPU is enabled.
32/32 [==============================] - 0s 4ms/step - loss: 932.5007 - mean_absolute_error: 932.5007 Epoch 3/100 32/32 [==============================] - 0s 3ms/step - loss: 723.8837 - mean_absolute_error: 723.8837 Epoch 4/100 32/32 [==============================] - 0s 3ms/step - loss: 539.7209 - mean_absolute_error: 539.7209 Epoch 5/100 32/32 [==============================] - 0s 4ms/step - loss: 430.1161 - mean_absolute_error: 430.1161 Epoch 6/100 32/32 [==============================] - 0s 4ms/step - loss: 371.5009 - mean_absolute_error: 371.5009 Epoch 7/100 32/32 [==============================] - 0s 4ms/step - loss: 288.6484 - mean_absolute_error: 288.6484 Epoch 8/100 32/32 [==============================] - 0s 3ms/step - loss: 244.9536 - mean_absolute_error: 244.9536 Epoch 9/100 32/32 [==============================] - 0s 4ms/step - loss: 184.6690 - mean_absolute_error: 184.6690 Epoch 10/100 32/32 [==============================] - 0s 4ms/step - loss: 270.8843 - mean_absolute_error: 270.8843 Epoch 11/100 32/32 [==============================] - 0s 4ms/step - loss: 251.4684 - mean_absolute_error: 251.4684 Epoch 12/100 32/32 [==============================] - 0s 4ms/step - loss: 264.9601 - mean_absolute_error: 264.9601 Epoch 13/100 32/32 [==============================] - 0s 4ms/step - loss: 212.7753 - mean_absolute_error: 212.7753 Epoch 14/100 32/32 [==============================] - 0s 4ms/step - loss: 266.6929 - mean_absolute_error: 266.6929 Epoch 15/100 32/32 [==============================] - 0s 4ms/step - loss: 177.0505 - mean_absolute_error: 177.0505 Epoch 16/100 32/32 [==============================] - 0s 4ms/step - loss: 316.8542 - mean_absolute_error: 316.8542 Epoch 17/100 32/32 [==============================] - 0s 4ms/step - loss: 369.1585 - mean_absolute_error: 369.1585 Epoch 18/100 32/32 [==============================] - 0s 4ms/step - loss: 203.2409 - mean_absolute_error: 203.2409 Epoch 19/100 32/32 [==============================] - 0s 4ms/step - loss: 222.8471 - mean_absolute_error: 222.8471 Epoch 20/100 32/32 [==============================] - 0s 4ms/step - loss: 185.4706 - mean_absolute_error: 185.4706 Epoch 21/100 32/32 [==============================] - 0s 4ms/step - loss: 151.8288 - mean_absolute_error: 151.8288 Epoch 22/100 32/32 [==============================] - 0s 4ms/step - loss: 308.0082 - mean_absolute_error: 308.0082 Epoch 23/100 32/32 [==============================] - 0s 4ms/step - loss: 260.7388 - mean_absolute_error: 260.7388 Epoch 24/100 32/32 [==============================] - 0s 4ms/step - loss: 198.2821 - mean_absolute_error: 198.2821 Epoch 25/100 32/32 [==============================] - 0s 4ms/step - loss: 228.0280 - mean_absolute_error: 228.0280 Epoch 26/100 32/32 [==============================] - 0s 4ms/step - loss: 137.4012 - mean_absolute_error: 137.4012 Epoch 27/100 32/32 [==============================] - 0s 4ms/step - loss: 257.5800 - mean_absolute_error: 257.5800 Epoch 28/100 32/32 [==============================] - 0s 4ms/step - loss: 414.0735 - mean_absolute_error: 414.0735 Epoch 29/100 32/32 [==============================] - 0s 4ms/step - loss: 193.3530 - mean_absolute_error: 193.3530 Epoch 30/100 32/32 [==============================] - 0s 4ms/step - loss: 215.4861 - mean_absolute_error: 215.4861 Epoch 31/100 32/32 [==============================] - 0s 3ms/step - loss: 180.7227 - mean_absolute_error: 180.7227 Epoch 32/100 32/32 [==============================] - 0s 4ms/step - loss: 274.8415 - mean_absolute_error: 274.8415 Epoch 33/100 32/32 [==============================] - 0s 4ms/step - loss: 222.8818 - mean_absolute_error: 222.8818 Epoch 34/100 32/32 [==============================] - 0s 4ms/step - loss: 224.6321 - mean_absolute_error: 224.6321 Epoch 35/100 32/32 [==============================] - 