Learn how to classify images with TensorFlow
  • 355 views,
  • 08-02,
  • 上傳者: Kuann Hung,
  •  0
先來個最基本的 TensorFlow 實作
869c27393f454e42406f2e55a5b2a34a.png
這個範例是把圖片根據 "目錄名稱" 分類好,透過 retrain.py 來訓練,訓練後的結果會存在 output_graph.pb 跟 output_labels.txt 中,可以隨時調用。
 
 
步驟
1.
下載範例圖片
curl -O http://download.tensorflow.org/example_images/flower_photos.tgz
2.
下載程式
curl -O https://raw.githubusercontent.com/tensorflow/tensorflow/10cf65b48e1b2f16eaa826d2793cb67207a085d0/tensorflow/examples/image_retraining/retrain.py
3.
開始訓練
python retrain.py --image_dir flower_photos --output_graph output_graph.pb --output_labels output_labels.txt
4.
套用訓練後的資料判斷
將下列程式命名為 classify.py
import tensorflow as tf, sys
 
image_path = sys.argv[1]
graph_path = 'output_graph.pb'
labels_path = 'output_labels.txt'
 
# Read in the image_data
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
 
# Loads label file, strips off carriage return
label_lines = [line.rstrip() for line
    in tf.gfile.GFile(labels_path)]
 
# Unpersists graph from file
with tf.gfile.FastGFile(graph_path, 'rb') as f:
    graph_def = tf.GraphDef()
    graph_def.ParseFromString(f.read())
    _ = tf.import_graph_def(graph_def, name='')
 
# Feed the image_data as input to the graph and get first prediction
with tf.Session() as sess:
    softmax_tensor = sess.graph.get_tensor_by_name('final_result:0')
    predictions = sess.run(softmax_tensor, 
    {'DecodeJpeg/contents:0': image_data})
    # Sort to show labels of first prediction in order of confidence
    top_k = predictions[0].argsort()[-len(predictions[0]):][::-1]
    for node_id in top_k:
         human_string = label_lines[node_id]
         score = predictions[0][node_id]
         print('%s (score = %.5f)' % (human_string, score))
5.
也可以用 Tensorboard 看看訓練的資料過程
tensorboard --logdir /tmp/retrain_logs
訪客如要回應,請先 登入
    資料夾 :
    發表時間 :
    2018-08-02 21:33:11
    觀看數 :
    355
    發表人 :
    Kuann Hung
    部門 :
    老洪的 IT 學習系統
    QR Code :