[tensorflow] How to make tfrecord file for training ** training data image들로 부터 tfrecord 만들기 ** ** Assume you have saved 100 images at 'file_path'. The corresponding labels are stored in label.csv file. That is, one integer value label per RGB image. // PSEUDO CODE //////////////////////////////////////import tensorflow as tfimport something def _bytes_feature(value): return tf.train.Feature(bytes_list=tf.train.BytesList(value=[value])) def _int6.. 더보기 [tensorflow] how to load and use the saved trained network in python ** tensorflow에서 미리 저장한 CNN로드하고 사용하기 **** See '[tensorflow] how to save trained network' first. // PSEUDO CODE ////////////////////////////////////////import tensorflow as tfimport something # save trained netnet_dir = 'path_to_saved_trained_network'image_path = 'path_to_input_images' with tf.Session() as sess: # Step1) Load graph from meta file (meta file contains the graph that I had defined be.. 더보기 [tensorflow] how to freeze trained network (make one pb file) ** 학습한 CNN graph 저장하기 - C++에서 사용하기 위해 **** See '[tensorflow] how to save trained network' first! ** Download the attached file ' freeze_graph.py'** The following code will create graph.pb at net_dir. This pb file will be used at c++. ** To see how to use graph.pb in c++, visit '[tensorflow] how to load and use CNN in c++' /// CODE /////////////////////////////from __future__ import absolute_impo.. 더보기 이전 1 ··· 61 62 63 64 65 66 67 다음