Skip to content

GitLab

Commit af155c51 authored by chenzk's avatar chenzk
Browse files

v1.0

parents
Pipeline #2732 failed with stages
in 0 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 2207 additions and 0 deletions
CITATION.cff 0 → 100644
View file @ af155c51
# This CITATION.cff file was generated with https://bit.ly/cffinit
cff-version: 1.2.0
title: Ultralytics YOLO
message: >-
If you use this software, please cite it using the
metadata from this file.
type: software
authors:
- given-names: Glenn
family-names: Jocher
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0001-5950-6979'
- family-names: Qiu
given-names: Jing
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0003-3783-7069'
- given-names: Ayush
family-names: Chaurasia
affiliation: Ultralytics
orcid: 'https://orcid.org/0000-0002-7603-6750'
repository-code: 'https://github.com/ultralytics/ultralytics'
url: 'https://ultralytics.com'
license: AGPL-3.0
version: 8.0.0
date-released: '2023-01-10'
CONTRIBUTING.md 0 → 100644
View file @ af155c51
---
comments: true
description: Learn how to contribute to Ultralytics YOLO open-source repositories. Follow guidelines for pull requests, code of conduct, and bug reporting.
keywords: Ultralytics, YOLO, open-source, contribution, pull request, code of conduct, bug reporting, GitHub, CLA, Google-style docstrings
---
# Contributing to Ultralytics Open-Source Projects
Welcome! We're thrilled that you're considering contributing to our [Ultralytics](https://www.ultralytics.com/) [open-source](https://github.com/ultralytics) projects. Your involvement not only helps enhance the quality of our repositories but also benefits the entire community. This guide provides clear guidelines and best practices to help you get started.
<a href="https://github.com/ultralytics/ultralytics/graphs/contributors">
<img width="100%" src="https://github.com/ultralytics/assets/raw/main/im/image-contributors.png" alt="Ultralytics open-source contributors"></a>
## Table of Contents
1. [Code of Conduct](#code-of-conduct)
2. [Contributing via Pull Requests](#contributing-via-pull-requests)
- [CLA Signing](#cla-signing)
- [Google-Style Docstrings](#google-style-docstrings)
- [GitHub Actions CI Tests](#github-actions-ci-tests)
3. [Reporting Bugs](#reporting-bugs)
4. [License](#license)
5. [Conclusion](#conclusion)
6. [FAQ](#faq)
## Code of Conduct
To ensure a welcoming and inclusive environment for everyone, all contributors must adhere to our [Code of Conduct](https://docs.ultralytics.com/help/code_of_conduct/). Respect, kindness, and professionalism are at the heart of our community.
## Contributing via Pull Requests
We greatly appreciate contributions in the form of pull requests. To make the review process as smooth as possible, please follow these steps:
1. **[Fork the repository](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/fork-a-repo):** Start by forking the Ultralytics YOLO repository to your GitHub account.
2. **[Create a branch](https://docs.github.com/en/desktop/making-changes-in-a-branch/managing-branches-in-github-desktop):** Create a new branch in your forked repository with a clear, descriptive name that reflects your changes.
3. **Make your changes:** Ensure your code adheres to the project's style guidelines and does not introduce any new errors or warnings.
4. **[Test your changes](https://github.com/ultralytics/ultralytics/tree/main/tests):** Before submitting, test your changes locally to confirm they work as expected and don't cause any new issues.
5. **[Commit your changes](https://docs.github.com/en/desktop/making-changes-in-a-branch/committing-and-reviewing-changes-to-your-project-in-github-desktop):** Commit your changes with a concise and descriptive commit message. If your changes address a specific issue, include the issue number in your commit message.
6. **[Create a pull request](https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/proposing-changes-to-your-work-with-pull-requests/creating-a-pull-request):** Submit a pull request from your forked repository to the main Ultralytics YOLO repository. Provide a clear and detailed explanation of your changes and how they improve the project.
### CLA Signing
Before we can merge your pull request, you must sign our [Contributor License Agreement (CLA)](https://docs.ultralytics.com/help/CLA/). This legal agreement ensures that your contributions are properly licensed, allowing the project to continue being distributed under the AGPL-3.0 license.
After submitting your pull request, the CLA bot will guide you through the signing process. To sign the CLA, simply add a comment in your PR stating:
```
I have read the CLA Document and I sign the CLA
```
### Google-Style Docstrings
When adding new functions or classes, please include [Google-style docstrings](https://google.github.io/styleguide/pyguide.html). These docstrings provide clear, standardized documentation that helps other developers understand and maintain your code.
#### Example
This example illustrates a Google-style docstring. Ensure that both input and output `types` are always enclosed in parentheses, e.g., `(bool)`.
```python
def example_function(arg1, arg2=4):
"""
Example function demonstrating Google-style docstrings.
Args:
arg1 (int): The first argument.
arg2 (int): The second argument, with a default value of 4.
Returns:
(bool): True if successful, False otherwise.
Examples:
>>> result = example_function(1, 2) # returns False
"""
if arg1 == arg2:
return True
return False
```
#### Example with type hints
This example includes both a Google-style docstring and type hints for arguments and returns, though using either independently is also acceptable.
```python
def example_function(arg1: int, arg2: int = 4) -> bool:
"""
Example function demonstrating Google-style docstrings.
Args:
arg1: The first argument.
arg2: The second argument, with a default value of 4.
Returns:
True if successful, False otherwise.
Examples:
>>> result = example_function(1, 2) # returns False
"""
if arg1 == arg2:
return True
return False
```
#### Example Single-line
For smaller or simpler functions, a single-line docstring may be sufficient. The docstring must use three double-quotes, be a complete sentence, start with a capital letter, and end with a period.
```python
def example_small_function(arg1: int, arg2: int = 4) -> bool:
"""Example function with a single-line docstring."""
return arg1 == arg2
```
### GitHub Actions CI Tests
All pull requests must pass the GitHub Actions [Continuous Integration](https://docs.ultralytics.com/help/CI/) (CI) tests before they can be merged. These tests include linting, unit tests, and other checks to ensure that your changes meet the project's quality standards. Review the CI output and address any issues that arise.
## Reporting Bugs
We highly value bug reports as they help us maintain the quality of our projects. When reporting a bug, please provide a [Minimum Reproducible Example](https://docs.ultralytics.com/help/minimum_reproducible_example/)—a simple, clear code example that consistently reproduces the issue. This allows us to quickly identify and resolve the problem.
## License
Ultralytics uses the [GNU Affero General Public License v3.0 (AGPL-3.0)](https://github.com/ultralytics/ultralytics/blob/main/LICENSE) for its repositories. This license promotes openness, transparency, and collaborative improvement in software development. It ensures that all users have the freedom to use, modify, and share the software, fostering a strong community of collaboration and innovation.
We encourage all contributors to familiarize themselves with the terms of the AGPL-3.0 license to contribute effectively and ethically to the Ultralytics open-source community.
## Conclusion
Thank you for your interest in contributing to [Ultralytics](https://www.ultralytics.com/) [open-source](https://github.com/ultralytics) YOLO projects. Your participation is essential in shaping the future of our software and building a vibrant community of innovation and collaboration. Whether you're enhancing code, reporting bugs, or suggesting new features, your contributions are invaluable.
