Skip to content

As_a_joint_training_module

Directory actions

More options

Directory actions

More options

Latest commit

 

History

History

As_a_joint_training_module

Folders and files

NameName
Last commit message
Last commit date

parent directory

..
base
base
 
 
configs
configs
 
 
data_loader
data_loader
 
 
model
model
 
 
trainer
trainer
 
 
utils
utils
 
 
README.md
README.md
 
 
parse_config.py
parse_config.py
 
 
requirements.txt
requirements.txt
 
 
train.py
train.py
 
 

README.md

EMCL as a joint training module (EMCL+MMT)

EMCL can be easy to be incorporated into any existing methods.

Requirements

  • Python 3.7
  • Pytorch 1.4.0
  • Transformers 3.1.0
  • Numpy 1.18.1
# Install the requirements
pip install -r requirements.txt

Preparing data

The video features can be found in sharing from MMT, i.e.,

# Create and move to mmt/data directory
mkdir data
cd data
# Download the video features
wget http://pascal.inrialpes.fr/data2/vgabeur/video-features/MSRVTT.tar.gz
wget http://pascal.inrialpes.fr/data2/vgabeur/video-features/activity-net.tar.gz
wget http://pascal.inrialpes.fr/data2/vgabeur/video-features/LSMDC.tar.gz
# Extract the video features
tar -xvf MSRVTT.tar.gz
tar -xvf activity-net.tar.gz
tar -xvf LSMDC.tar.gz

Training

python -m train --config configs/*

Acknowledge

  • This code implementation are adopted from MMT. We sincerely appreciate for their contributions. We sincerely appreciate for their contributions.