Question

我已经从Object Detection Zoo Model对模型进行了微调（使用TF 1.9），现在我正尝试使用TF 1.9冻结TensorFlowSharp的图形。

import tensorflow as tf
import os
from tensorflow.python.tools import freeze_graph
from tensorflow.core.protobuf import saver_pb2

#print("current tensorflow version: ", tf.version)
sess=tf.Session()

model_path = 'latest_cp/'
saver = tf.train.import_meta_graph('model.ckpt.meta')
saver.restore(sess,tf.train.latest_checkpoint('.')) #current dir of the checkpoint file
tf.train.write_graph(sess.graph_def, '.', 'test.pbtxt') #output in pbtxt format

freeze_graph.freeze_graph(input_graph = 'test.pbtxt',
    input_binary = False,
    input_checkpoint = model_path + 'model.ckpt',
    output_node_names =     "num_detections,detection_boxes,detection_scores,detection_classes",
    output_graph = 'test.bytes' ,
    clear_devices = True, initializer_nodes = "",input_saver = "",
    restore_op_name = "save/restore_all", filename_tensor_name = "save/Const:0")

它起作用了，但是当我将其导入Unity之后，它返回了以下错误：

TFException: Op type not registered 'NonMaxSuppressionV3' in binary running on AK38713. Make sure the Op and Kernel are registered in the binary running in this process.

我发现TensorFlowSharp可与TensorFlow 1.4一起使用，当我尝试使用1.4冻结图时，它返回相同的NonMaxSuppressionV3错误。您知道解决此问题的任何方法吗？非常感谢您的支持。

使用TF 1.4冻结TensorFlowSharp的微调图

0 个答案: