A python library for highly configurable transformers - easing model architecture search and experimentation.

Related tags

Deep Learningdeep-learningtransformerspytorchartificial-intelligence
Overview

configaformers (re-factor in progress)

A python library for highly configurable transformers - easing model architecture search and experimentation. It is premised on building small and independent modules that enables users to configure custom transformer architectures.

Special thanks to lucidrains (https://github.com/lucidrains) and Kharr.

Usage

Quick demo that will configure a 768-wide, 12-layer transformer, with a language modeling head.

Import, and create token embedding block:

import torch
from model_builder import ConfigaFormer

emb = []
model_dim = 768

emb.append({'type': 'embedding',
            'output_dim': model_dim,
            'num_classes': 50257})

Create self-attention module:

attn = []

# Make residual and norm
attn.append({'type': 'make_stream', 'output_name': 'residual'})
attn.append({'type': 'norm', 'norm_type': 'layer_norm'})

# Make QKVs
attn.append({'type': 'linear', 'output_name': 'queries'})
attn.append({'type': 'linear', 'output_name': 'keys'})
attn.append({'type': 'linear', 'output_name': 'values'})

attn.append({'type': 'make_heads', 'input_name': 'queries', 'output_name': 'queries', 'num_heads': 12})
attn.append({'type': 'make_heads', 'input_name': 'keys', 'output_name': 'keys', 'num_heads': 12})

attn.append({'type': 'rope', 'input_name': 'queries', 'output_name': 'queries', 'rotate_dim': 16})
attn.append({'type': 'rope', 'input_name': 'keys', 'output_name': 'keys', 'rotate_dim': 16})

# Perform attention
attn.append({'type': 'mha_dots',
             'input_name_queries': 'queries',
             'input_name_keys': 'keys'})
attn.append({'type': 'attention_offset'})
attn.append({'type': 'mha_sum',
             'input_name_values': 'values'})

# Mix
attn.append({'type': 'linear'})

# Add residual
attn.append({'type': 'merge_streams',
             'input_name_1': 'residual',
             'merge_type': 'add'})

Create FFN module:

ffn = []

# Make residual and norm
ffn.append({'type': 'make_stream', 'output_name': 'residual'})
ffn.append({'type': 'norm', 'norm_type': 'layer_norm'})

# Proj Up
ffn.append({'type': 'linear', 'output_dim': 768*4})

# Activation
ffn.append({'type': 'activation'})

# Proj Down
ffn.append({'type': 'linear', 'output_dim': 768})

# Add residual
ffn.append({'type': 'merge_streams',
             'input_name_1': 'residual',
             'merge_type': 'add'})

Create language modeling head:

to_logits = []
to_logits.append({'type': 'linear', 'output_dim': 50257})

Create blocks, initialize input shapes, and init the model:

transformer_block = attn + ffn
classifier = ffn + to_logits

blocks = [{"config": emb,
           "repeat": 1},
          {"config": transformer_block,
           "repeat": 12},
          {"config": classifier,
           "repeat": 1},
          ]
          
my_config = {'blocks' = blocks}
input_streams = {'emb_ids': ['B', 'L_in'],
                 'attn_offset': ['B', 12, 'L_in', 'L_in'],}

model = ConfigaFormer(model_config=my_config,
                     input_streams=input_streams).cuda()

This will print out the transformer config:

Block #1, 1x
embedding -> Input(s): emb_ids (BSZ, L_in) - Output(s): x (BSZ, L_in, 768)


