![](/img/trans.png)
[英]Uncertain how to run Bazel: Tensorflow Inception Retrain New Categories Tutorial Python
[英]Tensorflow inception without bazel
我從tensorflow網站嘗試了這個圖像識別教程: https ://www.tensorflow.org/tutorials/image_retraining,它成功地與bazel bu命令行一起使用是否可以使用bazel或通過python腳本以編程方式調用此初始模型所以我可以很容易地給它喂圖像
您可以使用tmp目錄下生成的文件並編寫python腳本來加載模型並生成預測。
另外,建議將文件保留在tmp文件夾以外的目錄中,因為可以清除文件夾的內容。
import tensorflow as tf
import sys
image_path = sys.argv[1]
image_data = tf.gfile.FastGFile(image_path, 'rb').read()
#loads label file, strips off carriage return
label_lines = [line.strip() for line in tf.gfile.GFile("/tmp/output_labels.txt")]
# Unpersists graph from file
with tf.gfile.FastGFile("/tmp/output_graph.pb", 'rb') as f:
graph_def = tf.GraphDef()
graph_def.ParseFromString(f.read())
_ = tf.import_graph_def(graph_def, name='')
with tf.Session() as sess:
# Feed the image data as input to the graph an get first prediction
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 = %.2f)' % (human_string, score))
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.