We're excited to see your ideas come to life and appreciate your commitment to advancing object detection technology. Together, let's continue to grow and innovate in this exciting open-source journey. Happy coding! 🚀🌟
## FAQ
### Why should I contribute to Ultralytics YOLO open-source repositories?
Contributing to Ultralytics YOLO open-source repositories improves the software, making it more robust and feature-rich for the entire community. Contributions can include code enhancements, bug fixes, documentation improvements, and new feature implementations. Additionally, contributing allows you to collaborate with other skilled developers and experts in the field, enhancing your own skills and reputation. For details on how to get started, refer to the [Contributing via Pull Requests](#contributing-via-pull-requests) section.
### How do I sign the Contributor License Agreement (CLA) for Ultralytics YOLO?
To sign the Contributor License Agreement (CLA), follow the instructions provided by the CLA bot after submitting your pull request. This process ensures that your contributions are properly licensed under the AGPL-3.0 license, maintaining the legal integrity of the open-source project. Add a comment in your pull request stating:
```
I have read the CLA Document and I sign the CLA.
```
For more information, see the [CLA Signing](#cla-signing) section.
### What are Google-style docstrings, and why are they required for Ultralytics YOLO contributions?
Google-style docstrings provide clear, concise documentation for functions and classes, improving code readability and maintainability. These docstrings outline the function's purpose, arguments, and return values with specific formatting rules. When contributing to Ultralytics YOLO, following Google-style docstrings ensures that your additions are well-documented and easily understood. For examples and guidelines, visit the [Google-Style Docstrings](#google-style-docstrings) section.
### How can I ensure my changes pass the GitHub Actions CI tests?
Before your pull request can be merged, it must pass all GitHub Actions Continuous Integration (CI) tests. These tests include linting, unit tests, and other checks to ensure the code meets
the project's quality standards. Review the CI output and fix any issues. For detailed information on the CI process and troubleshooting tips, see the [GitHub Actions CI Tests](#github-actions-ci-tests) section.
### How do I report a bug in Ultralytics YOLO repositories?
To report a bug, provide a clear and concise [Minimum Reproducible Example](https://docs.ultralytics.com/help/minimum_reproducible_example/) along with your bug report. This helps developers quickly identify and fix the issue. Ensure your example is minimal yet sufficient to replicate the problem. For more detailed steps on reporting bugs, refer to the [Reporting Bugs](#reporting-bugs) section.
LICENSE 0 → 100644
View file @ af155c51
GNU AFFERO GENERAL PUBLIC LICENSE
Version 3, 19 November 2007
Copyright (C) 2007 Free Software Foundation, Inc. <https://fsf.org/>
Everyone is permitted to copy and distribute verbatim copies
of this license document, but changing it is not allowed.
Preamble
The GNU Affero General Public License is a free, copyleft license for
software and other kinds of works, specifically designed to ensure
cooperation with the community in the case of network server software.
The licenses for most software and other practical works are designed
to take away your freedom to share and change the works. By contrast,
our General Public Licenses are intended to guarantee your freedom to
share and change all versions of a program--to make sure it remains free
software for all its users.
When we speak of free software, we are referring to freedom, not
price. Our General Public Licenses are designed to make sure that you
have the freedom to distribute copies of free software (and charge for
them if you wish), that you receive source code or can get it if you
want it, that you can change the software or use pieces of it in new
free programs, and that you know you can do these things.
Developers that use our General Public Licenses protect your rights
with two steps: (1) assert copyright on the software, and (2) offer
you this License which gives you legal permission to copy, distribute
and/or modify the software.
A secondary benefit of defending all users' freedom is that
improvements made in alternate versions of the program, if they
receive widespread use, become available for other developers to
incorporate. Many developers of free software are heartened and
encouraged by the resulting cooperation. However, in the case of
software used on network servers, this result may fail to come about.
The GNU General Public License permits making a modified version and
letting the public access it on a server without ever releasing its
source code to the public.
The GNU Affero General Public License is designed specifically to
ensure that, in such cases, the modified source code becomes available
to the community. It requires the operator of a network server to
provide the source code of the modified version running there to the
users of that server. Therefore, public use of a modified version, on
a publicly accessible server, gives the public access to the source
code of the modified version.
An older license, called the Affero General Public License and
published by Affero, was designed to accomplish similar goals. This is
a different license, not a version of the Affero GPL, but Affero has
released a new version of the Affero GPL which permits relicensing under
this license.
The precise terms and conditions for copying, distribution and
modification follow.
TERMS AND CONDITIONS
0. Definitions.
"This License" refers to version 3 of the GNU Affero General Public License.
"Copyright" also means copyright-like laws that apply to other kinds of
works, such as semiconductor masks.
"The Program" refers to any copyrightable work licensed under this
License. Each licensee is addressed as "you". "Licensees" and
"recipients" may be individuals or organizations.
To "modify" a work means to copy from or adapt all or part of the work
in a fashion requiring copyright permission, other than the making of an
exact copy. The resulting work is called a "modified version" of the
earlier work or a work "based on" the earlier work.
A "covered work" means either the unmodified Program or a work based
on the Program.
To "propagate" a work means to do anything with it that, without
permission, would make you directly or secondarily liable for
infringement under applicable copyright law, except executing it on a
computer or modifying a private copy. Propagation includes copying,
distribution (with or without modification), making available to the
public, and in some countries other activities as well.
To "convey" a work means any kind of propagation that enables other
parties to make or receive copies. Mere interaction with a user through
a computer network, with no transfer of a copy, is not conveying.
An interactive user interface displays "Appropriate Legal Notices"
to the extent that it includes a convenient and prominently visible
feature that (1) displays an appropriate copyright notice, and (2)
tells the user that there is no warranty for the work (except to the
extent that warranties are provided), that licensees may convey the
work under this License, and how to view a copy of this License. If
the interface presents a list of user commands or options, such as a
menu, a prominent item in the list meets this criterion.
1. Source Code.
The "source code" for a work means the preferred form of the work
for making modifications to it. "Object code" means any non-source
form of a work.
A "Standard Interface" means an interface that either is an official
standard defined by a recognized standards body, or, in the case of
interfaces specified for a particular programming language, one that
is widely used among developers working in that language.
The "System Libraries" of an executable work include anything, other
than the work as a whole, that (a) is included in the normal form of
packaging a Major Component, but which is not part of that Major
Component, and (b) serves only to enable use of the work with that
Major Component, or to implement a Standard Interface for which an
implementation is available to the public in source code form. A
"Major Component", in this context, means a major essential component
(kernel, window system, and so on) of the specific operating system
(if any) on which the executable work runs, or a compiler used to
produce the work, or an object code interpreter used to run it.
The "Corresponding Source" for a work in object code form means all
the source code needed to generate, install, and (for an executable
work) run the object code and to modify the work, including scripts to
control those activities. However, it does not include the work's
System Libraries, or general-purpose tools or generally available free
programs which are used unmodified in performing those activities but
which are not part of the work. For example, Corresponding Source
includes interface definition files associated with source files for
the work, and the source code for shared libraries and dynamically
linked subprograms that the work is specifically designed to require,
such as by intimate data communication or control flow between those
subprograms and other parts of the work.
The Corresponding Source need not include anything that users
can regenerate automatically from other parts of the Corresponding
Source.
The Corresponding Source for a work in source code form is that
same work.