Block #2, 12x
make_stream -> Input(s): x (BSZ, L_in, 768) - Output(s): residual (BSZ, L_in, 768)
norm -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): queries (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): keys (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): values (BSZ, L_in, 768)
make_heads -> Input(s): queries (BSZ, L_in, 768) - Output(s): queries (BSZ, 12, L_in, 64)
make_heads -> Input(s): keys (BSZ, L_in, 768) - Output(s): keys (BSZ, 12, L_in, 64)
rope -> Input(s): queries (BSZ, 12, L_in, 64), rope_16 (2048, 16) - Output(s): queries (BSZ, 12, L_in, 64)
rope -> Input(s): keys (BSZ, 12, L_in, 64), rope_16 (2048, 16) - Output(s): keys (BSZ, 12, L_in, 64)
mha_dots -> Input(s): queries (BSZ, 12, L_in, 64), keys (BSZ, 12, L_in, 64) - Output(s): attn_dots (BSZ, 12, L_in, L_in)
attention_offset -> Input(s): attn_dots (BSZ, 12, L_in, L_in), attn_offset (BSZ, 12, L_in, L_in) - Output(s): attn_dots (BSZ, 12, L_in, L_in)
mha_sum -> Input(s): values (BSZ, L_in, 768), attn_dots (BSZ, 12, L_in, L_in) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
merge_streams -> Input(s): residual (BSZ, L_in, 768), x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
make_stream -> Input(s): x (BSZ, L_in, 768) - Output(s): residual (BSZ, L_in, 768)
norm -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 3072)
activation -> Input(s): x (BSZ, L_in, 3072) - Output(s): x (BSZ, L_in, 3072)
linear -> Input(s): x (BSZ, L_in, 3072) - Output(s): x (BSZ, L_in, 768)
merge_streams -> Input(s): residual (BSZ, L_in, 768), x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)


Block #3, 1x
make_stream -> Input(s): x (BSZ, L_in, 768) - Output(s): residual (BSZ, L_in, 768)
norm -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 3072)
activation -> Input(s): x (BSZ, L_in, 3072) - Output(s): x (BSZ, L_in, 3072)
linear -> Input(s): x (BSZ, L_in, 3072) - Output(s): x (BSZ, L_in, 768)
merge_streams -> Input(s): residual (BSZ, L_in, 768), x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 768)
linear -> Input(s): x (BSZ, L_in, 768) - Output(s): x (BSZ, L_in, 50257)

Before running, we need to get the attention offset (in this case, AliBi with a causal mask):

from attention_offset_module import get_alibi

attn_offset = get_alibi(num_heads=12)

Now we can use the model:

input_data = {'emb_ids': batch_ids.view(bsz, 1024).cuda(),
              'attn_offset': attn_offset.cuda()}

logits = model(input_data)['x'].view(bsz, 1024, 50257)

TODO

  1. Token shifting, down/up sampling
  2. Create higher abstractions for FFN and self-attention
  3. everything else
Owner
Anthony Fuller
Anthony Fuller
GitHub Repository
Convolutional Neural Network for 3D meshes in PyTorch

MeshCNN in PyTorch SIGGRAPH 2019 [Paper] [Project Page] MeshCNN is a general-purpose deep neural network for 3D triangular meshes, which can be used f

Rana Hanocka 1.4k Jan 04, 2023
Self-Supervised Learning with Kernel Dependence Maximization

Self-Supervised Learning with Kernel Dependence Maximization This is the code for SSL-HSIC, a self-supervised learning loss proposed in the paper Self

DeepMind 29 Dec 29, 2022
PyTorch implementation of Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy

Anomaly Transformer in PyTorch This is an implementation of Anomaly Transformer: Time Series Anomaly Detection with Association Discrepancy. This pape

spencerbraun 160 Dec 19, 2022
This repository is a series of notebooks that show solutions for the projects at Dataquest.io.

Dataquest Project Solutions This repository is a series of notebooks that show solutions for the projects at Dataquest.io. Of course, there are always

Dataquest 1.1k Dec 30, 2022
UI2I via StyleGAN2 - Unsupervised image-to-image translation method via pre-trained StyleGAN2 network

We proposed an unsupervised image-to-image translation method via pre-trained StyleGAN2 network. paper: Unsupervised Image-to-Image Translation via Pr

208 Dec 30, 2022
Deep Watershed Transform for Instance Segmentation

Deep Watershed Transform Performs instance level segmentation detailed in the following paper: Min Bai and Raquel Urtasun, Deep Watershed Transformati

193 Nov 20, 2022
An algorithmic trading bot that learns and adapts to new data and evolving markets using Financial Python Programming and Machine Learning.

