Fashion-MNIST VAE¶
-
class
deepobs.pytorch.testproblems.fmnist_vae.
fmnist_vae
(batch_size, weight_decay=None)[source]¶ DeepOBS test problem class for a variational autoencoder (VAE) on Fashion-MNIST.
The network has been adapted from the here and consists of an encoder:
- With three convolutional layers with each
64
filters. - Using a leaky ReLU activation function with \(\alpha = 0.3\)
- Dropout layers after each convolutional layer with a rate of
0.2
.
and an decoder:
- With two dense layers with
24
and49
units and leaky ReLU activation. - With three deconvolutional layers with each
64
filters. - Dropout layers after the first two deconvolutional layer with a rate of
0.2
. - A final dense layer with
28 x 28
units and sigmoid activation.
No regularization is used.
Parameters: - batch_size (int) -- Batch size to use.
- weight_decay (float) -- No weight decay (L2-regularization) is used in this
test problem. Defaults to
None
and any input here is ignored.
-
data
¶ The DeepOBS data set class for Fashion-MNIST.
-
loss_function
¶ The loss function for this testproblem (vae_loss_function as defined in testproblem_utils)
-
net
¶ The DeepOBS subclass of torch.nn.Module that is trained for this tesproblem (net_vae).
-
get_batch_loss_and_accuracy_func
(reduction='mean', add_regularization_if_available=True)[source]¶ Gets a new batch and calculates the loss and accuracy (if available) on that batch. This is a default implementation for image classification. Testproblems with different calculation routines (e.g. RNNs) overwrite this method accordingly.
Parameters: return_forward_func (bool) -- If True
, the call also returns a function that calculates the loss on the current batch. Can be used if you need to access the forward path twice.Returns: loss and accuracy of the model on the current batch. If return_forward_func
isTrue
it also returns the function that calculates the loss on the current batch.Return type: float, float, (callable)
- With three convolutional layers with each