Fashion-MNIST MLP

class deepobs.pytorch.testproblems.fmnist_mlp.fmnist_mlp(batch_size, l2_reg=None)[source]

DeepOBS test problem class for a multi-layer perceptron neural network on Fashion-MNIST.

The network is build as follows:

  • Four fully-connected layers with 1000, 500, 100 and 10 units per layer.
  • The first three layers use ReLU activation, and the last one a softmax activation.
  • The biases are initialized to 0.0 and the weight matrices with truncated normal (standard deviation of 3e-2)
  • The model uses a cross entropy loss.
  • No regularization is used.
Parameters:
  • batch_size (int) -- Batch size to use.
  • l2_reg (float) --
    No L2-Regularization (weight decay) 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 is torch.nn.CrossEntropyLoss()

    net

    The DeepOBS subclass of torch.nn.Module that is trained for this tesproblem (net_mlp).
set_up()[source]

Sets up the vanilla MLP test problem on Fashion-MNIST.