我有一个经过冷冻训练的对象检测模型,该模型已经在视频上进行了测试。我想使用optimize_for_inference
库并使用以下代码来优化模型:
import tensorflow as tf
from tensorflow.python.tools import freeze_graph
from tensorflow.python.tools import optimize_for_inference_lib
input_graph_def = tf.GraphDef()
with tf.gfile.Open("frozen_inference_graph.pb", "rb") as f:
data = f.read()
input_graph_def.ParseFromString(data)
output_graph_def = optimize_for_inference_lib.optimize_for_inference(
input_graph_def,
['input'], ## input
['y_'], ## output
tf.float32.as_datatype_enum)
f = tf.gfile.FastGFile("./inference_graph/optimized_inference_graph.pb", "wb")
f.write(output_graph_def.SerializeToString())
我测试了生成的optimized_inference_graph.pb
,但它在测试期间发出了此错误:
DecodeError Traceback(最近的呼叫 最后)在() 5以tf.gfile.GFile(PATH_TO_CKPT,'rb')作为fid: 6 serialized_graph = fid.read() ----> 7 od_graph_def.ParseFromString(serialized_graph) 8 tf.import_graph_def(od_graph_def,name ='') 9
DecodeError:错误解析消息
该图书馆不再可用吗?它被transform
_graph
取代了吗?