Large Scale GAN Training for High Fidelity Natural Image Synthesis
Paper
•
1809.11096
•
Published
•
1
Note Table 1: Frechet Inception Distance (FID, lower is better) and Inception Score (IS, higher is better) for ablations of our proposed modifications. Batch is batch size, Param is total number of param- eters, Ch. is the channel multiplier representing the number of units in each layer, Shared is using shared embeddings, Skip-z is using skip connections from the latent to multiple layers, Ortho. is Orthogonal Regularization, and Itr indicates if the setting is stable to 106 iterations, or it...