![](/img/trans.png)
[英]How to convert an object detection model, in it's frozen graph, to a .tflite, without any knowledge of input and output arrays
[英]How to set input and output arrays while converting to a tflite model
import tensorflow as tf
from tensorflow.contrib import lite
graph_def_file = 'D:\\Models\\kapl\\inference_graph \\frozen_inference_graph.pb'
input_arrays = [1,600,1024,1] #image_tensor
output_arrays = [1,600,1024,1]
converter = tf.contrib.lite.TFLiteConverter.from_frozen_graph(graph_def_file, input_arrays, output_arrays)
converter.post_training_quantize = True
tflite_quantized_model = converter.convert()
open("quantized_model.tflite", "wb").write(tflite_quantized_model)
input_arrays
和output_arrays
表示模型圖的輸入和輸出張量。
檢查從圖表的最簡單方式.pb
文件是使用summarize_graph工具。
如果該方法產生錯誤,則可以使用TensorBoard可視化GraphDef,並在圖形中查找輸入和輸出。 要可視化.pb
文件,請使用import_pb_to_tensorboard.py
腳本,如下所示:
python import_pb_to_tensorboard.py --model_dir <model path> --log_dir <log dir path>
聲明:本站的技術帖子網頁,遵循CC BY-SA 4.0協議,如果您需要轉載,請注明本站網址或者原文地址。任何問題請咨詢:yoyou2525@163.com.