ImageNet VGG16

class deepobs.tensorflow.testproblems.imagenet_vgg16.imagenet_vgg16(batch_size, weight_decay=0.0005)[source]

DeepOBS test problem class for the VGG 16 network on ImageNet.

Details about the architecture can be found in the original paper. VGG 16 consists of 16 weight layers, of mostly convolutions. The model uses cross-entroy loss. A weight decay is used on the weights (but not the biases) which defaults to 5e-4.

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 ImageNet.

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.

set_up()[source]

Set up the VGG 16 test problem on ImageNet.