Please allow ads on our site
Please log in to access this content. You will be redirected to the login page shortly.
LoginKeras - UpSampling2D layer appears to be returning a 2D tensor rather than 4D
General Tech Bugs & Fixes 2 years ago
Posted on 16 Aug 2022, this text provides information on Bugs & Fixes related to General Tech. Please note that while accuracy is prioritized, the data presented might not be entirely correct or up-to-date. This information is offered for general knowledge and informational purposes only, and should not be considered as a substitute for professional advice.
manpreet 2 years ago
The input to your model should be of shape (batch_size, x_res, y_res, n_channels), please check it.
Following is a simple test:
import keras
from keras.layers import Conv2D, MaxPooling2D, UpSampling2D
import numpy as np
x_res = 1080
y_res = 1616
n_channels = 3
model = keras.Sequential([
Conv2D(32, (3,3), padding='same', activation='relu', data_format="channels_last", input_shape=(x_res,y_res,n_channels), kernel_initializer=keras.initializers.he_normal()),
MaxPooling2D((2,2)),
Conv2D(64, (3, 3), padding='same', activation='relu', kernel_initializer=keras.initializers.he_normal()),
MaxPooling2D((2, 2)),
Conv2D(128, (3, 3), padding='same', activation='relu', kernel_initializer=keras.initializers.he_normal()),
MaxPooling2D((2, 2)),
Conv2D(256, (3, 3), padding='same', activation='relu', kernel_initializer=keras.initializers.he_normal()),
UpSampling2D((2, 2)),
Conv2D(128, (3, 3), padding='same', activation='relu', kernel_initializer=keras.initializers.he_normal()),
UpSampling2D((2, 2)),
Conv2D(64, (3, 3), padding='same', activation='relu', kernel_initializer=keras.initializers.he_normal()),
UpSampling2D((2, 2)),
Conv2D(n_channels,
manpreet![Tuteehub forum best answer]()
Best Answer
2 years ago
I am feeding 1080x1616 color photos into a convolutional neural network in Keras. The data is fed through the network just fine, until it gets to the last convolutional layer, throwing an error saying that it expects a 4D tensor, but instead gets a (32,1) tensor. I don't understand where this number is being generated.
This is my model architecture: