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
Sequential GCN for Active Learning

Sequential GCN for Active Learning Please cite if using the code: Link to paper. Requirements: python 3.6+ torch 1.0+ pip libraries: tqdm, sklearn, sc

45 Dec 26, 2022
Spearmint Bayesian optimization codebase

Spearmint Spearmint is a software package to perform Bayesian optimization. The Software is designed to automatically run experiments (thus the code n

Formerly: Harvard Intelligent Probabilistic Systems Group -- Now at Princeton 1.5k Dec 29, 2022
AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation

AirPose AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation Check the teaser video This repository contains the code of A

Robot Perception Group 41 Dec 05, 2022
Este conversor criará a medida exata para sua receita de capuccino gelado da grandiosa Rafaella Ballerini!

ConversorDeMedidas_CapuccinoGelado Este conversor criará a medida exata para sua receita de capuccino gelado da grandiosa Rafaella Ballerini! Requirem

Arthur Ottoni Ribeiro 48 Nov 15, 2022
RobustART: Benchmarking Robustness on Architecture Design and Training Techniques

The first comprehensive Robustness investigation benchmark on large-scale dataset ImageNet regarding ARchitecture design and Training techniques towards diverse noises.

132 Dec 23, 2022
An open-source project for applying deep learning to medical scenarios

Auto Vaidya An open source solution for creating end-end web app for employing the power of deep learning in various clinical scenarios like implant d

Smaranjit Ghose 18 May 29, 2022
Open source implementation of "A Self-Supervised Descriptor for Image Copy Detection" (SSCD).

A Self-Supervised Descriptor for Image Copy Detection (SSCD) This is the open-source codebase for "A Self-Supervised Descriptor for Image Copy Detecti

Meta Research 68 Jan 04, 2023
Official pytorch implementation of paper Dual-Level Collaborative Transformer for Image Captioning (AAAI 2021).

Dual-Level Collaborative Transformer for Image Captioning This repository contains the reference code for the paper Dual-Level Collaborative Transform

lyricpoem 160 Dec 11, 2022
Language Used: Python . Made in Jupyter(Anaconda) notebook.

FACE-DETECTION-ATTENDENCE-SYSTEM Made in Jupyter(Anaconda) notebook. Language Used: Python Steps to perform before running the program : Install Anaco

1 Jan 12, 2022
Model Zoo for MindSpore

Welcome to the Model Zoo for MindSpore In order to facilitate developers to enjoy the benefits of MindSpore framework, we will continue to add typical

MindSpore 226 Jan 07, 2023
Pytorch implementation of "A simple neural network module for relational reasoning" (Relational Networks)

Pytorch implementation of Relational Networks - A simple neural network module for relational reasoning Implemented & tested on Sort-of-CLEVR task. So

Kim Heecheol 800 Dec 05, 2022
RL-driven agent playing tic-tac-toe on starknet against challengers.

tictactoe-on-starknet RL-driven agent playing tic-tac-toe on starknet against challengers. GUI reference: https://pythonguides.com/create-a-game-using

21 Jul 30, 2022
Dilated RNNs in pytorch

PyTorch Dilated Recurrent Neural Networks PyTorch implementation of Dilated Recurrent Neural Networks (DilatedRNN). Getting Started Installation: $ pi

Zalando Research 200 Nov 17, 2022
Implementation of "A MLP-like Architecture for Dense Prediction"

A MLP-like Architecture for Dense Prediction (arXiv) Updates (22/07/2021) Initial release. Model Zoo We provide CycleMLP models pretrained on ImageNet

Shoufa Chen 244 Dec 27, 2022
Weight initialization schemes for PyTorch nn.Modules

nninit Weight initialization schemes for PyTorch nn.Modules. This is a port of the popular nninit for Torch7 by @kaixhin. ##Update This repo has been

Alykhan Tejani 69 Jan 26, 2021
💊 A 3D Generative Model for Structure-Based Drug Design (NeurIPS 2021)

A 3D Generative Model for Structure-Based Drug Design Coming soon... Citation @inproceedings{luo2021sbdd, title={A 3D Generative Model for Structu

Shitong Luo 118 Jan 05, 2023
Contextual Attention Localization for Offline Handwritten Text Recognition

CALText This repository contains the source code for CALText model introduced in "CALText: Contextual Attention Localization for Offline Handwritten T

0 Feb 17, 2022
TumorInsight is a Brain Tumor Detection and Classification model built using RESNET50 architecture.

A Brain Tumor Detection and Classification Model built using RESNET50 architecture. The model is also deployed as a web application using Flask framework.

Pranav Khurana 0 Aug 17, 2021
A Fast Knowledge Distillation Framework for Visual Recognition

FKD: A Fast Knowledge Distillation Framework for Visual Recognition Official PyTorch implementation of paper A Fast Knowledge Distillation Framework f

Zhiqiang Shen 129 Dec 24, 2022
Code from PropMix, accepted at BMVC'21

PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labels This repository is the official implementation of Hard Sample Fil

6 Dec 21, 2022