With Python and Keras, I have been using three different deep learning models and extracting features from different layers for the given images. I'm getting feature vectors of dimensions (1,6,6,512), (1,50,50,128) and (1,1,1,128) from three different models. How can I concatenate these feature vectors in Python?
Flatten each matrix before concatenate to get 1-D vector and then concatenate all vector using numpy.concatenate function.
You can read doc here
https://docs.scipy.org/doc/numpy/reference/generated/numpy.concatenate.html
Hopes it it helps you.
I use the tf.image.resize_images to make them equal along the axis that you want to concatenate your features , here is an example(you have to modify it for your feature sizes).
x1 = tf.image.resize_images(block1_pool_features[0],[112,112])
x2 = tf.image.resize_images(block2_pool_features[0],[112,112])
x3 = tf.image.resize_images(block3_pool_features[0],[112,112])
x4 = tf.image.resize_images(block4_pool_features[0],[112,112])
x5 = tf.image.resize_images(block5_pool_features[0],[112,112])
And, then you concatenate using a simple
F = tf.concat([x3,x2,x1,x4,x5],0)
- Badges
- Science topic
- Similar topics
- Phytochemistry
- Extracts