Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[ViTMAE] Renamed variable name #18850

Merged
merged 2 commits into from
Oct 10, 2022
Merged

[ViTMAE] Renamed variable name #18850

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a164e3f
fix: renamed variable name
ariG23498 Sep 1, 2022
7edfb0e
Merge branch 'main' into fix/mae-var-name
ariG23498 Sep 19, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions src/transformers/models/vit_mae/modeling_tf_vit_mae.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -254,7 +254,7 @@ def random_masking(self, sequence: tf.Tensor, noise: Optional[tf.Tensor] = None)

# keep the first subset
ids_keep = ids_shuffle[:, :len_keep]
sequence_masked = tf.gather(
sequence_unmasked = tf.gather(
sequence,
axis=1,
batch_dims=1,
Expand All @@ -271,7 +271,7 @@ def random_masking(self, sequence: tf.Tensor, noise: Optional[tf.Tensor] = None)
# unshuffle to get the binary mask
mask = tf.gather(mask, axis=1, batch_dims=1, indices=ids_restore)

return sequence_masked, mask, ids_restore
return sequence_unmasked, mask, ids_restore

def call(self, pixel_values: tf.Tensor, noise: tf.Tensor = None) -> tf.Tensor:
embeddings = self.patch_embeddings(pixel_values)
Expand Down
4 changes: 2 additions & 2 deletions src/transformers/models/vit_mae/modeling_vit_mae.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -251,15 +251,15 @@ def random_masking(self, sequence, noise=None):

# keep the first subset
ids_keep = ids_shuffle[:, :len_keep]
sequence_masked = torch.gather(sequence, dim=1, index=ids_keep.unsqueeze(-1).repeat(1, 1, dim))
sequence_unmasked = torch.gather(sequence, dim=1, index=ids_keep.unsqueeze(-1).repeat(1, 1, dim))

# generate the binary mask: 0 is keep, 1 is remove
mask = torch.ones([batch_size, seq_length], device=sequence.device)
mask[:, :len_keep] = 0
# unshuffle to get the binary mask
mask = torch.gather(mask, dim=1, index=ids_restore)

return sequence_masked, mask, ids_restore
return sequence_unmasked, mask, ids_restore

def forward(self, pixel_values, noise=None):
batch_size, num_channels, height, width = pixel_values.shape
Expand Down