AlexNet's input image size is
A32 by 32 pixels RGB
B64 by 64 pixels RGB
C224 by 224 pixels RGB
D512 by 512 pixels RGB
Answer & Solution
Correct answer: C. 224 by 224 pixels RGB
The first convolutional layer filters the 224x224x3 input image with 96 kernels of size 11x11x3 at stride 4. The input is cropped from 256x256 source images.
Related questions
Image similarity in AlexNet's last hidden layer is measured byThe SGD update rule for AlexNet usesRemoving any single middle convolutional layer of AlexNet costs roughlyAlexNet was trained for roughly how many epochs on ImageNet?At test time dropout is approximated byAlexNet uses overlapping pooling withAlexNet's second form of data augmentation isAlexNet's first form of data augmentation is