I tried tensorflow for the first time

As the title says, I tried tensorflow for the first time and struggled to build an environment, so I wrote it. Qiita This is my first time writing, so the explanation may not be good, but thank you.

Constructed environment

I will give you a rough idea of the environment I built.

First, build a Python environment

Download the Graphical Installer below from Anaconda3, and select the OS and bit according to your environment. スクリーンショット 2020-10-13 153017.jpg You can leave the installation, check, etc. according to the installer's guide. After installation, launch Anaconda prompt image.png Download the one for your environment from the list under tensorflow pip guide to install tensorflow-gpu 2.30 image.png After downloading the tensorflow package file, Install by typing pip install --upgrade [downloaded file] and Anaconda prompt

Building Nvidia GPU environment

From here on, it's for people who want to use Nvidia GPUs. According to the article I referred to, tensorflow 2.3 seems to work with CUDA 10.1, cuDNN 7.6. It worked with this combination in my environment as well. Please install CUDA, cuDNN according to the version of tensorflow.

-Note on the version of CUDA, cuDNN where tensorflow-gpu works

Also, in order to use GPU with tensorflow, it seems that you have to set the memory usage. To do this, write the following code at the beginning of the code.

python


physical_devices = tf.config.list_physical_devices('GPU')
if len(physical_devices) > 0:
    for device in physical_devices:
        tf.config.experimental.set_memory_growth(device, True)
        print('{} memory growth: {}'.format(device, tf.config.experimental.get_memory_growth(device)))
else:
    print("Not enough GPU hardware devices available")

The code description depends on the version of tensorflow, so please refer to the article I referred to.

-How to reduce GPU memory usage with tensorflow2.0 + keras Keras2.0

Try tensorflow

Let's try the image classification using the neural network in the tutorial of tensorflow. I've added the code above to process it on the GPU.

newralnet_demo.py


#TensorFlow and tf.import keras
import tensorflow as tf
from tensorflow import keras

#Import helper library
import numpy as np
import matplotlib.pyplot as plt

# import os
# os.environ['CUDA_VISIBLE_DEVICES'] = '-1'
# print(tf.__version__)

# GPU_settings
physical_devices = tf.config.list_physical_devices('GPU')
if len(physical_devices) > 0:
    for device in physical_devices:
        tf.config.experimental.set_memory_growth(device, True)
        print('{} memory growth: {}'.format(
            device, tf.config.experimental.get_memory_growth(device)))
else:
    print("Not enough GPU hardware devices available")

fashion_mnist = keras.datasets.fashion_mnist

(train_images, train_labels), (test_images,
                               test_labels) = fashion_mnist.load_data()

class_names = ['T-shirt/top', 'Trouser', 'Pullover', 'Dress', 'Coat',
               'Sandal', 'Shirt', 'Sneaker', 'Bag', 'Ankle boot']

train_images.shape
len(train_labels)
train_labels
test_images.shape
len(test_labels)

plt.figure()
plt.imshow(train_images[0])
plt.colorbar()
plt.grid(False)
plt.show()

train_images = train_images / 255.0
test_images = test_images / 255.0

plt.figure(figsize=(10, 10))
for i in range(25):
    plt.subplot(5, 5, i+1)
    plt.xticks([])
    plt.yticks([])
    plt.grid(False)
    plt.imshow(train_images[i], cmap=plt.cm.binary)
    plt.xlabel(class_names[train_labels[i]])
plt.show()

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

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

model.fit(train_images, train_labels, epochs=5)

test_loss, test_acc = model.evaluate(test_images,  test_labels, verbose=2)
print('\nTest accuracy:', test_acc)

predictions = model.predict(test_images)
predictions[0]
np.argmax(predictions[0])
test_labels[0]


def plot_image(i, predictions_array, true_label, img):
    predictions_array, true_label, img = predictions_array[i], true_label[i], img[i]
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])

    plt.imshow(img, cmap=plt.cm.binary)

    predicted_label = np.argmax(predictions_array)
    if predicted_label == true_label:
        color = 'blue'
    else:
        color = 'red'

    plt.xlabel("{} {:2.0f}% ({})".format(class_names[predicted_label],
                                         100*np.max(predictions_array),
                                         class_names[true_label]),
               color=color)


def plot_value_array(i, predictions_array, true_label):
    predictions_array, true_label = predictions_array[i], true_label[i]
    plt.grid(False)
    plt.xticks([])
    plt.yticks([])
    thisplot = plt.bar(range(10), predictions_array, color="#777777")
    plt.ylim([0, 1])
    predicted_label = np.argmax(predictions_array)

    thisplot[predicted_label].set_color('red')
    thisplot[true_label].set_color('blue')


i = 0
plt.figure(figsize=(6, 3))
plt.subplot(1, 2, 1)
plot_image(i, predictions, test_labels, test_images)
plt.subplot(1, 2, 2)
plot_value_array(i, predictions,  test_labels)
plt.show()

i = 12
plt.figure(figsize=(6, 3))
plt.subplot(1, 2, 1)
plot_image(i, predictions, test_labels, test_images)
plt.subplot(1, 2, 2)
plot_value_array(i, predictions,  test_labels)
plt.show()

