I have been using three different deep learning models and extracting features from the given images. I'm getting feature vectors of dimensions (1,4096), (1,2048) and (1,21024) from three different models. How can I concatenate these feature vectors and make feature selection using Principal Component Analysis in Python?
First of all, the row dimension of the new array must be equal to the largest vector size of the extracted features. Therefore, to concatenate vectors in an array, all the vectors must be of the same size (i.e the largest size).
For example, if you have three vectors (X, Y and Z) of different lengths, and the largest length is L. The following code may be used to concatenate the three vectors (Assume L is the length of vector Z) :
import numpy as np
X = np.array(X)
Y = np.array(Y)
Z = np.array(Z)
L = len(Z)
X.resize(L)
Y.resize(L)
A = (X, Y, Z)
R = np.vstack(A)
# R is the new array
- Badges
- Science topic
- Similar topics
- Computer Science and Engineering
- Programming Languages
- Python