pyiqa.archs.inceptionscore_arch

Inception score metric, proposed by

Salimans, Tim, Ian Goodfellow, Wojciech Zaremba, Vicki Cheung, Alec Radford, and Xi Chen. “Improved techniques for training gans.” Advances in neural information processing systems 29 (2016).

Reference codes:

• https://github.com/openai/improved-gan/tree/master/inception_score

• https://github.com/sbarratt/inception-score-pytorch

Module Contents

class pyiqa.archs.inceptionscore_arch.InceptionScore

Bases: torch.nn.Module

Implements the Inception Score (IS) metric.

Parameters:

dims (int) – The number of dimensions of the Inception-v3 feature representation to use. Must be one of 64, 192, 768, or 2048. Default: 2048.

model

The Inception-v3 network used to extract features.

Type:

nn.Module

forward(img_dir, mode='legacy_tensorflow', splits=10, num_workers=12, batch_size=32, device=torch.device('cuda'), verbose=True, **kwargs)