Data Science Asked by scoute21 on July 16, 2021
I want to create a ship detection classifier from a dataset that is formed by 4000 photos(3072*2048).
But the dataset that i currently have is not labeled so i can feed it to a cnn.So i want to cluster this dataset to 2 labels(or 2 directories) ship and no_ship.I tried running k-means but the results were dissapointing.Is some other more functional way to do this?
Here's what you could try.
Softmax()
layer or after the Flatten()
layerAnswered by Vincent Yong on July 16, 2021
First of all, keep this in mind:
I can see two options:
As Vincent Young suggests, you can find pre-trained networks which have been trained on similar detection tasks. ModelZoo is a good place to find pre-trained networks for the framework you are using.
K-Means is straight forward but has some flow. It doesn't deal well with clusters of uneven size and will learn towards creating circular clusters due to Euclidean distance.
Mean-shift can deal with arbitrary feature spaces and can use arbitrary kernel functions. You may not end up with 2 clusters, but you may be able to find useful clusters regardless. On this note, if you try using more than 2 clusters with K-Means, you may find some clusters being "pure" (containing a single class) while some may be mixed. These pure clusters can be a good start.
I wrote a chapter on Mean Shift on my website, including other resources, if you want to read it.
Answered by Valentin Calomme on July 16, 2021
In addition to the answers provided, you can:
1.) Train jointly a CNN (or Autoencoder) with clustering on your data. (DCN, kmeansNet,..)
2.) Pretrain a CNN using self-supervision on your data. (Have a look into the vast self-supervision literature, e.g. this work).
3.) Use an alternating scheme to train a CNN classifier on soft-labels provided by a clustering algorithm, e.g k-means (e.g. this work).
Answered by Graph4Me Consultant on July 16, 2021
Get help from others!
Recent Questions
Recent Answers
© 2024 TransWikia.com. All rights reserved. Sites we Love: PCI Database, UKBizDB, Menu Kuliner, Sharing RPP