2. Basic Permissions.
All rights granted under this License are granted for the term of
copyright on the Program, and are irrevocable provided the stated
conditions are met. This License explicitly affirms your unlimited
permission to run the unmodified Program. The output from running a
covered work is covered by this License only if the output, given its
content, constitutes a covered work. This License acknowledges your
rights of fair use or other equivalent, as provided by copyright law.
You may make, run and propagate covered works that you do not
convey, without conditions so long as your license otherwise remains
in force. You may convey covered works to others for the sole purpose
of having them make modifications exclusively for you, or provide you
with facilities for running those works, provided that you comply with
the terms of this License in conveying all material for which you do
not control copyright. Those thus making or running the covered works
for you must do so exclusively on your behalf, under your direction
and control, on terms that prohibit them from making any copies of
your copyrighted material outside their relationship with you.
Conveying under any other circumstances is permitted solely under
the conditions stated below. Sublicensing is not allowed; section 10
makes it unnecessary.
3. Protecting Users' Legal Rights From Anti-Circumvention Law.
No covered work shall be deemed part of an effective technological
measure under any applicable law fulfilling obligations under article
11 of the WIPO copyright treaty adopted on 20 December 1996, or
similar laws prohibiting or restricting circumvention of such
measures.
When you convey a covered work, you waive any legal power to forbid
circumvention of technological measures to the extent such circumvention
is effected by exercising rights under this License with respect to
the covered work, and you disclaim any intention to limit operation or
modification of the work as a means of enforcing, against the work's
users, your or third parties' legal rights to forbid circumvention of
technological measures.
4. Conveying Verbatim Copies.
You may convey verbatim copies of the Program's source code as you
receive it, in any medium, provided that you conspicuously and
appropriately publish on each copy an appropriate copyright notice;
keep intact all notices stating that this License and any
non-permissive terms added in accord with section 7 apply to the code;
keep intact all notices of the absence of any warranty; and give all
recipients a copy of this License along with the Program.
You may charge any price or no price for each copy that you convey,
and you may offer support or warranty protection for a fee.
5. Conveying Modified Source Versions.
You may convey a work based on the Program, or the modifications to
produce it from the Program, in the form of source code under the
terms of section 4, provided that you also meet all of these conditions:
a) The work must carry prominent notices stating that you modified
it, and giving a relevant date.
b) The work must carry prominent notices stating that it is
released under this License and any conditions added under section
7. This requirement modifies the requirement in section 4 to
"keep intact all notices".
c) You must license the entire work, as a whole, under this
License to anyone who comes into possession of a copy. This
License will therefore apply, along with any applicable section 7
additional terms, to the whole of the work, and all its parts,
regardless of how they are packaged. This License gives no
permission to license the work in any other way, but it does not
invalidate such permission if you have separately received it.
d) If the work has interactive user interfaces, each must display
Appropriate Legal Notices; however, if the Program has interactive
interfaces that do not display Appropriate Legal Notices, your
work need not make them do so.
A compilation of a covered work with other separate and independent
works, which are not by their nature extensions of the covered work,
and which are not combined with it such as to form a larger program,
in or on a volume of a storage or distribution medium, is called an
"aggregate" if the compilation and its resulting copyright are not
used to limit the access or legal rights of the compilation's users
beyond what the individual works permit. Inclusion of a covered work
in an aggregate does not cause this License to apply to the other
parts of the aggregate.
6. Conveying Non-Source Forms.
You may convey a covered work in object code form under the terms
of sections 4 and 5, provided that you also convey the
machine-readable Corresponding Source under the terms of this License,
in one of these ways:
a) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by the
Corresponding Source fixed on a durable physical medium
customarily used for software interchange.
b) Convey the object code in, or embodied in, a physical product
(including a physical distribution medium), accompanied by a
written offer, valid for at least three years and valid for as
long as you offer spare parts or customer support for that product
model, to give anyone who possesses the object code either (1) a
copy of the Corresponding Source for all the software in the
product that is covered by this License, on a durable physical
medium customarily used for software interchange, for a price no
more than your reasonable cost of physically performing this
conveying of source, or (2) access to copy the
Corresponding Source from a network server at no charge.
c) Convey individual copies of the object code with a copy of the
written offer to provide the Corresponding Source. This
alternative is allowed only occasionally and noncommercially, and
only if you received the object code with such an offer, in accord
with subsection 6b.
d) Convey the object code by offering access from a designated
place (gratis or for a charge), and offer equivalent access to the
Corresponding Source in the same way through the same place at no
further charge. You need not require recipients to copy the
Corresponding Source along with the object code. If the place to
copy the object code is a network server, the Corresponding Source
may be on a different server (operated by you or a third party)
that supports equivalent copying facilities, provided you maintain
clear directions next to the object code saying where to find the
Corresponding Source. Regardless of what server hosts the
Corresponding Source, you remain obligated to ensure that it is
available for as long as needed to satisfy these requirements.
e) Convey the object code using peer-to-peer transmission, provided
you inform other peers where the object code and Corresponding
Source of the work are being offered to the general public at no
charge under subsection 6d.
A separable portion of the object code, whose source code is excluded
from the Corresponding Source as a System Library, need not be
included in conveying the object code work.
A "User Product" is either (1) a "consumer product", which means any
tangible personal property which is normally used for personal, family,
or household purposes, or (2) anything designed or sold for incorporation
into a dwelling. In determining whether a product is a consumer product,
doubtful cases shall be resolved in favor of coverage. For a particular
product received by a particular user, "normally used" refers to a
typical or common use of that class of product, regardless of the status
of the particular user or of the way in which the particular user
actually uses, or expects or is expected to use, the product. A product
is a consumer product regardless of whether the product has substantial
commercial, industrial or non-consumer uses, unless such uses represent
the only significant mode of use of the product.
"Installation Information" for a User Product means any methods,
procedures, authorization keys, or other information required to install
and execute modified versions of a covered work in that User Product from
a modified version of its Corresponding Source. The information must
suffice to ensure that the continued functioning of the modified object
code is in no case prevented or interfered with solely because
modification has been made.
If you convey an object code work under this section in, or with, or
specifically for use in, a User Product, and the conveying occurs as
part of a transaction in which the right of possession and use of the
User Product is transferred to the recipient in perpetuity or for a
fixed term (regardless of how the transaction is characterized), the
Corresponding Source conveyed under this section must be accompanied
by the Installation Information. But this requirement does not apply
if neither you nor any third party retains the ability to install
modified object code on the User Product (for example, the work has
been installed in ROM).
The requirement to provide Installation Information does not include a
requirement to continue to provide support service, warranty, or updates
for a work that has been modified or installed by the recipient, or for
the User Product in which it has been modified or installed. Access to a
network may be denied when the modification itself materially and
adversely affects the operation of the network or violates the rules and
protocols for communication across the network.
Corresponding Source conveyed, and Installation Information provided,
in accord with this section must be in a format that is publicly
documented (and with an implementation available to the public in
source code form), and must require no special password or key for
unpacking, reading or copying.
7. Additional Terms.
"Additional permissions" are terms that supplement the terms of this
License by making exceptions from one or more of its conditions.
Additional permissions that are applicable to the entire Program shall
be treated as though they were included in this License, to the extent
that they are valid under applicable law. If additional permissions
apply only to part of the Program, that part may be used separately
under those permissions, but the entire Program remains governed by
this License without regard to the additional permissions.
