You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
{{ message }}
This repository has been archived by the owner on Oct 31, 2023. It is now read-only.
I have looked through the architecture of dataset.md, and wanted to prepare my own datasets in ava style to perform training on pretrained model. I really wounder how did the ava_train_predicted_boxes.csv and ava_val_predicted_boxes.csv produced? The coordinates in the two file are different from the ava official annotation files such as ava_train_v2.1.csv. BTW, if I use my own datasets, is the [official AVA annotation files] needed? Thanks in advance
ava
|_ frames
| |_ [video name 0]
| | |_ [video name 0]_000001.jpg
| | |_ [video name 0]_000002.jpg
| | |_ ...
| |_ [video name 1]
| |_ [video name 1]_000001.jpg
| |_ [video name 1]_000002.jpg
| |_ ...
|_ frame_lists
| |_ train.csv
| |_ val.csv
|_ annotations
|_ [official AVA annotation files]
|_ ava_train_predicted_boxes.csv
|_ ava_val_predicted_boxes.csv
The text was updated successfully, but these errors were encountered:
Sign up for freeto subscribe to this conversation on GitHub.
Already have an account?
Sign in.
I have looked through the architecture of
dataset.md
, and wanted to prepare my own datasets in ava style to perform training on pretrained model. I really wounder how did theava_train_predicted_boxes.csv
andava_val_predicted_boxes.csv
produced? The coordinates in the two file are different from the ava official annotation files such asava_train_v2.1.csv
. BTW, if I use my own datasets, is the[official AVA annotation files]
needed? Thanks in advanceThe text was updated successfully, but these errors were encountered: