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. 🚀 Features 🙅 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
HW3 ― GAN, ACGAN and UDA

HW3 ― GAN, ACGAN and UDA In this assignment, you are given datasets of human face and digit images. You will need to implement the models of both GAN

grassking100 1 Dec 13, 2021
Image Captioning using CNN and Transformers

Image-Captioning Keras/Tensorflow Image Captioning application using CNN and Transformer as encoder/decoder. In particulary, the architecture consists

24 Dec 28, 2022
This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their coordinates and detected labels.

This YoloV5 based model is fit to detect people and different types of land vehicles, and displaying their density on a fitted map, according to their

Liron Bdolah 8 May 22, 2022
A programming language written with python

Kaoft A programming language written with python How to use A simple Hello World: c="Hello World" c Output: "Hello World" Operators: a=12

1 Jan 24, 2022
Microsoft Cognitive Toolkit (CNTK), an open source deep-learning toolkit

CNTK Chat Windows build status Linux build status The Microsoft Cognitive Toolkit (https://cntk.ai) is a unified deep learning toolkit that describes

Microsoft 17.3k Dec 29, 2022
Deep Learning and Reinforcement Learning Library for Scientists and Engineers 🔥

TensorLayer is a novel TensorFlow-based deep learning and reinforcement learning library designed for researchers and engineers. It provides an extens

TensorLayer Community 7.1k Dec 29, 2022
Python framework for Stochastic Differential Equations modeling

SDElearn: a Python package for SDE modeling This package implements functionalities for working with Stochastic Differential Equations models (SDEs fo

4 May 10, 2022
project page for VinVL

VinVL: Revisiting Visual Representations in Vision-Language Models Updates 02/28/2021: Project page built. Introduction This repository is the project

308 Jan 09, 2023
How to use TensorLayer

How to use TensorLayer While research in Deep Learning continues to improve the world, we use a bunch of tricks to implement algorithms with TensorLay

zhangrui 349 Dec 07, 2022
(JMLR'19) A Python Toolbox for Scalable Outlier Detection (Anomaly Detection)

Python Outlier Detection (PyOD) Deployment & Documentation & Stats Build Status & Coverage & Maintainability & License PyOD is a comprehensive and sca

Yue Zhao 6.6k Jan 03, 2023
Source code, data, and evaluation details for “Cross-Lingual Citations in English Papers: A Large-Scale Analysis of Prevalence, Formation, and Ramifications”

Analysis of cross-lingual citations in English papers Contents initial_analysis Source code, data, and evaluation details as published at ICADL2020 ci

Tarek Saier 1 Oct 27, 2022
MLPs for Vision and Langauge Modeling (Coming Soon)

MLP Architectures for Vision-and-Language Modeling: An Empirical Study MLP Architectures for Vision-and-Language Modeling: An Empirical Study (Code wi

Yixin Nie 27 May 09, 2022
Offical implementation of Shunted Self-Attention via Multi-Scale Token Aggregation

Shunted Transformer This is the offical implementation of Shunted Self-Attention via Multi-Scale Token Aggregation by Sucheng Ren, Daquan Zhou, Shengf

156 Dec 27, 2022
Gym environment for FLIPIT: The Game of "Stealthy Takeover"

gym-flipit Gym environment for FLIPIT: The Game of "Stealthy Takeover" invented by Marten van Dijk, Ari Juels, Alina Oprea, and Ronald L. Rivest. Desi

Lisa Oakley 2 Dec 15, 2021
Code for Understanding Pooling in Graph Neural Networks

Select, Reduce, Connect This repository contains the code used for the experiments of: "Understanding Pooling in Graph Neural Networks" Setup Install

Daniele Grattarola 37 Dec 13, 2022
Official implementation for the paper: Generating Smooth Pose Sequences for Diverse Human Motion Prediction

Generating Smooth Pose Sequences for Diverse Human Motion Prediction This is official implementation for the paper Generating Smooth Pose Sequences fo

Wei Mao 28 Dec 10, 2022
Code of the paper "Shaping Visual Representations with Attributes for Few-Shot Learning (ASL)".

Shaping Visual Representations with Attributes for Few-Shot Learning This code implements the Shaping Visual Representations with Attributes for Few-S

chx_nju 9 Sep 01, 2022
ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction

ViSER: Video-Specific Surface Embeddings for Articulated 3D Shape Reconstruction. NeurIPS 2021.

Gengshan Yang 59 Nov 25, 2022
✔️ Visual, reactive testing library for Julia. Time machine included.

PlutoTest.jl (alpha release) Visual, reactive testing library for Julia A macro @test that you can use to verify your code's correctness. But instead

Pluto 68 Dec 20, 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