CIFAR-100 3c3d¶
-
class
deepobs.pytorch.testproblems.cifar100_3c3d.
cifar100_3c3d
(batch_size, weight_decay=0.002)[source]¶ DeepOBS test problem class for a three convolutional and three dense layered neural network on Cifar-100.
The network consists of
- thre conv layers with ReLUs, each followed by max-pooling
- two fully-connected layers with
512
and256
units and ReLU activation - 100-unit output layer with softmax
- cross-entropy loss
- L2 regularization on the weights (but not the biases) with a default factor of 0.002
The weight matrices are initialized using Xavier initialization and the biases are initialized to
0.0
.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
0.002
.
-
data
¶ The DeepOBS data set class for Cifar-100.
-
loss_function
¶ The loss function for this testproblem is torch.nn.CrossEntropyLoss().
-
net
¶ The DeepOBS subclass of torch.nn.Module that is trained for this tesproblem (net_cifar10_3c3d with 100 outputs).
-
get_regularization_loss
()¶ Returns the current regularization loss of the network state.