Transformer on a Diet

Reference: C Wang, Z Ye, A Zhang, Z Zhang, A Smola. "Transformer on a Diet". arXiv preprint arXiv (2020).

Installation

pip install --pre --upgrade mxnet
pip install gluonnlp

Results

The results and the command line to reproduce the results on PTB dataset are as follows.

[1] Full (Val PPL 109.19 Test PPL 103.72)

$ cd scripts/language_model/
$ python transformer_language_model.py --model full --data ptb --emsize 320 --nhid 2000 --nlayers 3 --lr 10 --epochs 500 --batch_size 20 --bptt 70 --dropout 0.4 --dropout_h 0.25 --dropout_i 0 --dropout_e 0 --weight_drop 0 --tied --alpha 0 --beta 0 --lr_update_interval 100 --lr_update_factor 1 --num_heads 16 --scaled --units 320 --use_residual --max_src_length 1000 --warmup_steps 0 --first_window_size 1 --kernel_size 3 --d_base 2

[2] Dilated (Val PPL 115.67 Test PPL 110.92)

$ cd scripts/language_model/
$ python transformer_language_model.py --model dilated --data ptb --emsize 320 --nhid 2000 --nlayers 3 --lr 10 --epochs 500 --batch_size 20 --bptt 70 --dropout 0.4 --dropout_h 0.25 --dropout_i 0 --dropout_e 0 --weight_drop 0 --tied --alpha 0 --beta 0 --lr_update_interval 100 --lr_update_factor 1 --num_heads 16 --scaled --units 320 --use_residual --max_src_length 1000 --warmup_steps 0 --first_window_size 1 --kernel_size 3 --d_base 2

[3] Dilated-Memory (Val PPL 115.35 Test PPL 110.98)

$ cd scripts/language_model/
$ python transformer_language_model.py --model dilated_mem --data ptb --emsize 320 --nhid 2000 --nlayers 3 --lr 10 --epochs 500 --batch_size 20 --bptt 70 --dropout 0.4 --dropout_h 0.25 --dropout_i 0 --dropout_e 0 --weight_drop 0 --tied --alpha 0 --beta 0 --lr_update_interval 100 --lr_update_factor 1 --num_heads 16 --scaled --units 320 --use_residual --max_src_length 1000 --warmup_steps 0 --first_window_size 1 --kernel_size 3 --d_base 2

[4] Cascade (Val PPL 109.16 Test PPL 105.27)

$ cd scripts/language_model/
$ python transformer_language_model.py --model cascade --data ptb --emsize 320 --nhid 2000 --nlayers 3 --lr 10 --epochs 500 --batch_size 20 --bptt 70 --dropout 0.4 --dropout_h 0.25 --dropout_i 0 --dropout_e 0 --weight_drop 0 --tied --alpha 0 --beta 0 --lr_update_interval 100 --lr_update_factor 1 --num_heads 16 --scaled --units 320 --use_residual --max_src_length 1000 --warmup_steps 0 --first_window_size 4 --window_size_multiplier 2 --kernel_size 3 --d_base 2

Note that the command to reproduce the results on wikitext-2 would be updated soon.

Reference Paper

The bibtext entry of the reference paper is:

@article{transformerdiet2020,
   title={Transformer on a Diet},
   author={Chenguang Wang and Zihao Ye and Aston Zhang and Zheng Zhang and Alexander J. Smola},
   journal={ArXiv},
   year={2020},
   volume={abs/2002.06170}
}

Code repo for "Transformer on a Diet" paper

Related tags

Overview

Transformer on a Diet

Installation

Results

Reference Paper

Owner

cgraywang

GazeScroller - Using Facial Movements to perform Hands-free Gesture on the system

Adapter-BERT: Parameter-Efficient Transfer Learning for NLP.

Active window border replacement for window managers.

LieTransformer: Equivariant Self-Attention for Lie Groups

Official Pytorch Implementation for Splicing ViT Features for Semantic Appearance Transfer presenting Splice

Code for MarioNette: Self-Supervised Sprite Learning, in NeurIPS 2021

Face Mask Detector by live camera using tensorflow-keras, openCV and Python

ML-based medical imaging using Azure

This is an official implementation of CvT: Introducing Convolutions to Vision Transformers.

[ICCV21] Official implementation of the "Social NCE: Contrastive Learning of Socially-aware Motion Representations" in PyTorch.

Benchmark spaces - Benchmarks of how well different two dimensional spaces work for clustering algorithms

[Official] Exploring Temporal Coherence for More General Video Face Forgery Detection(ICCV 2021)

Compute execution plan: A DAG representation of work that you want to get done. Individual nodes of the DAG could be simple python or shell tasks or complex deeply nested parallel branches or embedded DAGs themselves.

MetaTTE: a Meta-Learning Based Travel Time Estimation Model for Multi-city Scenarios

Interactive Image Segmentation via Backpropagating Refinement Scheme

Malware Analysis Neural Network project.

Code for Understanding Pooling in Graph Neural Networks

ERISHA is a mulitilingual multispeaker expressive speech synthesis framework. It can transfer the expressivity to the speaker's voice for which no expressive speech corpus is available.

Code release of paper "Deep Multi-View Stereo gone wild"

Age and Gender prediction using Keras