CIFAR-100 VGG16¶
-
class
deepobs.cifar100.cifar100_vgg16.set_up(batch_size=128, weight_decay=0.0005)[source]¶ Class providing the functionality for the VGG 16 architecture on CIFAR-100. The CIFAR-100 images are resized to
224by224to fit the input dimension of the original VGG network, which was designed for 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.Basis data augmentation (random crop, left-right flip, lighting augmentation) is done on the training images.
Parameters: - batch_size (int) -- Batch size of the data points. Defaults to
128. - weight_decay (float) -- Weight decay factor. In this model weight decay is applied to the weights, but not the biases. Defaults to
5e-4.
-
data_loading¶ Data loading class for CIFAR-100,
cifar100_input.data_loading.Type: deepobs.data_loading
-
losses¶ Tensor of size
batch_sizecontaining the individual losses per data point.Type: tf.Tensor
-
accuracy¶ Tensor containing the accuracy of the model.
Type: tf.Tensor
-
train_init_op¶ A TensorFlow operation to be performed before starting every training epoch.
Type: tf.Operation
-
train_eval_init_op¶ A TensorFlow operation to be performed before starting every training eval epoch.
Type: tf.Operation
-
test_init_op¶ A TensorFlow operation to be performed before starting every test evaluation phase.
Type: tf.Operation
- batch_size (int) -- Batch size of the data points. Defaults to