search

DonaldRR / SimpleNet

MIT License
402 stars 59 forks source link

The feature about feeding to discriminator #36

Closed FFFox-abc closed 8 months ago

FFFox-abc commented 10 months ago

I find in the _train_discriminator() function in simplenet.py after the _embed() function, the feature becomes [10368, 1536], It's a two dimensions feature and no batch information, and then use this feature to train the discriminator. But for the output of the discriminator, it's like 10368 positive results and 10368 negetive result? And no batch information. I got confused. Why they need do those.

DonaldRR commented 8 months ago

The features of the batch are flattened(reshape) to 1D here.