I have a 3D Image of size 100x100x100. I have features (feature dimension 25) extracted for each pixel by considering a small pacth around it. So the input to 1D CNN is 100x100x100x25 reshaped to 1000000x25 in the form nxf where n is the number of samples( in this case pixels) and f being the feature dimension. Is using CNN ideal for this scenario? or is a different deep learning model necessary?
Dear Faizuddin Nasar ,
Look the link, maybe useful.
https://www.analyticsvidhya.com/blog/2020/02/learn-image-classification-cnn-convolutional-neural-networks-3-datasets/
Regards,
Shafagat
Hi Faizuddin,
Generally speaking CNN's should work.
What kind of interactions are you planning to model? Specifically, will you be looking at discriminative features in independent 2D image planes? Are plane-to-plane interactions of interest?
Finally, in typical use cases CNNs are input with raw data and feature extraction is left to the network. Assuming you can provide abundant labelled data, feature extraction is one thing that CNNs are really good at.
In my experience, CNN-based feature extraction did worked using some popular pre-trained models for feature extraction. However, as supervised learning is hungry for the quantum of labeled data, the need to make sure will have a sufficient volume of labeled data is there. Also, I did introduce a good amount of noise for generalization to safeguard against bias.
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Programming Languages
- Python