0s 4ms/step - loss: 294.0774 - mean_absolute_error: 294.0774 Epoch 36/100 32/32 [==============================] - 0s 4ms/step - loss: 233.9464 - mean_absolute_error: 233.9464 Epoch 37/100 32/32 [==============================] - 0s 4ms/step - loss: 259.1333 - mean_absolute_error: 259.1333 Epoch 38/100 32/32 [==============================] - 0s 4ms/step - loss: 196.5505 - mean_absolute_error: 196.5505 Epoch 39/100 32/32 [==============================] - 0s 4ms/step - loss: 140.2408 - mean_absolute_error: 140.2408 Epoch 40/100 32/32 [==============================] - 0s 4ms/step - loss: 126.6778 - mean_absolute_error: 126.6778 Epoch 41/100 32/32 [==============================] - 0s 4ms/step - loss: 171.8206 - mean_absolute_error: 171.8206 Epoch 42/100 32/32 [==============================] - 0s 4ms/step - loss: 154.8684 - mean_absolute_error: 154.8684 Epoch 43/100 32/32 [==============================] - 0s 4ms/step - loss: 183.5418 - mean_absolute_error: 183.5418 Epoch 44/100 32/32 [==============================] - 0s 4ms/step - loss: 170.9957 - mean_absolute_error: 170.9957 Epoch 45/100 32/32 [==============================] - 0s 4ms/step - loss: 250.7556 - mean_absolute_error: 250.7556 Epoch 46/100 32/32 [==============================] - 0s 4ms/step - loss: 130.4983 - mean_absolute_error: 130.4983 Epoch 47/100 32/32 [==============================] - 0s 4ms/step - loss: 192.2448 - mean_absolute_error: 192.2448 Epoch 48/100 32/32 [==============================] - 0s 4ms/step - loss: 127.2329 - mean_absolute_error: 127.2329 Epoch 49/100 32/32 [==============================] - 0s 4ms/step - loss: 167.2814 - mean_absolute_error: 167.2814 Epoch 50/100 32/32 [==============================] - 0s 4ms/step - loss: 251.3058 - mean_absolute_error: 251.3058 Epoch 51/100 32/32 [==============================] - 0s 4ms/step - loss: 172.5872 - mean_absolute_error: 172.5872 Epoch 52/100 32/32 [==============================] - 0s 4ms/step - loss: 140.7612 - mean_absolute_error: 140.7612 Epoch 53/100 32/32 [==============================] - 0s 4ms/step - loss: 250.3051 - mean_absolute_error: 250.3051 Epoch 54/100 32/32 [==============================] - 0s 4ms/step - loss: 103.1959 - mean_absolute_error: 103.1959 Epoch 55/100 32/32 [==============================] - 0s 4ms/step - loss: 148.3423 - mean_absolute_error: 148.3423 Epoch 56/100 32/32 [==============================] - 0s 4ms/step - loss: 130.6254 - mean_absolute_error: 130.6254 Epoch 57/100 32/32 [==============================] - 0s 4ms/step - loss: 74.8769 - mean_absolute_error: 74.8769 Epoch 58/100 32/32 [==============================] - 0s 4ms/step - loss: 156.9543 - mean_absolute_error: 156.9543 Epoch 59/100 32/32 [==============================] - 0s 4ms/step - loss: 143.6268 - mean_absolute_error: 143.6268 Epoch 60/100 32/32 [==============================] - 0s 4ms/step - loss: 130.9978 - mean_absolute_error: 130.9978 Epoch 61/100 32/32 [==============================] - 0s 4ms/step - loss: 202.3431 - mean_absolute_error: 202.3431 Epoch 62/100 32/32 [==============================] - 0s 4ms/step - loss: 173.4388 - mean_absolute_error: 173.4388 Epoch 63/100 32/32 [==============================] - 0s 4ms/step - loss: 90.0105 - mean_absolute_error: 90.0105 Epoch 64/100 32/32 [==============================] - 0s 4ms/step - loss: 110.1699 - mean_absolute_error: 110.1699 Epoch 65/100 32/32 [==============================] - 0s 4ms/step - loss: 166.2449 - mean_absolute_error: 166.2449 Epoch 66/100 32/32 [==============================] - 0s 4ms/step - loss: 103.2946 - mean_absolute_error: 103.2946 Epoch 67/100 32/32 [==============================] - 0s 4ms/step - loss: 185.7347 - mean_absolute_error: 185.7347 Epoch 68/100 32/32 [==============================] - 0s 4ms/step - loss: 114.4777 - mean_absolute_error: 