- class torchmetrics.image.inception.InceptionScore(feature='logits_unbiased', splits=10, compute_on_step=None, **kwargs)
Calculates the Inception Score (IS) which is used to access how realistic generated images are. It is defined as
where is the KL divergence between the conditional distribution and the margianl distribution . Both the conditional and marginal distribution is calculated from features extracted from the images. The score is calculated on random splits of the images such that both a mean and standard deviation of the score are returned. The metric was originally proposed in .
Using the default feature extraction (Inception v3 using the original weights from ), the input is expected to be mini-batches of 3-channel RGB images of shape (3 x H x W) with dtype uint8. All images will be resized to 299 x 299 which is the size of the original training data.
using this metric with the default feature extractor requires that
torch-fidelityis installed. Either install as
pip install torchmetrics[image]or
pip install torch-fidelity
forwardmethod can be used but
compute_on_stepis disabled by default (oppesit of all other metrics) as this metric does not really make sense to calculate on a single batch. This means that by default
forwardwill just call
Either an str, integer or
an str or integer will indicate the inceptionv3 feature layer to choose. Can be one of the following: ‘logits_unbiased’, 64, 192, 768, 2048
nn.Modulefor using a custom feature extractor. Expects that its forward method returns an
Nis the batch size and
dis the feature size.
Forward only calls
update()and returns None if this is set to False.
Deprecated since version v0.8: Argument has no use anymore and will be removed v0.9.
 Improved Techniques for Training GANs Tim Salimans, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, Xi Chen https://arxiv.org/abs/1606.03498
 GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium, Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, Sepp Hochreiter https://arxiv.org/abs/1706.08500
>>> import torch >>> _ = torch.manual_seed(123) >>> from torchmetrics.image.inception import InceptionScore >>> inception = InceptionScore() >>> # generate some images >>> imgs = torch.randint(0, 255, (100, 3, 299, 299), dtype=torch.uint8) >>> inception.update(imgs) >>> inception.compute() (tensor(1.0544), tensor(0.0117))
Initializes internal Module state, shared by both nn.Module and ScriptModule.
Override this method to compute the final metric value from state variables synchronized across the distributed backend.