6
6

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?

More than 5 years have passed since last update.

[TensorFlow] 学習済みモデルInception-v3から特徴量を抽出する

Last updated at Posted at 2017-06-27

TensorFlowで、Inception-v3モデルを使って特徴量抽出をします。

  1. 以下から学習済みモデルをダウンロードする
    http://download.tensorflow.org/models/image/imagenet/inception-2015-12-05.tgz
  2. 上記ファイルを解凍して、classify_image_graph_def.pbを抽出
  3. ソースコード
    feature_extraction.py

IMG_PATHMODEL_PATHを環境に合わせて書き換えてください。

feature_extraction.py
import tensorflow as tf
import numpy as np

IMG_PATH = 'path/to/input/image.jpg'
MODEL_PATH = 'path/to/classify_image_graph_def.pb'

# 学習済みモデルの読み込み
inception_v3 = tf.gfile.FastGFile(MODEL_PATH, 'rb')
graph_def =tf.GraphDef()
graph_def.ParseFromString(inception_v3.read())
tf.import_graph_def(graph_def, name='')

with tf.Session() as sess:
    # 抽出層の指定
    pool3 = sess.graph.get_tensor_by_name('pool_3:0')

    # 入力画像の読み込み
    image_data = tf.gfile.FastGFile(IMG_PATH, 'rb').read()

    # 特徴量の抽出
    features = sess.run(pool3, {'DecodeJpeg/contents:0': image_data})
    print(np.squeeze(features))

PNGファイルを入力する場合

上記はJPEGファイルの入力のみを受け付けます。
PNGファイルを入力したい場合は、特徴量の抽出時に以下ように、'DecodeJpeg:0'ノードを指定します。

features = sess.run(pool3, {'DecodeJpeg:0':image_data})
6
6
0

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
6
6

Delete article

Deleted articles cannot be recovered.

Draft of this article would be also deleted.

Are you sure you want to delete this article?