SoccerNet SDK
Project description
SOCCERNETV2
conda create -n SoccerNet python pip
pip install SoccerNet
How to Download Games (Python)
from SoccerNet import SoccerNetDownloader
mySoccerNetDownloader = SoccerNetDownloader(
LocalDirectory="/path/to/soccernet/folder")
# input password to download video (copyright protected)
password = input("Password for videos? (contact the author):\n")
mySoccerNetDownloader.password = password
# Download SoccerNet v1
mySoccerNetDownloader.downloadGames(files=["Labels.json"], split=["train","valid","test"]) # download labels
mySoccerNetDownloader.downloadGames(files=["1.mkv", "2.mkv"], split=["train","valid","test"]) # download LQ Videos
mySoccerNetDownloader.downloadGames(files=["1_HQ.mkv", "2_HQ.mkv", "video.ini"], split=["train","valid","test"]) # download HQ Videos
mySoccerNetDownloader.downloadGames(files=["1_ResNET_TF2.npy", "2_ResNET_TF2.npy"], split=["train","valid","test"]) # download Features
# Download SoccerNet Test Set
mySoccerNetDownloader.LocalDirectory = "/path/to/soccernet/challenge/folder"
mySoccerNetDownloader.downloadGames(files=["1.mkv", "2.mkv"], split=["challenge"]) # download LQ Videos
mySoccerNetDownloader.downloadGames(files=["1_HQ.mkv", "2_HQ.mkv", "video.ini"], split=["challenge"]) # download HQ Videos
mySoccerNetDownloader.downloadGames(files=["1_ResNET_TF2.npy", "2_ResNET_TF2.npy"], split=["challenge"]) # download Features
How to read the list Games (Python)
from SoccerNet import getListGames
print(getListGames(split="train")) # return list of games recommended for training
print(getListGames(split="valid")) # return list of games recommended for validation
print(getListGames(split="test")) # return list of games recommended for testing
print(getListGames(split=["train", "valid", "test"])) # return list of games for training, validation and testing
print(getListGames(split="v1")) # return list of games from SoccerNetv1 (train/valid/test)
print(getListGames(split="challenge")) # return list of games for the challenge
print(getListGames(split=["v1", "challenge"])) # return complete list of games
[Coming soon...] How to extract features (TensorFlow 2)
from SoccerNet import FeatureExtractor
myFeatureExtractor = FeatureExtractor(
args.soccernet_dirpath, feature="ResNet", video="LQ", back_end="TF2")
myFeatureExtractor.extractGameIndex(0)
[Coming soon...] Tensorflow/Pytorch dataloader
pip install scikit-video
pip cudnn cudatoolkit=10.1
pip install tensorflow
pip install pytorch torchvision cudatoolkit=10.1
pip install av
# conda install pytorch torchvision cudatoolkit=10.1 -c pytorch
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
SoccerNet-0.0.40.tar.gz
(16.9 kB
view hashes)
Built Distribution
Close
Hashes for SoccerNet-0.0.40-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | b923aef20112d8f8276746edac1ac17661db568856483fa7c4a82a22c0f967b6 |
|
MD5 | 0536e7dd2f9877c168ca6751fede9e2f |
|
BLAKE2b-256 | 08bf7799accfe293d61d8b9f74e4db6dc049f7a03d0f88f7af32e9c3405ca858 |