WarpRNNT loss ported in Numba CPU/CUDA for Pytorch

Last update: Oct 22, 2022

Related tags

Overview

RNNT loss in Pytorch - Numba JIT compiled (warprnnt_numba)

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 :

WarpRNNT loss in pytorch for CPU / CUDA (jit compiled)
FastEmit
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+.

Comments

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. Is this known issue? How can it be debugged and solved?

Thank you!

opened by jiay7 2
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:

Pytorch RNNT loss (CPU and JIT compiled CUDA)

FastEmit

Gradient clipping

Source code(tar.gz)
Source code(zip)

WarpRNNT loss ported in Numba CPU/CUDA for Pytorch

Related tags

Overview

RNNT loss in Pytorch - Numba JIT compiled (warprnnt_numba)

Supported Features

Installation

Usage

Tests

Requirements

You might also like...

This Repo is the official CUDA implementation of ICCV 2019 Oral paper for CARAFE: Content-Aware ReAssembly of FEatures

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

Convert Python 3 code to CUDA code.

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

LightSeq is a high performance training and inference library for sequence processing and generation implemented in CUDA

CUDA Python Low-level Bindings

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

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

An addernet CUDA version

Comments

GPU under utilization due to low occupancy.

Fix runtime speed

Improve runtime speed of numba loss

Releases(v0.4.0)

v0.4.0(Jan 30, 2022)

Supports

Improvements

v0.2.2(Jan 24, 2022)

Owner

Somshubra Majumdar

Adjust Decision Boundary for Class Imbalanced Learning

A scikit-learn compatible neural network library that wraps PyTorch

Hack Camera, Microphone, Location, Clipboard With Just a Link. Also, Get Many Details About Victim's Device. And So On...

ML-Ensemble – high performance ensemble learning

A 10000+ hours dataset for Chinese speech recognition

SpanNER: Named EntityRe-/Recognition as Span Prediction

A Streamlit demo demonstrating the Deep Dream technique. Adapted from the TensorFlow Deep Dream tutorial.

NeuroGen: activation optimized image synthesis for discovery neuroscience

Theano is a Python library that allows you to define, optimize, and evaluate mathematical expressions involving multi-dimensional arrays efficiently. It can use GPUs and perform efficient symbolic differentiation.

TensorFlow Ranking is a library for Learning-to-Rank (LTR) techniques on the TensorFlow platform

Txt2Xml tool will help you convert from txt COCO format to VOC xml format in Object Detection Problem.

Simple, but essential Bayesian optimization package

ComPhy: Compositional Physical Reasoning ofObjects and Events from Videos

Compare outputs between layers written in Tensorflow and layers written in Pytorch

Real time Human Detection Counting

Dense matching library based on PyTorch

An implementation of the AlphaZero algorithm for Gomoku (also called Gobang or Five in a Row)

Differential Privacy for Heterogeneous Federated Learning : Utility & Privacy tradeoffs

A simple, unofficial implementation of MAE using pytorch-lightning

Character Controllers using Motion VAEs