WarpRNNT loss ported in Numba CPU/CUDA for Pytorch

Overview

RNNT loss in Pytorch - Numba JIT compiled (warprnnt_numba) Test-CPU

Warp RNN Transducer Loss for ASR in Pytorch, ported from HawkAaron/warp-transducer and a replica of the stable version in NVIDIA Neural Module repository (NVIDIA NeMo).

NOTE: The code here will have experimental extensions and may be potentially unstable, use the version in NeMo for long term supported loss version of RNNT for PyTorch.

Supported Features

Currently supports :

  1. WarpRNNT loss in pytorch for CPU / CUDA (jit compiled)
  2. FastEmit
  3. Gradient Clipping (from Torch Audio)

Installation

You will need PyTorch (usually the latest version should be used), plus installation of Numba in a Conda environment (pip only environment is untested but may work).

# Follow installation instructions to install pytorch from website (with cuda if required)
conda install -c conda-force numba or conda update -c conda-forge numba (to get latest version)

# Then install this library
pip install --upgrade git+https://github.com/titu1994/warprnnt_numba.git

Usage

Import warprnnt_numba and use RNNTLossNumba. If attempting to use CUDA version of loss, it is advisable to test that your installed CUDA version is compatible with numba version using numba_utils.

There is also included a very slow numpy/pytorch explicit-loop based loss implementation for verification of exact correct results.

import torch
import numpy as np
import warprnnt_numba

# Define the loss function
fastemit_lambda = 0.001  # any float >= 0.0
loss_pt = warprnnt_numba.RNNTLossNumba(blank=4, reduction='sum', fastemit_lambda=fastemit_lambda)

# --------------
# Example usage

device = "cuda"
torch.random.manual_seed(0)

# Assume Batchsize=2, Acoustic Timesteps = 8, Label Timesteps = 5 (including BLANK=BOS token),
# and Vocabulary size of 5 tokens (including RNNT BLANK)
acts = torch.randn(2, 8, 5, 5, device=device, requires_grad=True)
sequence_length = torch.tensor([5, 8], dtype=torch.int32,
                               device=device)  # acoustic sequence length. One element must be == acts.shape[1].

# Let 0 be MASK/PAD value, 1-3 be token ids, and 4 represent RNNT BLANK token
# The BLANK token is overloaded for BOS token as well here, but can be different token.
# Let first sample be padded with 0 (actual length = 3). Loss is computed according to supplied `label_lengths`.
# and gradients for the 4th index onwards (0 based indexing).
labels = torch.tensor([[4, 1, 1, 3, 0], [4, 2, 2, 3, 1]], dtype=torch.int32, device=device)
label_lengths = torch.tensor([3, 4], dtype=torch.int32,
                             device=device)  # Lengths here must be WITHOUT the BOS token.

# If on CUDA, log_softmax is computed internally efficiently (preserving memory and speed)
# Compute it explicitly for CPU, this is done automatically for you inside forward() of the loss.
# -1-th vocab index is RNNT blank token here.
loss_func = warprnnt_numba.RNNTLossNumba(blank=4, reduction='none',
                                         fastemit_lambda=0.0, clamp=0.0)
loss = loss_func(acts, labels, sequence_length, label_lengths)
print("Loss :", loss)
loss.sum().backward()

# When parsing the gradients, look at grads[0] -
# Since it was padded in T (sequence_length=5 < T=8), there are gradients only for grads[0, :5, :, :].
# Since it was padded in U (label_lengths=3+1 < U=5), there are gradeints only for grads[0, :5, :3+1, :].
grads = acts.grad
print("Gradients of activations :")
print(grads)

Tests

Tests will perform CPU only checks if there are no GPUs. If GPUs are present, will run all tests once for cuda:0 as well.

pytest tests/

Requirements

  • pytorch >= 1.10. Older versions might work, not tested.
  • numba - Minimum required version is 0.53.0, preferred is 0.54+.
You might also like...
This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures

Introduction This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures. @inproceedings{Wa

Example repository for custom C++/CUDA operators for TorchScript

Custom TorchScript Operators Example This repository contains examples for writing, compiling and using custom TorchScript operators. See here for the

Convert Python 3 code to CUDA code.

Py2CUDA Convert python code to CUDA. Usage To convert a python file say named py_file.py to CUDA, run python generate_cuda.py --file py_file.py --arch

This demo showcase the use of onnxruntime-rs with a GPU on CUDA 11 to run Bert in a data pipeline with Rust.

Demo BERT ONNX pipeline written in rust This demo showcase the use of onnxruntime-rs with a GPU on CUDA 11 to run Bert in a data pipeline with Rust. R

LightSeq is a high performance training and inference library for sequence processing and generation implemented in CUDA
CUDA Python Low-level Bindings

CUDA Python Low-level Bindings

A dead simple python wrapper for darknet that works with OpenCV 4.1, CUDA 10.1

What Dead simple python wrapper for Yolo V3 using AlexyAB's darknet fork. Works with CUDA 10.1 and OpenCV 4.1 or later (I use OpenCV master as of Jun

Prevent `CUDA error: out of memory` in just 1 line of code.
Prevent `CUDA error: out of memory` in just 1 line of code.

🐨 Koila Koila solves CUDA error: out of memory error painlessly. Fix it with just one line of code, and forget it. πŸš€ Features πŸ™… Prevents CUDA error

An addernet CUDA version

Training addernet accelerated by CUDA Usage cd adder_cuda python setup.py install cd .. python main.py Environment pytorch 1.10.0 CUDA 11.3 benchmark

Comments
  • GPU under utilization due to low occupancy.

    GPU under utilization due to low occupancy.

    Thank you for the warprnnt_numba, I got the warnning (show blow) when I use this loss in my code. 1650880807(1) Is this known issue? How can it be debugged and solved?

    Thank you!

    opened by jiay7 2
  • Fix runtime speed

    Fix runtime speed

    Improve runtime speed of numba loss

    • Fix issue with data movement of costs tensor from llForward to pytorch data view in numba
    • This alone costs a linear loop (scaling with batch size) that is roughly 10x the kernel costs themselves.
    • Fix by writing a small kernel to copy the data and update the costs.
    opened by titu1994 0
Releases(v0.4.0)
  • v0.4.0(Jan 30, 2022)

    Supports

    • Simple RNNT loss with Atomic Locks implementation

    Improvements

    • Improve runtime speed of numba loss
      • Fix issue with data movement of costs tensor from llForward to pytorch data view in numba
      • This alone costs a linear loop (scaling with batch size) that is roughly 10x the kernel costs themselves.
      • Fix by writing a small kernel to copy the data and update the costs.
    Source code(tar.gz)
    Source code(zip)
  • v0.2.2(Jan 24, 2022)

    Initial release of Warp RNNT loss with Numba JIT compile (CPU/CUDA)

    Supports:

    1. Pytorch RNNT loss (CPU and JIT compiled CUDA)
    2. FastEmit
    3. Gradient clipping
    Source code(tar.gz)
    Source code(zip)
Owner
Somshubra Majumdar
Interested in Machine Learning, Deep Learning and Data Science in general
Somshubra Majumdar
Pytorch implementation AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative Adversarial Networks

AttnGAN Pytorch implementation for reproducing AttnGAN results in the paper AttnGAN: Fine-Grained Text to Image Generation with Attentional Generative

Tao Xu 1.2k Dec 26, 2022
Official repository of the paper Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Official repository of the paper Learning to Regress 3D Face Shape and Expression from an Image without 3D Supervision

Soubhik Sanyal 689 Dec 25, 2022
DSL for matching Python ASTs

py-ast-rule-engine This library provides a DSL (domain-specific language) to match a pattern inside a Python AST (abstract syntax tree). The library i

1 Dec 18, 2021
Deep Learning as a Cloud API Service.

Deep API Deep Learning as Cloud APIs. This project provides pre-trained deep learning models as a cloud API service. A web interface is available as w

Wu Han 4 Jan 06, 2023
Delta Conformity Sociopatterns Analysis - Delta Conformity Sociopatterns Analysis

Delta_Conformity_Sociopatterns_Analysis βˆ†-Conformity is a local homophily measur

2 Jan 09, 2022
Official repository for Automated Learning Rate Scheduler for Large-Batch Training (8th ICML Workshop on AutoML)

Automated Learning Rate Scheduler for Large-Batch Training The official repository for Automated Learning Rate Scheduler for Large-Batch Training (8th

Kakao Brain 35 Jan 04, 2023
πŸš€ An end-to-end ML applications using PyTorch, W&B, FastAPI, Docker, Streamlit and Heroku

πŸš€ An end-to-end ML applications using PyTorch, W&B, FastAPI, Docker, Streamlit and Heroku

Made With ML 82 Jun 26, 2022
Implementation of the HMAX model of vision in PyTorch

PyTorch implementation of HMAX PyTorch implementation of the HMAX model that closely follows that of the MATLAB implementation of The Laboratory for C

Marijn van Vliet 52 Oct 13, 2022
Official implementation of Protected Attribute Suppression System, ICCV 2021

Official implementation of Protected Attribute Suppression System, ICCV 2021

Prithviraj Dhar 6 Jan 01, 2023
Code for "Retrieving Black-box Optimal Images from External Databases" (WSDM 2022)

Retrieving Black-box Optimal Images from External Databases (WSDM 2022) We propose how a user retreives an optimal image from external databases of we

joisino 5 Apr 13, 2022
Agent-based model simulator for air quality and pandemic risk assessment in architectural spaces

Agent-based model simulation for air quality and pandemic risk assessment in architectural spaces. User Guide archABM is a fast and open source agent-

Vicomtech 10 Dec 05, 2022
AAAI-22 paper: SimSR: Simple Distance-based State Representationfor Deep Reinforcement Learning

SimSR Code and dataset for the paper SimSR: Simple Distance-based State Representationfor Deep Reinforcement Learning (AAAI-22). Requirements We assum

7 Dec 19, 2022
Object tracking and object detection is applied to track golf puts in real time and display stats/games.

Putting_Game Object tracking and object detection is applied to track golf puts in real time and display stats/games. Works best with the Perfect Prac

Max 1 Dec 29, 2021
Export CenterPoint PonintPillars ONNX Model For TensorRT

CenterPoint-PonintPillars Pytroch model convert to ONNX and TensorRT Welcome to CenterPoint! This project is fork from tianweiy/CenterPoint. I impleme

CarkusL 149 Dec 13, 2022
Scikit-learn compatible estimation of general graphical models

skggm : Gaussian graphical models using the scikit-learn API In the last decade, learning networks that encode conditional independence relationships

213 Jan 02, 2023
Code for reproducing our analysis in the paper titled: Image Cropping on Twitter: Fairness Metrics, their Limitations, and the Importance of Representation, Design, and Agency

Image Crop Analysis This is a repo for the code used for reproducing our Image Crop Analysis paper as shared on our blog post. If you plan to use this

Twitter Research 239 Jan 02, 2023
IMBENS: class-imbalanced ensemble learning in Python.

IMBENS: class-imbalanced ensemble learning in Python. Links: [Documentation] [Gallery] [PyPI] [Changelog] [Source] [Download] [ηŸ₯乎/Zhihu] [δΈ­ζ–‡README] [a

Zhining Liu 176 Jan 04, 2023
DI-smartcross - Decision Intelligence Platform for Traffic Crossing Signal Control

DI-smartcross DI-smartcross - Decision Intelligence Platform for Traffic Crossin

OpenDILab 213 Jan 02, 2023
Single Red Blood Cell Hydrodynamic Traps Via the Generative Design

Rbc-traps-generative-design - The generative design for single red clood cell hydrodynamic traps using GEFEST framework

Natural Systems Simulation Lab 4 Jun 16, 2022
The MATH Dataset

Measuring Mathematical Problem Solving With the MATH Dataset This is the repository for Measuring Mathematical Problem Solving With the MATH Dataset b

Dan Hendrycks 267 Dec 26, 2022