dataset size for training #387

New Issue

2023-03-07T10:13:56+01:00

tyrink commented

2023-03-07 10:13:56 +01:00

(Migrated from github.com)

Hi, the results of your method seems good, but I wonder if you chose a subset of the original vggface-2 for training and what's the size of your selected training set?

sjokic commented

2023-03-13 17:19:43 +01:00

(Migrated from github.com)

According to their paper: "To improve the quality of our training set, we remove images with size smaller than 250 × 250. We
align and crop the images to a standard position with size 224 × 224". So yes, they choose a subset of VGGFace2 and use 224x224 for all images in the training data set. You can find a download link for this data set in the readme of this repo.

According to their paper: "To improve the quality of our training set, we remove images with size smaller than 250 × 250. We align and crop the images to a standard position with size 224 × 224". So yes, they choose a subset of VGGFace2 and use 224x224 for all images in the training data set. You can find a download link for this data set in the readme of this repo.

Sign in to join this conversation.

1 Participants

Notifications

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: CalvinBackup/neuralchen-SimSwap#387