WarpRNNT loss ported in Numba CPU/CUDA for Pytorch

Related tags

Deep Learningwarprnnt_numba
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

Jiaqi Wang 42 Jan 7, 2023
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

null 106 Dec 14, 2022
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

Yuval Rosen 3 Jul 14, 2021
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

Xavier Tao 14 Dec 17, 2022
LightSeq is a high performance training and inference library for sequence processing and generation implemented in CUDA
LightSeq is a high performance training and inference library for sequence processing and generation implemented in CUDA

LightSeq: A High Performance Library for Sequence Processing and Generation

Bytedance Inc. 2.5k Jan 6, 2023
CUDA Python Low-level Bindings

CUDA Python Low-level Bindings

NVIDIA Corporation 529 Jan 3, 2023
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

Pliable Pixels 6 Jan 12, 2022
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. 🚀 Features 🙅 Prevents CUDA error

RenChu Wang 1.7k Jan 2, 2023
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

LingXY 4 Jun 20, 2022
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
GitHub Repository
ROMP: Monocular, One-stage, Regression of Multiple 3D People, ICCV21

Monocular, One-stage, Regression of Multiple 3D People ROMP, accepted by ICCV 2021, is a concise one-stage network for multi-person 3D mesh recovery f

Yu Sun 937 Jan 04, 2023
Learned model to estimate number of distinct values (NDV) of a population using a small sample.

Learned NDV estimator Learned model to estimate number of distinct values (NDV) of a population using a small sample. The model approximates the maxim

2 Nov 21, 2022
Removing Inter-Experimental Variability from Functional Data in Systems Neuroscience

Removing Inter-Experimental Variability from Functional Data in Systems Neuroscience This repository is the official implementation of [https://www.bi

Eulerlab 6 Oct 09, 2022
Orchestrating Distributed Materials Acceleration Platform Tutorial

Orchestrating Distributed Materials Acceleration Platform Tutorial This tutorial for orchestrating distributed materials acceleration platform was pre

BIG-MAP 1 Jan 25, 2022
Efficient Training of Audio Transformers with Patchout

PaSST: Efficient Training of Audio Transformers with Patchout This is the implementation for Efficient Training of Audio Transformers with Patchout Pa

165 Dec 26, 2022
Implementation of the Chamfer Distance as a module for pyTorch

Chamfer Distance for pyTorch This is an implementation of the Chamfer Distance as a module for pyTorch. It is written as a custom C++/CUDA extension.

Christian Diller 205 Jan 05, 2023
Software & Hardware to do multi color printing with Sharpies

3D Print Colorizer is a combination of 3D printed parts and a Cura plugin which allows anyone with an Ender 3 like 3D printer to produce multi colored

343 Jan 06, 2023
Code for the paper "Can Active Learning Preemptively Mitigate Fairness Issues?" presented at RAI 2021.

Can Active Learning Preemptively Mitigate Fairness Issues? Code for the paper "Can Active Learning Preemptively Mitigate Fairness Issues?" presented a

ElementAI 7 Aug 12, 2022
Toward Realistic Single-View 3D Object Reconstruction with Unsupervised Learning from Multiple Images (ICCV 2021)

Table of Content Introduction Getting Started Datasets Installation Experiments Training & Testing Pretrained models Texture fine-tuning Demo Toward R

VinAI Research 42 Dec 05, 2022
Official implementation of VQ-Diffusion

Official implementation of VQ-Diffusion: Vector Quantized Diffusion Model for Text-to-Image Synthesis

Microsoft 592 Jan 03, 2023
Source code for From Stars to Subgraphs

GNNAsKernel Official code for From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness Visualizations GNN-AK(+) GNN-AK(+) with Subgra

44 Dec 19, 2022
HyperLib: Deep learning in the Hyperbolic space

HyperLib: Deep learning in the Hyperbolic space Background This library implements common Neural Network components in the hypberbolic space (using th

105 Dec 25, 2022
This is implementation of AlexNet(2012) with 3D Convolution on TensorFlow (AlexNet 3D).

AlexNet_3dConv TensorFlow implementation of AlexNet(2012) by Alex Krizhevsky, with 3D convolutiional layers. 3D AlexNet Network with a standart AlexNe

Denis Timonin 41 Jan 16, 2022
Code for: Gradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space. Nicholas Monath, Manzil Zaheer, Daniel Silva, Andrew McCallum, Amr Ahmed. KDD 2019.

gHHC Code for: Gradient-based Hierarchical Clustering using Continuous Representations of Trees in Hyperbolic Space. Nicholas Monath, Manzil Zaheer, D

Nicholas Monath 35 Nov 16, 2022
Tensorflow 2.x implementation of Vision-Transformer model

Vision Transformer Unofficial Tensorflow 2.x implementation of the Transformer based Image Classification model proposed by the paper AN IMAGE IS WORT

Soumik Rakshit 16 Jul 20, 2022
A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal

A lightweight library designed to accelerate the process of training PyTorch models by providing a minimal, but extensible training loop which is flexible enough to handle the majority of use cases,

Chris Hughes 110 Dec 23, 2022
Magisk module to enable hidden features on Android 12 Developer Preview 1.

Android 12 Extensions This is a Magisk module that enables hidden features on Android 12 Developer Preview 1. Features Scrolling screenshots Wallpaper

Danny Lin 384 Jan 06, 2023
Repository for the semantic WMI loss

Installation: pip install -e . Installing DL2: First clone DL2 in a separate directory and install it using the following commands: git clone https:/

Nick Hoernle 4 Sep 15, 2022
Prososdy Morph: A python library for manipulating pitch and duration in an algorithmic way, for resynthesizing speech.

ProMo (Prosody Morph) Questions? Comments? Feedback? Chat with us on gitter! A library for manipulating pitch and duration in an algorithmic way, for

Tim 71 Jan 02, 2023
Everything you need to know about NumPy( Creating Arrays, Indexing, Math,Statistics,Reshaping).

Everything you need to know about NumPy( Creating Arrays, Indexing, Math,Statistics,Reshaping).

1 Feb 14, 2022