Add vqvae-celeba-64-512

Files changed (7) hide show

vqvae-celeba-64-512/ckpt/step0499999/meta.pt ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:df99aa5f4769833bb82ff2e829751b4d07f62f0674714325cb3fc3ab673c2dc8
+size 852

vqvae-celeba-64-512/ckpt/step0499999/model.pt ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:da0d3ef832f72c693bd466758fbe91cf3554564b6f5c3c3695e0527701085ff8
+size 19723985

vqvae-celeba-64-512/ckpt/step0499999/optimizer.pt ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:bd19adf5c81d7c5dd6ffefaa1c88f35f93ad6556ad951657f98627eb4f64e307
+size 39452307

vqvae-celeba-64-512/config-2024-07-05-00-09-47.yaml ADDED Viewed

+seed: 8888
+data:
+  name: celeba
+  root: ~/data/CelebA/
+  img_size: 64
+dataloader:
+  num_workers: 4
+  pin_memory: true
+  prefetch_factor: 2
+encoder:
+  target: models.autoencoder.simple_cnn.Encoder
+  params:
+    img_channels: 3
+    hidden_dim: 256
+    n_resblocks: 2
+decoder:
+  target: models.autoencoder.simple_cnn.Decoder
+  params:
+    img_channels: 3
+    hidden_dim: 256
+    n_resblocks: 2
+quantizer:
+  target: models.quantizer.VectorQuantizer
+  params:
+    codebook_num: 512
+    codebook_dim: 64
+train:
+  n_steps: 500000
+  batch_size: 256
+  coef_commit: 0.25
+  print_freq: 100
+  sample_freq: 10000
+  save_freq: 10000
+  optim:
+    target: torch.optim.Adam
+    params:
+      lr: 0.0004

vqvae-celeba-64-512/output-2024-07-05-00-09-47.log ADDED Viewed

The diff for this file is too large to render. See raw diff

vqvae-celeba-64-512/samples.zip ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:65f6f776ba1822589b406ee663916511f91af8096f5689379094e82daa54c8c4
+size 23612409

vqvae-celeba-64-512/tensorboard/events.out.tfevents.1720109387.amax-ESC8000A-E11.2657471.0 ADDED Viewed

+version https://git-lfs.github.com/spec/v1
+oid sha256:ff00e8b45ad86fb05839624baa8980ee5c2b6b248b607473448441e2e88778a8
+size 133917518