Home › Claude › aifoundations › alexnet_cnn_imagenet › The final softmax layer in AlexNet outputs distr…
The final softmax layer in AlexNet outputs distributions over
ATwo classes for binary tasks
B10 classes for CIFAR-10 only
C100 classes for CIFAR-100 only
D1000 classes for ImageNet
Answer & Solution
Correct answer: D. 1000 classes for ImageNet
AlexNet was trained for the ILSVRC-2010 and 2012 ImageNet classification challenges with 1000 object classes. The final FC layer outputs 1000 logits, then softmax.
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