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.

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

Adding FID statistics calculation as an option (can now do "train", "eval", or "fid_stats") #5

Open
wants to merge 6 commits into
base: main
Choose a base branch
from
Open
Changes from 1 commit
Commits
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
Prev Previous commit
Next Next commit
remove some stuff
  • Loading branch information
AlexiaJM authored Mar 6, 2021
commit 978791f7390075a26b0a7dc54ec1f72483d7044c
6 changes: 0 additions & 6 deletions run_lib.py
Original file line number Diff line number Diff line change
Expand Up @@ -602,12 +602,6 @@ def fid_stats(config,

# Create data normalizer and its inverse
scaler = datasets.get_data_scaler(config)
inverse_scaler = datasets.get_data_inverse_scaler(config)
try: # Set the number of classes if info exists
config.model.num_classes = dataset_builder.info.features['label'].num_classes
except:
config.model.num_classes = 1
assert not config.model.class_conditional or (config.model.class_conditional and config.model.num_classes > 1)

# Use inceptionV3 for images with resolution higher than 256.
inceptionv3 = config.data.image_size >= 256
Expand Down