Is there a way to combine 2 pretrained tensorflow Models?
原文
2020-05-19 03:26:39
2
1
tensorflow/
machine-learning/
computer-vision/
classification/
ensemble-learning
Question
I have trained a TensorFlow classification model. Same model with different loaded weights classifies different classes better.
Is it possible to combine same model with different weights to increase its performance?
1 answers
solution1
0 2020-05-19 05:05:01
Yes, you can combine both their results by averaging out the final logits. Then, finding the final classification.
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.
Related Question
Tensorflow - Getting Probes of Pretrained models
converting pretrained tensorflow models for tensorflow serving
how to load pretrained LSTM models weights in Tensorflow
Tensorflow pretrained models input channel range
How to sequentially combine 2 tensorflow models?
Where to find tensorflow pretrained models (list or download link)
How to combine two predefined models in Keras TensorFlow?
Using a Tensorflow Pretrained model
How do I copy specific layer weights from pretrained models using Tensorflow Keras api?
Upgraded to Tensorflow 2.5 now get a Lambda Layer error when using pretrained Keras Applications Models
Related Tags