如何在 Tensorflow 2 中使用腌制的预训练权重？
[英]How to use pickled pretrained weights in Tensorflow 2?
问题描述
I'm trying to load a pkl file that was generated in a model trained with tensorflow 1.x in tf2.
我正在尝试加载在 tf2 中使用 tensorflow 1.x 训练的 model 中生成的 pkl 文件。 model.load_weights(checkpoint_path) does not seem to work. model.load_weights(checkpoint_path)似乎不起作用。 any suggestions?有什么建议么？
1 个解决方案
解决方案1
0 已采纳 2021-05-06 20:19:38
Try loading the pickle file then get the weights.尝试加载泡菜文件然后获取权重。
import pickle
import tensorflow as tf
model = pickle.loads('<path>')
loaded_model = model.get_weights()
声明:本站的技术帖子网页，遵循CC BY-SA 4.0协议，如果您需要转载，请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.
相关问题
Tensorflow：如何在新图中使用预训练权重？ - Tensorflow: how to use pretrained weights in new graph?
如何在Tensorflow中加载预训练的LSTM模型权重 - how to load pretrained LSTM models weights in Tensorflow
如何使用预训练模型的 model 架构但没有权重 - How to use model architecture of pretrained models but no weights
Keras：在theano和tensorflow之间转换预训练的权重 - Keras: convert pretrained weights between theano and tensorflow
将 CNN Pytorch 中的预训练权重传递给 Tensorflow 中的 CNN - Pass pretrained weights in CNN Pytorch to a CNN in Tensorflow
如何在Tensorflow中使用事件重量？ - How to use event-by-event weights in Tensorflow?
Tensorflow：使用预训练的初始模型 - Tensorflow: use pretrained inception model
如何使用Tensorflow的实例分割预训练的MaskRCNN模型？ - How to use Instance segmentation pretrained MaskRCNN model by Tensorflow?
如何在Tensorflow中使用预训练的Word2Vec模型 - How to use pretrained Word2Vec model in Tensorflow
仅用于人/车辆检测的预训练 CNN（tensorflow/darknet/caffe）权重 - Pretrained CNN(tensorflow/darknet/caffe) weights for human/vehicle detection only
相关标签