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

A Comprehensive Study on Learning-Based PE Malware Family Classification Methods

The code for our CVPR paper PISE: Person Image Synthesis and Editing with Decoupled GAN, Project Page, supp.

Pytorch implementation of face attention network

Complementary Patch for Weakly Supervised Semantic Segmentation, ICCV21 (poster)

This repo contains the implementation of the algorithm proposed in Off-Belief Learning, ICML 2021.

The official pytorch implemention of the CVPR paper "Temporal Modulation Network for Controllable Space-Time Video Super-Resolution".

Distributed DataLoader For Pytorch Based On Ray

Deep Learning Specialization by Andrew Ng, deeplearning.ai.

LF-YOLO (Lighter and Faster YOLO) is used to detect defect of X-ray weld image.

The lightweight PyTorch wrapper for high-performance AI research. Scale your models, not the boilerplate.

Implementation of Learning Gradient Fields for Molecular Conformation Generation (ICML 2021).

I-BERT: Integer-only BERT Quantization

Code for "Neural Parts: Learning Expressive 3D Shape Abstractions with Invertible Neural Networks", CVPR 2021

Automatic meme generation model using Tensorflow Keras.

PERIN is Permutation-Invariant Semantic Parser developed for MRP 2020

This repository is an implementation of paper : Improving the Training of Graph Neural Networks with Consistency Regularization

A Python module for the generation and training of an entry-level feedforward neural network.

[CVPR'22] COAP: Learning Compositional Occupancy of People

Complete system for facial identity system. Include one-shot model, database operation, features visualization, monitoring

CharacterGAN: Few-Shot Keypoint Character Animation and Reposing