pre trained deep learning network

2 visualizaciones (últimos 30 días)
Ahmad Alhashil
Ahmad Alhashil el 22 de Feb. de 2021
Respondida: Sanyam el 9 de Jul. de 2022
hi!
how i can immprove the accuarcy in pretrained deep learning network ?
and dose it by adding more layers in the network ?

Respuestas (1)

Sanyam
Sanyam el 9 de Jul. de 2022
There are a lot of different ways you can try to increase accuracy of your model using transfer learning.
The first thing you can try is to unfreeze weights and biases of more layers in the pretrained network, and train it using your dataset. This will increase the time to train the network as there are more learnable parameters but will also make your network suitable for your dataset.
Other than that you can use techniques common to all the neural networks to increase the performance, which are augmenting your dataset, and finetuning hyperparameters like learning rate, mini batch size, adding layers, adding neurons, applying regularization techniques like L1, L2, dropout.
Please refer to this article to get more insights on these techniques

Categorías

Más información sobre Deep Learning Toolbox en Help Center y File Exchange.

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by