When you convey a copy of a covered work, you may at your option
remove any additional permissions from that copy, or from any part of
it. (Additional permissions may be written to require their own
removal in certain cases when you modify the work.) You may place
additional permissions on material, added by you to a covered work,
for which you have or can give appropriate copyright permission.
Notwithstanding any other provision of this License, for material you
add to a covered work, you may (if authorized by the copyright holders of
that material) supplement the terms of this License with terms:
a) Disclaiming warranty or limiting liability differently from the
terms of sections 15 and 16 of this License; or
b) Requiring preservation of specified reasonable legal notices or
author attributions in that material or in the Appropriate Legal
Notices displayed by works containing it; or
c) Prohibiting misrepresentation of the origin of that material, or
requiring that modified versions of such material be marked in
reasonable ways as different from the original version; or
d) Limiting the use for publicity purposes of names of licensors or
authors of the material; or
e) Declining to grant rights under trademark law for use of some
trade names, trademarks, or service marks; or
f) Requiring indemnification of licensors and authors of that
material by anyone who conveys the material (or modified versions of
it) with contractual assumptions of liability to the recipient, for
any liability that these contractual assumptions directly impose on
those licensors and authors.
All other non-permissive additional terms are considered "further
restrictions" within the meaning of section 10. If the Program as you
received it, or any part of it, contains a notice stating that it is
governed by this License along with a term that is a further
restriction, you may remove that term. If a license document contains
a further restriction but permits relicensing or conveying under this
License, you may add to a covered work material governed by the terms
of that license document, provided that the further restriction does
not survive such relicensing or conveying.
If you add terms to a covered work in accord with this section, you
must place, in the relevant source files, a statement of the
additional terms that apply to those files, or a notice indicating
where to find the applicable terms.
Additional terms, permissive or non-permissive, may be stated in the
form of a separately written license, or stated as exceptions;
the above requirements apply either way.
8. Termination.
You may not propagate or modify a covered work except as expressly
provided under this License. Any attempt otherwise to propagate or
modify it is void, and will automatically terminate your rights under
this License (including any patent licenses granted under the third
paragraph of section 11).
However, if you cease all violation of this License, then your
license from a particular copyright holder is reinstated (a)
provisionally, unless and until the copyright holder explicitly and
finally terminates your license, and (b) permanently, if the copyright
holder fails to notify you of the violation by some reasonable means
prior to 60 days after the cessation.
Moreover, your license from a particular copyright holder is
reinstated permanently if the copyright holder notifies you of the
violation by some reasonable means, this is the first time you have
received notice of violation of this License (for any work) from that
copyright holder, and you cure the violation prior to 30 days after
your receipt of the notice.
Termination of your rights under this section does not terminate the
licenses of parties who have received copies or rights from you under
this License. If your rights have been terminated and not permanently
reinstated, you do not qualify to receive new licenses for the same
material under section 10.
9. Acceptance Not Required for Having Copies.
You are not required to accept this License in order to receive or
run a copy of the Program. Ancillary propagation of a covered work
occurring solely as a consequence of using peer-to-peer transmission
to receive a copy likewise does not require acceptance. However,
nothing other than this License grants you permission to propagate or
modify any covered work. These actions infringe copyright if you do
not accept this License. Therefore, by modifying or propagating a
covered work, you indicate your acceptance of this License to do so.
10. Automatic Licensing of Downstream Recipients.
Each time you convey a covered work, the recipient automatically
receives a license from the original licensors, to run, modify and
propagate that work, subject to this License. You are not responsible
for enforcing compliance by third parties with this License.
An "entity transaction" is a transaction transferring control of an
organization, or substantially all assets of one, or subdividing an
organization, or merging organizations. If propagation of a covered
work results from an entity transaction, each party to that
transaction who receives a copy of the work also receives whatever
licenses to the work the party's predecessor in interest had or could
give under the previous paragraph, plus a right to possession of the
Corresponding Source of the work from the predecessor in interest, if
the predecessor has it or can get it with reasonable efforts.
You may not impose any further restrictions on the exercise of the
rights granted or affirmed under this License. For example, you may
not impose a license fee, royalty, or other charge for exercise of
rights granted under this License, and you may not initiate litigation
(including a cross-claim or counterclaim in a lawsuit) alleging that
any patent claim is infringed by making, using, selling, offering for
sale, or importing the Program or any portion of it.
11. Patents.
A "contributor" is a copyright holder who authorizes use under this
License of the Program or a work on which the Program is based. The
work thus licensed is called the contributor's "contributor version".
A contributor's "essential patent claims" are all patent claims
owned or controlled by the contributor, whether already acquired or
hereafter acquired, that would be infringed by some manner, permitted
by this License, of making, using, or selling its contributor version,
but do not include claims that would be infringed only as a
consequence of further modification of the contributor version. For
purposes of this definition, "control" includes the right to grant
patent sublicenses in a manner consistent with the requirements of
this License.
Each contributor grants you a non-exclusive, worldwide, royalty-free
patent license under the contributor's essential patent claims, to
make, use, sell, offer for sale, import and otherwise run, modify and
propagate the contents of its contributor version.
In the following three paragraphs, a "patent license" is any express
agreement or commitment, however denominated, not to enforce a patent
(such as an express permission to practice a patent or covenant not to
sue for patent infringement). To "grant" such a patent license to a
party means to make such an agreement or commitment not to enforce a
patent against the party.
If you convey a covered work, knowingly relying on a patent license,
and the Corresponding Source of the work is not available for anyone
to copy, free of charge and under the terms of this License, through a
publicly available network server or other readily accessible means,
then you must either (1) cause the Corresponding Source to be so
available, or (2) arrange to deprive yourself of the benefit of the
patent license for this particular work, or (3) arrange, in a manner
consistent with the requirements of this License, to extend the patent
license to downstream recipients. "Knowingly relying" means you have
actual knowledge that, but for the patent license, your conveying the
covered work in a country, or your recipient's use of the covered work
in a country, would infringe one or more identifiable patents in that
country that you have reason to believe are valid.
If, pursuant to or in connection with a single transaction or
arrangement, you convey, or propagate by procuring conveyance of, a
covered work, and grant a patent license to some of the parties
receiving the covered work authorizing them to use, propagate, modify
or convey a specific copy of the covered work, then the patent license
you grant is automatically extended to all recipients of the covered
work and works based on it.
A patent license is "discriminatory" if it does not include within
the scope of its coverage, prohibits the exercise of, or is
conditioned on the non-exercise of one or more of the rights that are
specifically granted under this License. You may not convey a covered
work if you are a party to an arrangement with a third party that is
in the business of distributing software, under which you make payment
to the third party based on the extent of your activity of conveying
the work, and under which the third party grants, to any of the
parties who would receive the covered work from you, a discriminatory
patent license (a) in connection with copies of the covered work
conveyed by you (or copies made from those copies), or (b) primarily
for and in connection with specific products or compilations that
contain the covered work, unless you entered into that arrangement,
or that patent license was granted, prior to 28 March 2007.
Nothing in this License shall be construed as excluding or limiting
any implied license or other defenses to infringement that may
otherwise be available to you under applicable patent law.
