https://arxiv.org/abs/1809.03672
You can get the data from amazon website and process it using the script
sh prepare_data.sh
Because getting and processing the data is time consumingso we had processed it and upload it for you. You can unzip it to use directly.
tar -jxvf data.tar.gz
mv data/* .
tar -jxvf data1.tar.gz
mv data1/* .
tar -jxvf data2.tar.gz
mv data2/* .
When you see the files below, you can do the next work.
python train.py train [model name]
The model blelow had been supported:
Note: we use tensorflow 1.4.