#Shows X test images, predicted labels, and correct labels.
#Correct predictions are shown in blue and wrong predictions are shown in red.
num_rows = 5
num_cols = 3
num_images = num_rows*num_cols
plt.figure(figsize=(2*2*num_cols, 2*num_rows))
for i in range(num_images):
    plt.subplot(num_rows, 2*num_cols, 2*i+1)
    plot_image(i, predictions, test_labels, test_images)
    plt.subplot(num_rows, 2*num_cols, 2*i+2)
    plot_value_array(i, predictions, test_labels)
plt.show()

#Extract one image from the test dataset
img = test_images[0]
print(img.shape)

#Make an image a member of only one batch
img = (np.expand_dims(img, 0))
print(img.shape)

predictions_single = model.predict(img)
print(predictions_single)

plot_value_array(0, predictions_single, test_labels)
_ = plt.xticks(range(10), class_names, rotation=45)

np.argmax(predictions_single[0])

If the process is successful, the images will be sorted and displayed in a list. image.png

Referenced site

I referred to the website of Kunihiko Kaneko Lab. It was very helpful. Thank you very much.

-First Neural Network: Introduction to Classification Problems -Note on the version of CUDA, cuDNN where tensorflow-gpu works -Install TensorFlow 2.2 (GPU compatible) (on Windows) -How to reduce GPU memory usage with tensorflow2.0 + keras

Recommended Posts

I tried tensorflow for the first time
I tried using scrapy for the first time
I tried python programming for the first time.
I tried Mind Meld for the first time
I tried Python on Mac for the first time.
I tried python on heroku for the first time
AI Gaming I tried it for the first time
I tried the Google Cloud Vision API for the first time
Kaggle for the first time (kaggle ①)
Kaguru for the first time
I tried logistic regression analysis for the first time using Titanic data
What I got into Python for the first time
I tried the MNIST tutorial for beginners of tensorflow.
For the first time, I learned about Unix (Linux).
I tried the TensorFlow tutorial 1st
I tried the TensorFlow tutorial 2nd
[For self-learning] Go2 for the first time
See python for the first time
Start Django for the first time
I tried porting the code written for TensorFlow to Theano
I tried running PIFuHD on Windows for the time being
[For beginners] I tried using the Tensorflow Object Detection API
I tried the TensorFlow tutorial MNIST 3rd
MongoDB for the first time in Python
Let's try Linux for the first time
I tried running the TensorFlow tutorial with comments (_TensorFlow_2_0_Introduction for beginners)
I tried running TensorFlow
[Python] I tried substituting the function name for the function name
How to use MkDocs for the first time
vprof --I tried using the profiler for Python
[Note] Deploying Azure Functions for the first time
Before the coronavirus, I first tried SARS analysis
I played with Floydhub for the time being
Try posting to Qiita for the first time
For the first time in Numpy, I will update it from time to time
Since I'm free, the front-end engineer tried Python (v3.7.5) for the first time.
I tried to create serverless batch processing for the first time with DynamoDB and Step Functions
Register a task in cron for the first time
I tried the changefinder library!
Looking back on the machine learning competition that I worked on for the first time
I will install Arch Linux for the time being.
I tried using magenta / TensorFlow
GTUG Girls + PyLadiesTokyo Meetup I went to machine learning for the first time
After attending school, I participated in SIGNATE's BEGINNER limited competition for the first time.
I want to create a lunch database [EP1] Django study for the first time
I want to create a lunch database [EP1-4] Django study for the first time
[TensorFlow] I want to master the indexing for Ragged Tensor
I tried to find the average of the sequence with TensorFlow
I tried refactoring the CNN model of TensorFlow using TF-Slim
I want to move selenium for the time being [for mac]
Summary of stumbling blocks in Django for the first time
Introducing yourself at Qiita for the first time (test post)
I tried to illustrate the time and time in C language
I tried to display the time and today's weather w
Miscellaneous notes that I tried using python for the matter
I want to create a Dockerfile for the time being.
If you're learning Linux for the first time, do this!
I tried the Naro novel API 2
I tried TensorFlow tutorial CNN 4th
I tried the Naruro novel API
I tried to move the ball