12. No Surrender of Others' Freedom.
If conditions are imposed on you (whether by court order, agreement or
otherwise) that contradict the conditions of this License, they do not
excuse you from the conditions of this License. If you cannot convey a
covered work so as to satisfy simultaneously your obligations under this
License and any other pertinent obligations, then as a consequence you may
not convey it at all. For example, if you agree to terms that obligate you
to collect a royalty for further conveying from those to whom you convey
the Program, the only way you could satisfy both those terms and this
License would be to refrain entirely from conveying the Program.
13. Remote Network Interaction; Use with the GNU General Public License.
Notwithstanding any other provision of this License, if you modify the
Program, your modified version must prominently offer all users
interacting with it remotely through a computer network (if your version
supports such interaction) an opportunity to receive the Corresponding
Source of your version by providing access to the Corresponding Source
from a network server at no charge, through some standard or customary
means of facilitating copying of software. This Corresponding Source
shall include the Corresponding Source for any work covered by version 3
of the GNU General Public License that is incorporated pursuant to the
following paragraph.
Notwithstanding any other provision of this License, you have
permission to link or combine any covered work with a work licensed
under version 3 of the GNU General Public License into a single
combined work, and to convey the resulting work. The terms of this
License will continue to apply to the part which is the covered work,
but the work with which it is combined will remain governed by version
3 of the GNU General Public License.
14. Revised Versions of this License.
The Free Software Foundation may publish revised and/or new versions of
the GNU Affero General Public License from time to time. Such new versions
will be similar in spirit to the present version, but may differ in detail to
address new problems or concerns.
Each version is given a distinguishing version number. If the
Program specifies that a certain numbered version of the GNU Affero General
Public License "or any later version" applies to it, you have the
option of following the terms and conditions either of that numbered
version or of any later version published by the Free Software
Foundation. If the Program does not specify a version number of the
GNU Affero General Public License, you may choose any version ever published
by the Free Software Foundation.
If the Program specifies that a proxy can decide which future
versions of the GNU Affero General Public License can be used, that proxy's
public statement of acceptance of a version permanently authorizes you
to choose that version for the Program.
Later license versions may give you additional or different
permissions. However, no additional obligations are imposed on any
author or copyright holder as a result of your choosing to follow a
later version.
15. Disclaimer of Warranty.
THERE IS NO WARRANTY FOR THE PROGRAM, TO THE EXTENT PERMITTED BY
APPLICABLE LAW. EXCEPT WHEN OTHERWISE STATED IN WRITING THE COPYRIGHT
HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" WITHOUT WARRANTY
OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, BUT NOT LIMITED TO,
THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE OF THE PROGRAM
IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME THE COST OF
ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
16. Limitation of Liability.
IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING
WILL ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MODIFIES AND/OR CONVEYS
THE PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE
USE OR INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF
DATA OR DATA BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD
PARTIES OR A FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS),
EVEN IF SUCH HOLDER OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF
SUCH DAMAGES.
17. Interpretation of Sections 15 and 16.
If the disclaimer of warranty and limitation of liability provided
above cannot be given local legal effect according to their terms,
reviewing courts shall apply local law that most closely approximates
an absolute waiver of all civil liability in connection with the
Program, unless a warranty or assumption of liability accompanies a
copy of the Program in return for a fee.
END OF TERMS AND CONDITIONS
How to Apply These Terms to Your New Programs
If you develop a new program, and you want it to be of the greatest
possible use to the public, the best way to achieve this is to make it
free software which everyone can redistribute and change under these terms.
To do so, attach the following notices to the program. It is safest
to attach them to the start of each source file to most effectively
state the exclusion of warranty; and each file should have at least
the "copyright" line and a pointer to where the full notice is found.
<one line to give the program's name and a brief idea of what it does.>
Copyright (C) <year> <name of author>
This program is free software: you can redistribute it and/or modify
it under the terms of the GNU Affero General Public License as published by
the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
This program is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
GNU Affero General Public License for more details.
You should have received a copy of the GNU Affero General Public License
along with this program. If not, see <https://www.gnu.org/licenses/>.
Also add information on how to contact you by electronic and paper mail.
If your software can interact with users remotely through a computer
network, you should also make sure that it provides a way for users to
get its source. For example, if your program is a web application, its
interface could display a "Source" link that leads users to an archive
of the code. There are many ways you could offer source, and different
solutions will be better for different programs; see section 13 for the
specific requirements.
You should also get your employer (if you work as a programmer) or school,
if any, to sign a "copyright disclaimer" for the program, if necessary.
For more information on this, and how to apply and follow the GNU AGPL, see
<https://www.gnu.org/licenses/>.
README.md 0 → 100644
View file @ af155c51
# YOLOE
YOLOE跨越多种开放Prompt机制实现了实时感知任何事物，不受限于预定义类别。
## 论文
`YOLOE: Real-Time Seeing Anything`
- https://arxiv.org/pdf/2503.07465
## 模型结构
YOLOE采用了典型的YOLOs架构，通过RepRTA支持文本Prompt，通过SAVPE支持视觉Prompt，以及通过LRPC支持无Prompt场景，YOLOs中分类头的结构将最后一个卷积层的输出通道数从闭集场景中的类别数更改为嵌入维度，以支持文本和视觉Prompt。
<div align=center>
<img src="./doc/yoloe.png"/>
</div>
## 算法原理
视觉Prompt旨在通过视觉线索Anchor点指示感兴趣的物体类别。
<div align=center>
<img src="./doc/SAVPE.png"/>
</div>
## 环境配置
```
mv yoloe_pytorch yoloe # 去框架名后缀
```
### Docker（方法一）
```
docker pull image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.4.1-ubuntu22.04-dtk25.04-py3.10-fixpy
# <your IMAGE ID>为以上拉取的docker的镜像ID替换，本镜像为：6063b673703a
docker run -it --shm-size=64G -v $PWD/yoloe:/home/yoloe -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video --name ye <your IMAGE ID> bash
cd /home/yoloe
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple
```
### Dockerfile（方法二）
```
cd /home/yoloe/docker
docker build --no-cache -t ye:latest .
docker run --shm-size=64G --name ye -v /opt/hyhal:/opt/hyhal:ro --privileged=true --device=/dev/kfd --device=/dev/dri/ --group-add video -v $PWD/../../yoloe:/home/yoloe -it ye bash
# 若遇到Dockerfile启动的方式安装环境需要长时间等待，可注释掉里面的pip安装，启动容器后再安装python库：pip install -r requirements.txt。
```
### Anaconda（方法三）
1、关于本项目DCU显卡所需的特殊深度学习库可从光合开发者社区下载安装：
- https://developer.sourcefind.cn/tool/
```
DTK驱动:dtk2504
python:python3.10
torch:2.4.1
torchvision:0.19.1
triton:3.0.0
vllm:0.6.2
flash-attn:2.6.1
deepspeed:0.14.2
apex:1.4.0
transformers:4.46.3
```
`Tips：以上dtk驱动、python、torch等DCU相关工具版本需要严格一一对应。`
2、其它非特殊库参照requirements.txt安装
```
cd /home/yoloe
pip install -r requirements.txt -i https://mirrors.aliyun.com/pypi/simple
```
## 数据集
`无`
## 训练
无
## 推理
预训练权重目录结构：
```
/home/yoloe/
|── pretrain/yoloe-v8l-seg.pt
└── mobileclip_blt.pt
```
### 单机单卡
```
cd /home/yoloe
export HF_ENDPOINT=https://hf-mirror.com
sh infer.sh
```
更多资料可参考源项目中的[`README_origin`](./README_origin.md)。
## result
`输入: `
```
--source ultralytics/assets/bus.jpg
--names person dog cat
```
`输出:`
```
ultralytics/assets/bus-output.jpg
```
<div align=center>
<img src="./doc/bus-output.png"/>
</div>
### 精度
DCU与GPU精度一致，推理框架：pytorch。
## 应用场景
### 算法类别
`目标检测`
### 热点应用行业
`制造,电商,医疗,能源,教育`
## 预训练权重
github/HF下载地址为：[yoloe-v8l-seg](https://github.com/ultralytics/assets/releases/download/v8.3.0/yoloe-v8l-seg.pt)、[mobileclip_blt](https://huggingface.co/apple/MobileCLIP-B-LT/blob/main/mobileclip_blt.pt)
github权重可通过镜像地址用wget下载，例如：https://bgithub.xyz。
## 源码仓库及问题反馈
- http://developer.sourcefind.cn/codes/modelzoo/yoloe_pytorch.git
## 参考资料
- https://github.com/THU-MIG/yoloe.git
README_origin.md 0 → 100644
View file @ af155c51
# [YOLOE: Real-Time Seeing Anything](https://arxiv.org/abs/2503.07465)
Official PyTorch implementation of **YOLOE**.
