我一直在無(wú)休止地尋找一個(gè) python 腳本或命令行函數(shù)來(lái)將 .pb 文件轉(zhuǎn)換為 .tflite。我試過(guò)使用 tflite_convert，但它返回錯(cuò)誤：OSError：SavedModel 文件不存在于：C:/tensorflowTraining/export_dir/saved_model.pb/{saved_model.pbtxt|saved_model.pb}我還嘗試了一些腳本，例如：import tensorflow as togf = tf.compat.v1.GraphDef()m_file = open('saved_model.pb', 'rb')gf.ParseFromString(m_file.read())with open('somefile.txt', 'a') as the_file: for n in gf.node: the_file.write(n.name+'\n')file = open('somefile.txt', 'r')data = file.readlines()print("output name = ")print(data[len(data)-1])print("Input name = ")file.seek(0)print(file.readline())這將返回：發(fā)生異常：DecodeError意外的結(jié)束組標(biāo)記。這個(gè)錯(cuò)誤發(fā)生在第 4 行： gf.ParseFromString(m_file.read())如果有人可以提供工作腳本或命令行功能，那將非常有幫助，正如我研究過(guò)的那樣返回錯(cuò)誤或無(wú)法正常運(yùn)行。謝謝！
1 回答
溫溫醬
TA貢獻(xiàn)1752條經(jīng)驗(yàn) 獲得超4個(gè)贊
你可以嘗試像下面這樣的東西TF2.2。
import tensorflow as tf
graph_def_file = "./saved_model.pb"
tflite_file = 'mytflite.tflite'
input_arrays = ["input"]. # you need to change it based on your model
output_arrays = ["output"] # you need to change it based on your model
print("{} -> {}".format(graph_def_file, tflite_file))
converter = tf.compat.v1.lite.TFLiteConverter.from_frozen_graph(
graph_def_file=graph_def_file,
input_arrays=input_arrays,
output_arrays=output_arrays,input_shapes={'input_mel':[ 1, 50, 80]})
# If there are multiple inputs, then update the dictionary above
tflite_model = converter.convert()
open(tflite_file,'wb').write(tflite_model)
在上面的代碼中，您需要使用與您的模型相對(duì)應(yīng)的input_arrays, output_arrays, 和。input_shapes
添加回答
舉報(bào)
0/150
提交
取消