I am new in Tensorflow and Python. I have built a multi layer network and I have pretrained it. Now I want to build another multilayer network next to the first. The weights of the first network are frozen and I want to concatenate features I got from the first network with the normal input of the layer of the new network. How can I concatenate the output of a specific layer in the first network with the input to this network and feed the layer of the new network?
1
-
Can you please clarify the requirement? Can you add a pseudo code for better understanding.user11530462– user115304622020-05-05 10:49:23 +00:00Commented May 5, 2020 at 10:49
Add a comment
|
1 Answer
Below is the simple example of concatenating 2 input layers of different input shape and feeding to next layer.
import tensorflow.keras.backend as K
import tensorflow as tf
from tensorflow.keras.models import Model
from tensorflow.keras.layers import Input, concatenate, Conv2D, ZeroPadding2D, Dense
from tensorflow.keras.optimizers import Adagrad
input_img1 = Input(shape=(44,44,3))
x1 = Conv2D(3, (3, 3), activation='relu', padding='same')(input_img1)
input_img2 = Input(shape=(34,34,3))
x2 = Conv2D(3, (3, 3), activation='relu', padding='same')(input_img2)
# Zero Padding of 5 at the top, bottom, left and right side of an image tensor
x3 = ZeroPadding2D(padding = (5,5))(x2)
# Concatenate works as layers have same size output
x4 = concatenate([x1,x3])
output = Dense(18, activation='relu')(x4)
model = Model(inputs=[input_img1,input_img2], outputs=output)
model.summary()
Output -
Model: "model"
__________________________________________________________________________________________________
Layer (type) Output Shape Param # Connected to
==================================================================================================
input_4 (InputLayer) [(None, 34, 34, 3)] 0
__________________________________________________________________________________________________
input_3 (InputLayer) [(None, 44, 44, 3)] 0
__________________________________________________________________________________________________
conv2d_3 (Conv2D) (None, 34, 34, 3) 84 input_4[0][0]
__________________________________________________________________________________________________
conv2d_2 (Conv2D) (None, 44, 44, 3) 84 input_3[0][0]
__________________________________________________________________________________________________
zero_padding2d_1 (ZeroPadding2D (None, 44, 44, 3) 0 conv2d_3[0][0]
__________________________________________________________________________________________________
concatenate_1 (Concatenate) (None, 44, 44, 6) 0 conv2d_2[0][0]
zero_padding2d_1[0][0]
__________________________________________________________________________________________________
dense (Dense) (None, 44, 44, 18) 126 concatenate_1[0][0]
==================================================================================================
Total params: 294
Trainable params: 294
Non-trainable params: 0
__________________________________________________________________________________________________
If the above answer is not what you are looking for, then would request you to share the pseudo code or flow diagram of the models to answer better.
1 Comment
İhsan Dağ
Yes, I have also found this way to implement it and it worked. However, thanks a lot for the reply!!!