CIFAR-100 WideResNet 40-4¶
-
class
deepobs.tensorflow.testproblems.cifar100_wrn404.
cifar100_wrn404
(batch_size, weight_decay=0.0005)[source]¶ DeepOBS test problem class for the Wide Residual Network 40-4 architecture for CIFAR-100.
Details about the architecture can be found in the original paper. A weight decay is used on the weights (but not the biases) which defaults to
5e-4
.Training settings recommenden in the original paper:
batch size = 128
,num_epochs = 200
using the Momentum optimizer with \(\mu = 0.9\) and an initial learning rate of0.1
with a decrease by0.2
after60
,120
and160
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.