114.4777 Epoch 69/100 32/32 [==============================] - 0s 4ms/step - loss: 143.8170 - mean_absolute_error: 143.8170 Epoch 70/100 32/32 [==============================] - 0s 4ms/step - loss: 240.2648 - mean_absolute_error: 240.2648 Epoch 71/100 32/32 [==============================] - 0s 4ms/step - loss: 221.5770 - mean_absolute_error: 221.5770 Epoch 72/100 32/32 [==============================] - 0s 4ms/step - loss: 98.1613 - mean_absolute_error: 98.1613 Epoch 73/100 32/32 [==============================] - 0s 4ms/step - loss: 144.0810 - mean_absolute_error: 144.0810 Epoch 74/100 32/32 [==============================] - 0s 4ms/step - loss: 148.9324 - mean_absolute_error: 148.9324 Epoch 75/100 32/32 [==============================] - 0s 4ms/step - loss: 124.8470 - mean_absolute_error: 124.8470 Epoch 76/100 32/32 [==============================] - 0s 4ms/step - loss: 242.0774 - mean_absolute_error: 242.0774 Epoch 77/100 32/32 [==============================] - 0s 4ms/step - loss: 121.6172 - mean_absolute_error: 121.6172 Epoch 78/100 32/32 [==============================] - 0s 4ms/step - loss: 101.0091 - mean_absolute_error: 101.0091 Epoch 79/100 32/32 [==============================] - 0s 4ms/step - loss: 187.4833 - mean_absolute_error: 187.4833 Epoch 80/100 32/32 [==============================] - 0s 4ms/step - loss: 184.7905 - mean_absolute_error: 184.7905 Epoch 81/100 32/32 [==============================] - 0s 4ms/step - loss: 161.8695 - mean_absolute_error: 161.8695 Epoch 82/100 32/32 [==============================] - 0s 4ms/step - loss: 274.4011 - mean_absolute_error: 274.4011 Epoch 83/100 32/32 [==============================] - 0s 4ms/step - loss: 90.2962 - mean_absolute_error: 90.2962 Epoch 84/100 32/32 [==============================] - 0s 3ms/step - loss: 161.3433 - mean_absolute_error: 161.3433 Epoch 85/100 32/32 [==============================] - 0s 4ms/step - loss: 239.6779 - mean_absolute_error: 239.6779 Epoch 86/100 32/32 [==============================] - 0s 4ms/step - loss: 124.4336 - mean_absolute_error: 124.4336 Epoch 87/100 32/32 [==============================] - 0s 4ms/step - loss: 122.3127 - mean_absolute_error: 122.3127 Epoch 88/100 32/32 [==============================] - 0s 4ms/step - loss: 128.0379 - mean_absolute_error: 128.0379 Epoch 89/100 32/32 [==============================] - 0s 4ms/step - loss: 93.0046 - mean_absolute_error: 93.0046 Epoch 90/100 32/32 [==============================] - 0s 4ms/step - loss: 77.4748 - mean_absolute_error: 77.4748 Epoch 91/100 32/32 [==============================] - 0s 4ms/step - loss: 167.8816 - mean_absolute_error: 167.8816 Epoch 92/100 32/32 [==============================] - 0s 4ms/step - loss: 112.9497 - mean_absolute_error: 112.9497 Epoch 93/100 32/32 [==============================] - 0s 4ms/step - loss: 73.7069 - mean_absolute_error: 73.7069 Epoch 94/100 32/32 [==============================] - 0s 4ms/step - loss: 122.9201 - mean_absolute_error: 122.9201 Epoch 95/100 32/32 [==============================] - 0s 4ms/step - loss: 170.7848 - mean_absolute_error: 170.7848 Epoch 96/100 32/32 [==============================] - 0s 4ms/step - loss: 165.6123 - mean_absolute_error: 165.6123 Epoch 97/100 32/32 [==============================] - 0s 4ms/step - loss: 102.5798 - mean_absolute_error: 102.5798 Epoch 98/100 32/32 [==============================] - 0s 4ms/step - loss: 85.1246 - mean_absolute_error: 85.1246 Epoch 99/100 32/32 [==============================] - 0s 4ms/step - loss: 195.0565 - mean_absolute_error: 195.0565 Epoch 100/100 32/32 [==============================] - 0s 4ms/step - loss: 131.4377 - mean_absolute_error: 131.4377
<tensorflow.python.keras.callbacks.History at 0x294c29430>

Evaluation

model.predict([10, 20, 30])
array([[ 94.41813], [412.36084], [911.89355]], dtype=float32)