ALgorithmic_Trading_with_ML An algorithmic trading bot that learns and adapts to new data and evolving markets using Financial Python Programming and

1 Mar 14, 2022
Canonical Capsules: Unsupervised Capsules in Canonical Pose (NeurIPS 2021)

Canonical Capsules: Unsupervised Capsules in Canonical Pose (NeurIPS 2021) Introduction This is the official repository for the PyTorch implementation

165 Dec 07, 2022
Real-Time Seizure Detection using EEG: A Comprehensive Comparison of Recent Approaches under a Realistic Setting

Real-Time Seizure Detection using Electroencephalogram (EEG) This is the repository for "Real-Time Seizure Detection using EEG: A Comprehensive Compar

AITRICS 30 Dec 17, 2022
Julia package for contraction of tensor networks, based on the sweep line algorithm outlined in the paper General tensor network decoding of 2D Pauli codes

Julia package for contraction of tensor networks, based on the sweep line algorithm outlined in the paper General tensor network decoding of 2D Pauli codes

Christopher T. Chubb 35 Dec 21, 2022
TinyML Cookbook, published by Packt

TinyML Cookbook This is the code repository for TinyML Cookbook, published by Packt. Author: Gian Marco Iodice Publisher: Packt About the book This bo

Packt 93 Dec 29, 2022
Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception, IROS 2021

For academic use only. Stereo Hybrid Event-Frame (SHEF) Cameras for 3D Perception Ziwei Wang, Liyuan Pan, Yonhon Ng, Zheyu Zhuang and Robert Mahony Th

Ziwei Wang 11 Jan 04, 2023
Offcial repository for the IEEE ICRA 2021 paper Auto-Tuned Sim-to-Real Transfer.

Offcial repository for the IEEE ICRA 2021 paper Auto-Tuned Sim-to-Real Transfer.

47 Jun 30, 2022
Supervised Classification from Text (P)

MSc-Thesis Module: Masters Research Thesis Language: Python Grade: 75 Title: An investigation of supervised classification of therapeutic process from

Matthew Laws 1 Nov 22, 2021
MoveNet Single Pose on DepthAI

MoveNet Single Pose tracking on DepthAI Running Google MoveNet Single Pose models on DepthAI hardware (OAK-1, OAK-D,...). A convolutional neural netwo

64 Dec 29, 2022
Official Pytorch implementation for 2021 ICCV paper "Learning Motion Priors for 4D Human Body Capture in 3D Scenes" and trained models / data

Learning Motion Priors for 4D Human Body Capture in 3D Scenes (LEMO) Official Pytorch implementation for 2021 ICCV (oral) paper "Learning Motion Prior

165 Dec 19, 2022
Source code for "FastBERT: a Self-distilling BERT with Adaptive Inference Time".

FastBERT Source code for "FastBERT: a Self-distilling BERT with Adaptive Inference Time". Good News 2021/10/29 - Code: Code of FastPLM is released on

Weijie Liu 584 Jan 02, 2023
[CVPR2022] Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos

Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos Created by Muheng Li, Lei Chen, Yueqi Duan, Zhilan Hu, Jianjiang Feng, Jie

58 Dec 23, 2022
Robustness via Cross-Domain Ensembles

Robustness via Cross-Domain Ensembles [ICCV 2021, Oral] This repository contains tools for training and evaluating: Pretrained models Demo code Traini

Visual Intelligence & Learning Lab, Swiss Federal Institute of Technology (EPFL) 27 Dec 23, 2022
Vehicle speed detection with python

Vehicle-speed-detection In the project simulate the tracker.py first then simulate the SpeedDetector.py. Finally, a new window pops up and the output

3 Dec 15, 2022