因爲項目須要,須要將TensorFlow保存的模型從ckpt文件轉換爲pb文件。node
import os from tensorflow.python import pywrap_tensorflow from net2use import inception_resnet_v2_small#這裏使用本身定義的模型函數便可 import tensorflow as tf if __name__=='__main__': pb_file = "./model/output.pb" ckpt_file = "./model/model.ckpt-652900" ''' 這裏的節點名字可能跟設想的有出入,最直接的方法是直接輸出ckpt中保存的節點名字,而後對應着找節點名字,具體的進入convert_variables_to_constants函數的實現中graph_util_impl.py,130行的函數:_assert_nodes_are_present 添加代碼 print('在圖中的節點是:') for din in name_to_node: print('{},在圖中'.format(din)) 而後運行代碼,若正確就會直接保存;若失敗則會保存失敗,找好輸出節點的名字,在output_node_names 中添加就好 ''' output_node_names = ["embedding"] with tf.name_scope('input'): image = tf.placeholder(tf.float32,shape=(None,79,199,1),name='input_image') net, endpoints=inception_resnet_v2_small(image, is_training=False) embedding = tf.nn.l2_normalize(net,1,1e-10,name='embedding') config=tf.ConfigProto(allow_soft_placement=True) config.gpu_options.per_process_gpu_memory_fraction = 0.45 sess = tf.Session(config = config) saver = tf.train.Saver() saver.restore(sess, ckpt_file) print('read success') converted_graph_def = tf.graph_util.convert_variables_to_constants(sess, input_graph_def = sess.graph.as_graph_def(), output_node_names = output_node_names) with tf.gfile.GFile(pb_file, "wb") as f: f.write(converted_graph_def.SerializeToString()) print('保存成功')