1. Pre-trained Model
- cwgan_gp_mnist.pth
seed=888
n_epochs=50
batch_size=64
lr=0.0002
d_hidden_dim=32
g_latent_dim=100
g_hidden_dom=32
gp_weight=10
n_d_updates=3
2. Samples
3. Implementation Details
1) Architecture
- [1]eseo Architecturereul gajyeowaseo myeoc gajireul byeongyeonghaessseubnida.
- Discriminator:
- ceos beonjjae Convolutional layer daeume Batch normalization layerreul cugahaessseubnida.
- Generator:
- majimag Transposed convolutional layereseo
bias=Truero byeongyeonghaessseubnida. - ReLU activationeul Leaky ReLU activationeuro byeongyeonghaessseubnida.
- majimag Transposed convolutional layereseo
- Discriminator:
- ireohge byeongyeonghameurosseo saempeulyi kweolritiga sangseunghaessseubnida.