<p align="center">
<img src="figures/comparison.svg" width=70%> <br>
Comparison of performance, training cost, and inference efficiency between YOLOE (Ours) and YOLO-Worldv2 in terms of open text prompts.
</p>
[YOLOE: Real-Time Seeing Anything](https://arxiv.org/abs/2503.07465).\
Ao Wang*, Lihao Liu*, Hui Chen, Zijia Lin, Jungong Han, and Guiguang Ding\
[![arXiv](https://img.shields.io/badge/arXiv-2503.07465-b31b1b.svg)](https://arxiv.org/abs/2503.07465) [![Hugging Face Models](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Models-blue)](https://huggingface.co/jameslahm/yoloe/tree/main) [![Hugging Face Spaces](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Spaces-blue)](https://huggingface.co/spaces/jameslahm/yoloe) [![Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/zero-shot-object-detection-and-segmentation-with-yoloe.ipynb) [![Hugging Face Collection](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Collection-blue)](https://huggingface.co/collections/jameslahm/yoloe-67d5110aabaefbe129c15917) [![Openbayes Demo](https://img.shields.io/static/v1?label=Demo&message=OpenBayes%E8%B4%9D%E5%BC%8F%E8%AE%A1%E7%AE%97&color=green)](https://openbayes.com/console/public/tutorials/BQhUorEqyVX)
We introduce **YOLOE(ye)**, a highly **efficient**, **unified**, and **open** object detection and segmentation model, like human eye, under different prompt mechanisms, like *texts*, *visual inputs*, and *prompt-free paradigm*, with **zero inference and transferring overhead** compared with closed-set YOLOs.
<!-- <p align="center">
<img src="figures/pipeline.svg" width=96%> <br>
</p> -->
<p align="center">
<img src="figures/visualization.svg" width=96%> <br>
</p>
<details>
<summary>
<font size="+1">Abstract</font>
</summary>
Object detection and segmentation are widely employed in computer vision applications, yet conventional models like YOLO series, while efficient and accurate, are limited by predefined categories, hindering adaptability in open scenarios. Recent open-set methods leverage text prompts, visual cues, or prompt-free paradigm to overcome this, but often compromise between performance and efficiency due to high computational demands or deployment complexity. In this work, we introduce YOLOE, which integrates detection and segmentation across diverse open prompt mechanisms within a single highly efficient model, achieving real-time seeing anything. For text prompts, we propose Re-parameterizable Region-Text Alignment (RepRTA) strategy. It refines pretrained textual embeddings via a re-parameterizable lightweight auxiliary network and enhances visual-textual alignment with zero inference and transferring overhead. For visual prompts, we present Semantic-Activated Visual Prompt Encoder (SAVPE). It employs decoupled semantic and activation branches to bring improved visual embedding and accuracy with minimal complexity. For prompt-free scenario, we introduce Lazy Region-Prompt Contrast (LRPC) strategy. It utilizes a built-in large vocabulary and specialized embedding to identify all objects, avoiding costly language model dependency. Extensive experiments show YOLOE's exceptional zero-shot performance and transferability with high inference efficiency and low training cost. Notably, on LVIS, with $3\times$ less training cost and $1.4\times$ inference speedup, YOLOE-v8-S surpasses YOLO-Worldv2-S by 3.5 AP. When transferring to COCO, YOLOE-v8-L achieves 0.6 $AP^b$ and 0.4 $AP^m$ gains over closed-set YOLOv8-L with nearly $4\times$ less training time.
</details>
<p></p>
<p align="center">
<img src="figures/pipeline.svg" width=96%> <br>
</p>
## Performance
### Zero-shot detection evaluation
- *Fixed AP* is reported on LVIS `minival` set with text (T) / visual (V) prompts.
- Training time is for text prompts with detection based on 8 Nvidia RTX4090 GPUs.
- FPS is measured on T4 with TensorRT and iPhone 12 with CoreML, respectively.
- For training data, OG denotes Objects365v1 and GoldG.
- YOLOE can become YOLOs after re-parameterization with **zero inference and transferring overhead**.
| Model | Size | Prompt | Params | Data | Time | FPS | $AP$ | $AP_r$ | $AP_c$ | $AP_f$ | Log |
|---|---|---|---|---|---|---|---|---|---|---|---|
| [YOLOE-v8-S](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8s-seg.pt) | 640 | T / V | 12M / 13M | OG | 12.0h | 305.8 / 64.3 | 27.9 / 26.2 | 22.3 / 21.3 | 27.8 / 27.7 | 29.0 / 25.7 | [T](./logs/yoloe-v8s-seg) / [V](./logs/yoloe-v8s-seg-vp) |
| [YOLOE-v8-M](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8m-seg.pt) | 640 | T / V | 27M / 30M | OG | 17.0h | 156.7 / 41.7 | 32.6 / 31.0 | 26.9 / 27.0 | 31.9 / 31.7 | 34.4 / 31.1 | [T](./logs/yoloe-v8m-seg) / [V](./logs/yoloe-v8m-seg-vp) |
| [YOLOE-v8-L](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8l-seg.pt) | 640 | T / V | 45M / 50M | OG | 22.5h | 102.5 / 27.2 | 35.9 / 34.2 | 33.2 / 33.2 | 34.8 / 34.6 | 37.3 / 34.1 | [T](./logs/yoloe-v8l-seg) / [V](./logs/yoloe-v8l-seg-vp) |
| [YOLOE-11-S](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11s-seg.pt) | 640 | T / V | 10M / 12M | OG | 13.0h | 301.2 / 73.3 | 27.5 / 26.3 | 21.4 / 22.5 | 26.8 / 27.1 | 29.3 / 26.4 | [T](./logs/yoloe-11s-seg) / [V](./logs/yoloe-11s-seg-vp) |
| [YOLOE-11-M](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11m-seg.pt) | 640 | T / V | 21M / 27M | OG | 18.5h | 168.3 / 39.2 | 33.0 / 31.4 | 26.9 / 27.1 | 32.5 / 31.9 | 34.5 / 31.7 | [T](./logs/yoloe-11m-seg) / [V](./logs/yoloe-11m-seg-vp) |
| [YOLOE-11-L](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11l-seg.pt) | 640 | T / V | 26M / 32M | OG | 23.5h | 130.5 / 35.1 | 35.2 / 33.7 | 29.1 / 28.1 | 35.0 / 34.6 | 36.5 / 33.8 | [T](./logs/yoloe-11l-seg) / [V](./logs/yoloe-11l-seg-vp) |
### Zero-shot segmentation evaluation
- The model is the same as above in [Zero-shot detection evaluation](#zero-shot-detection-evaluation).
