Transformer-XL implemented in Keras
Project description
Keras Transformer-XL
Unofficial implementation of Transformer-XL.
Install
pip install keras-transformer-xl
Usage
Load Pretrained Weights
Several configuration files can be found at the info directory.
import os
from keras_transformer_xl import load_trained_model_from_checkpoint
checkpoint_path = 'foo/bar/sota/enwiki8'
model = load_trained_model_from_checkpoint(
config_path=os.path.join(checkpoint_path, 'config.json'),
checkpoint_path=os.path.join(checkpoint_path, 'model.ckpt')
)
model.summary()
About IO
Suppose the number of transformer blocks is n
. The last n
inputs are used for inputs of memorization, and the last n
outputs represents new data to be memorized.
Use tensorflow.python.keras
Add TF_KERAS=1
to environment variables to use tensorflow.python.keras
.
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
keras-transformer-xl-0.2.1.tar.gz
(12.8 kB
view hashes)
Close
Hashes for keras-transformer-xl-0.2.1.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 19840ffc6eba4f9c2097e70186aeef60393cdbdcc1f9709871ad0e41cdcfcf6d |
|
MD5 | c8572b60b059db1eeb530a73181cbb41 |
|
BLAKE2b-256 | 55b3133e1f8441ddff9df18262cdf8d78e309fe7d804292f994218ea93619274 |