DeepOBS test problem class for the All Convolutional Neural Network C on Cifar-100.
Details about the architecture can be found in the original paper.
The paper does not comment on initialization; here we use Xavier for conv filters and constant 0.1 for biases.
A weight decay is used on the weights (but not the biases) which defaults to
The reference training parameters from the paper are
batch size = 256,
num_epochs = 350using the Momentum optimizer with \(\mu = 0.9\) and an initial learning rate of \(\alpha = 0.05\) and decrease by a factor of
- batch_size (int) -- Batch size to use.
- weight_decay (float) -- Weight decay factor. Weight decay (L2-regularization)
is used on the weights but not the biases.
The DeepOBS data set class for Cifar-100.
A tensorflow operation initializing the test problem for the training phase.
A tensorflow operation initializing the test problem for evaluating on training data.
A tensorflow operation initializing the test problem for evaluating on test data.
A tf.Tensor of shape (batch_size, ) containing the per-example loss values.
A scalar tf.Tensor containing a regularization term.
A scalar tf.Tensor containing the mini-batch mean accuracy.
Set up the All CNN C test problem on Cifar-100.