In discretized_mix_logistic_loss in utils.py
It corresponds to
But I'm confused with coeffs[:, :, :, 0, :] * x[:, :, :, 0, :] part. Why it conditions on input image x?
It seems it predicts the logistic means of G channel based on the R channel of the real image rather than on the predicted R channel.
How is input real image accessible at inference time?
In discretized_mix_logistic_loss in utils.py It corresponds to But I'm confused with coeffs[:, :, :, 0, :] * x[:, :, :, 0, :] part. Why it conditions on input image x? It seems it predicts the logistic means of G channel based on the R channel of the real image rather than on the predicted R channel. How is input real image accessible at inference time?