- *Standard AP<sup>m</sup>* is reported on LVIS `val` set with text (T) / visual (V) prompts.
| Model | Size | Prompt | $AP^m$ | $AP_r^m$ | $AP_c^m$ | $AP_f^m$ |
|---|---|---|---|---|---|---|
| YOLOE-v8-S | 640 | T / V | 17.7 / 16.8 | 15.5 / 13.5 | 16.3 / 16.7 | 20.3 / 18.2 |
| YOLOE-v8-M | 640 | T / V | 20.8 / 20.3 | 17.2 / 17.0 | 19.2 / 20.1 | 24.2 / 22.0 |
| YOLOE-v8-L | 640 | T / V | 23.5 / 22.0 | 21.9 / 16.5 | 21.6 / 22.1 | 26.4 / 24.3 |
| YOLOE-11-S | 640 | T / V | 17.6 / 17.1 | 16.1 / 14.4 | 15.6 / 16.8 | 20.5 / 18.6 |
| YOLOE-11-M | 640 | T / V | 21.1 / 21.0 | 17.2 / 18.3 | 19.6 / 20.6 | 24.4 / 22.6 |
| YOLOE-11-L | 640 | T / V | 22.6 / 22.5 | 19.3 / 20.5 | 20.9 / 21.7 | 26.0 / 24.1 |
### Prompt-free evaluation
- The model is the same as above in [Zero-shot detection evaluation](#zero-shot-detection-evaluation) except the specialized prompt embedding.
- *Fixed AP* is reported on LVIS `minival` set and FPS is measured on Nvidia T4 GPU with Pytorch.
| Model | Size | Params | $AP$ | $AP_r$ | $AP_c$ | $AP_f$ | FPS | Log |
|---|---|---|---|---|---|---|---|---|
| [YOLOE-v8-S](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8s-seg-pf.pt) | 640 | 13M | 21.0 | 19.1 | 21.3 | 21.0 | 95.8 | [PF](./logs/yoloe-v8s-seg-pf/) |
| [YOLOE-v8-M](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8m-seg-pf.pt) | 640 | 29M | 24.7 | 22.2 | 24.5 | 25.3 | 45.9 | [PF](./logs/yoloe-v8m-seg-pf/) |
| [YOLOE-v8-L](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8l-seg-pf.pt) | 640 | 47M | 27.2 | 23.5 | 27.0 | 28.0 | 25.3 | [PF](./logs/yoloe-v8l-seg-pf/) |
| [YOLOE-11-S](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11s-seg-pf.pt) | 640 | 11M | 20.6 | 18.4 | 20.2 | 21.3 | 93.0 | [PF](./logs/yoloe-11s-seg-pf/) |
| [YOLOE-11-M](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11m-seg-pf.pt) | 640 | 24M | 25.5 | 21.6 | 25.5 | 26.1 | 42.5 | [PF](./logs/yoloe-11m-seg-pf/) |
| [YOLOE-11-L](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11l-seg-pf.pt) | 640 | 29M | 26.3 | 22.7 | 25.8 | 27.5 | 34.9 | [PF](./logs/yoloe-11l-seg-pf/) |
### Downstream transfer on COCO
- During transferring, YOLOE-v8 / YOLOE-11 is **exactly the same** as YOLOv8 / YOLO11.
- For *Linear probing*, only the last conv in classification head is trainable.
- For *Full tuning*, all parameters are trainable.
| Model | Size | Epochs | $AP^b$ | $AP^b_{50}$ | $AP^b_{75}$ | $AP^m$ | $AP^m_{50}$ | $AP^m_{75}$ | Log |
|---|---|---|---|---|---|---|---|---|---|
| Linear probing | | | | | | | | | |
| [YOLOE-v8-S](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8s-seg-coco-pe.pt) | 640 | 10 | 35.6 | 51.5 | 38.9 | 30.3 | 48.2 | 32.0 | [LP](./logs/yoloe-v8s-seg-coco-pe/) |
| [YOLOE-v8-M](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8m-seg-coco-pe.pt) | 640 | 10 | 42.2 | 59.2 | 46.3 | 35.5 | 55.6 | 37.7 | [LP](./logs/yoloe-v8m-seg-coco-pe/) |
| [YOLOE-v8-L](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8l-seg-coco-pe.pt) | 640 | 10 | 45.4 | 63.3 | 50.0 | 38.3 | 59.6 | 40.8 | [LP](./logs/yoloe-v8l-seg-coco-pe/) |
| [YOLOE-11-S](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11s-seg-coco-pe.pt) | 640 | 10 | 37.0 | 52.9 | 40.4 | 31.5 | 49.7 | 33.5 | [LP](./logs/yoloe-11s-seg-coco-pe/) |
| [YOLOE-11-M](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11m-seg-coco-pe.pt) | 640 | 10 | 43.1 | 60.6 | 47.4 | 36.5 | 56.9 | 39.0 | [LP](./logs/yoloe-11m-seg-coco-pe/) |
| [YOLOE-11-L](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11l-seg-coco-pe.pt) | 640 | 10 | 45.1 | 62.8 | 49.5 | 38.0 | 59.2 | 40.6 | [LP](./logs/yoloe-11l-seg-coco-pe/) |
| Full tuning | | | | | | | | | |
| [YOLOE-v8-S](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8s-seg-coco.pt) | 640 | 160 | 45.0 | 61.6 | 49.1 | 36.7 | 58.3 | 39.1 | [FT](./logs/yoloe-v8s-seg-coco/) |
| [YOLOE-v8-M](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8m-seg-coco.pt) | 640 | 80 | 50.4 | 67.0 | 55.2 | 40.9 | 63.7 | 43.5 | [FT](./logs/yoloe-v8m-seg-coco/) |
| [YOLOE-v8-L](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-v8l-seg-coco.pt) | 640 | 80 | 53.0 | 69.8 | 57.9 | 42.7 | 66.5 | 45.6 | [FT](./logs/yoloe-v8l-seg-coco/) |
| [YOLOE-11-S](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11s-seg-coco.pt) | 640 | 160 | 46.2 | 62.9 | 50.0 | 37.6 | 59.3 | 40.1 | [FT](./logs/yoloe-11s-seg-coco/) |
| [YOLOE-11-M](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11m-seg-coco.pt) | 640 | 80 | 51.3 | 68.3 | 56.0 | 41.5 | 64.8 | 44.3 | [FT](./logs/yoloe-11m-seg-coco/) |
| [YOLOE-11-L](https://huggingface.co/jameslahm/yoloe/blob/main/yoloe-11l-seg-coco.pt) | 640 | 80 | 52.6 | 69.7 | 57.5 | 42.4 | 66.2 | 45.2 | [FT](./logs/yoloe-11l-seg-coco/) |
## Installation
You could also quickly try YOLOE for [prediction](https://colab.research.google.com/drive/1LRFEVarAIVSnIeL_pCPtsFL87FsEe46U?usp=sharing) and [transferring](https://colab.research.google.com/drive/1y-r4y_owfFAfyqbqP2t64H7IqjURkKwe?usp=sharing) using colab notebooks.
