CIFAR-100 All-CNN-C¶
-
class
deepobs.tensorflow.testproblems.cifar100_allcnnc.
cifar100_allcnnc
(batch_size, weight_decay=0.0005)[source]¶ 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
5e-4
.The reference training parameters from the paper are
batch size = 256
,num_epochs = 350
using the Momentum optimizer with \(\mu = 0.9\) and an initial learning rate of \(\alpha = 0.05\) and decrease by a factor of10
after200
,250
and300
epochs.Parameters: - 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.
Defaults to
5e-4
.
-
dataset
¶ The DeepOBS data set class for Cifar-100.
-
train_init_op
¶ A tensorflow operation initializing the test problem for the training phase.
-
train_eval_init_op
¶ A tensorflow operation initializing the test problem for evaluating on training data.
-
test_init_op
¶ A tensorflow operation initializing the test problem for evaluating on test data.
-
losses
¶ A tf.Tensor of shape (batch_size, ) containing the per-example loss values.
-
regularizer
¶ A scalar tf.Tensor containing a regularization term.
-
accuracy
¶ A scalar tf.Tensor containing the mini-batch mean accuracy.