Change input size of a pre-trained network

23 visualizzazioni (ultimi 30 giorni)
Hi,
I am working on an object detection algorithm with YOLO V2 and I have been following Mathworks guidelines. In particular, I wanted to use the solution given in the following link: https://uk.mathworks.com/help/vision/ug/create-yolo-v2-object-detection-network.html. After that, I'd like to re-train the network so that it gets used to the type of images I am working with. However, when it comes to modify the input size, I end up by having a graph structure, and my imported network continues to have the same input size. If I try to modify it manually, it says the InputSize property is a read-only property, and if I try to directly change my new imageInputLayer object in the network, it also says it's read only.
Is there a way to:
  • Import a pre-trained network (I am using resnet50)
  • Change its input size and number of output features
  • Re-train it?
Thank you in advance!
Virginia

Risposte (1)

HyeongHun LEE
HyeongHun LEE il 11 Giu 2019
Modificato: HyeongHun LEE il 11 Giu 2019
Hi there
If you want to change the specific layer parameters in pretrained neural networks(e.g. ResNet, DenseNet etc), following the procedure will work.
1. Load target pretrained network in workspace
2. Open "Neural network designer (GUI version, newly updated in 2019a)"
3. Import pretrained network model into the neural network designer space (block diagram will display automatically)
4. Change layer properties (eg. input size, filter size etc)
5. Export network model
Best regards
  4 Commenti
Ansuman Mahapatra
Ansuman Mahapatra il 26 Mag 2020
Modificato: Ansuman Mahapatra il 26 Mag 2020
No it is read only. I cannot able to change even in designer app. I mean cannot edit.
But you have to delete the input layer and create a new input layer.
Mrutyunjaya Hiremath
Mrutyunjaya Hiremath il 25 Giu 2023
Modificato: Mrutyunjaya Hiremath il 25 Giu 2023
Delete existing Image Input Layer and Fully Connected Layer then add new Layer in that places . and modify the parameters.. also anyalyze the network for sucessfull creataion

Accedi per commentare.

Categorie

Scopri di più su Deep Learning Toolbox in Help Center e File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by