`conda` virtual environment is recommended.
```bash
conda create -n yoloe python=3.10 -y
conda activate yoloe
# If you clone this repo, please use this
pip install -r requirements.txt
# Or you can also directly install the repo by this
pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/CLIP
pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/ml-mobileclip
pip install git+https://github.com/THU-MIG/yoloe.git#subdirectory=third_party/lvis-api
pip install git+https://github.com/THU-MIG/yoloe.git
wget https://docs-assets.developer.apple.com/ml-research/datasets/mobileclip/mobileclip_blt.pt
```
## Demo
If desired objects are not identified, pleaset set a **smaller** confidence threshold, e.g., for visual prompts with handcrafted shape or cross-image prompts.
```bash
# Optional for mirror: export HF_ENDPOINT=https://hf-mirror.com
pip install gradio==4.42.0 gradio_image_prompter==0.1.0 fastapi==0.112.2 huggingface-hub==0.26.3 gradio_client==1.3.0 pydantic==2.10.6
python app.py
# Please visit http://127.0.0.1:7860
```
## Prediction
```bash
# Download pretrained models
# Optional for mirror: export HF_ENDPOINT=https://hf-mirror.com
# Please replace the pt file with your desired model
pip install huggingface-hub==0.26.3
huggingface-cli download jameslahm/yoloe yoloe-v8l-seg.pt --local-dir pretrain
```
For yoloe-(v8s/m/l)/(11s/m/l)-seg, Models can also be automatically downloaded using `from_pretrained`.
```python
from ultralytics import YOLOE
model = YOLOE.from_pretrained("jameslahm/yoloe-v8l-seg")
```
### Text prompt
```bash
python predict_text_prompt.py \
--source ultralytics/assets/bus.jpg \
--checkpoint pretrain/yoloe-v8l-seg.pt \
--names person dog cat \
--device cuda:0
```
### Visual prompt
```bash
python predict_visual_prompt.py
```
### Prompt free
```bash
python predict_prompt_free.py
```
## Transferring
After pretraining, YOLOE-v8 / YOLOE-11 can be re-parameterized into the same architecture as YOLOv8 / YOLO11, with **zero overhead for transferring**.
### Linear probing
Only the last conv, ie., the prompt embedding, is trainable.
```bash
python train_pe.py
```
### Full tuning
All parameters are trainable, for better performance.
```bash
# For models with s scale, please change the epochs to 160 for longer training
python train_pe_all.py
```
## Validation
### Data
- Please download LVIS following [here](https://docs.ultralytics.com/zh/datasets/detect/lvis/) or [lvis.yaml](./ultralytics/cfg/datasets/lvis.yaml).
- We use this [`minival.txt`](./tools/lvis/minival.txt) with background images for evaluation.
```bash
# For evaluation with visual prompt, please obtain the referring data.
python tools/generate_lvis_visual_prompt_data.py
```
### Zero-shot evaluation on LVIS
- For text prompts, `python val.py`.
- For visual prompts, `python val_vp.py`
For *Fixed AP*, please refer to the comments in `val.py` and `val_vp.py`, and use `tools/eval_fixed_ap.py` for evaluation.
### Prompt-free evaluation
```bash
python val_pe_free.py
python tools/eval_open_ended.py --json ../datasets/lvis/annotations/lvis_v1_minival.json --pred runs/detect/val/predictions.json --fixed
```
### Downstream transfer on COCO
```bash
python val_coco.py
```
## Training
The training includes three stages:
- YOLOE is trained with text prompts for detection and segmentation for 30 epochs.
- Only visual prompt encoder (SAVPE) is trained with visual prompts for 2 epochs.
- Only specialized prompt embedding for prompt free is trained for 1 epochs.
### Data
| Images | Raw Annotations | Processed Annotations |
|---|---|---|
| [Objects365v1](https://opendatalab.com/OpenDataLab/Objects365_v1) | [objects365_train.json](https://opendatalab.com/OpenDataLab/Objects365_v1) | [objects365_train_segm.json](https://huggingface.co/datasets/jameslahm/yoloe/blob/main/objects365_train_segm.json) |
| [GQA](https://nlp.stanford.edu/data/gqa/images.zip) | [ final_mixed_train_noo_coco.json](https://huggingface.co/GLIPModel/GLIP/blob/main/mdetr_annotations/final_mixed_train_no_coco.json) | [ final_mixed_train_noo_coco_segm.json](https://huggingface.co/datasets/jameslahm/yoloe/blob/main/final_mixed_train_no_coco_segm.json) |
| [Flickr30k](https://shannon.cs.illinois.edu/DenotationGraph/) | [final_flickr_separateGT_train.json](https://huggingface.co/GLIPModel/GLIP/blob/main/mdetr_annotations/final_flickr_separateGT_train.json) | [final_flickr_separateGT_train_segm.json](https://huggingface.co/datasets/jameslahm/yoloe/blob/main/final_flickr_separateGT_train_segm.json) |
For annotations, you can directly use our preprocessed ones or use the following script to obtain the processed annotations with segmentation masks.
```bash
# Generate segmentation data
conda create -n sam2 python==3.10.16
conda activate sam2
pip install -r third_party/sam2/requirements.txt
pip install -e third_party/sam2/
python tools/generate_sam_masks.py --img-path ../datasets/Objects365v1/images/train --json-path ../datasets/Objects365v1/annotations/objects365_train.json --batch
python tools/generate_sam_masks.py --img-path ../datasets/flickr/full_images/ --json-path ../datasets/flickr/annotations/final_flickr_separateGT_train.json
python tools/generate_sam_masks.py --img-path ../datasets/mixed_grounding/gqa/images --json-path ../datasets/mixed_grounding/annotations/final_mixed_train_no_coco.json
# Generate objects365v1 labels
python tools/generate_objects365v1.py
```
Then, please generate the data and embedding cache for training.
```bash
# Generate grounding segmentation cache
python tools/generate_grounding_cache.py --img-path ../datasets/flickr/full_images/ --json-path ../datasets/flickr/annotations/final_flickr_separateGT_train_segm.json
python tools/generate_grounding_cache.py --img-path ../datasets/mixed_grounding/gqa/images --json-path ../datasets/mixed_grounding/annotations/final_mixed_train_no_coco_segm.json
# Generate train label embeddings
python tools/generate_label_embedding.py
python tools/generate_global_neg_cat.py
```
At last, please download MobileCLIP-B(LT) for text encoder.
```bash
wget https://docs-assets.developer.apple.com/ml-research/datasets/mobileclip/mobileclip_blt.pt
```
### Text prompt
```bash
# For models with l scale, please change the initialization by referring to the comments in Line 549 in ultralytics/nn/moduels/head.py
# If you want to train YOLOE only for detection, you can use `train.py`
python train_seg.py
```
### Visual prompt
```bash
# For visual prompt, because only SAVPE is trained, we can adopt the detection pipeline with less training time
# First, obtain the detection model
python tools/convert_segm2det.py
# Then, train the SAVPE module
python train_vp.py
# After training, please use tools/get_vp_segm.py to add the segmentation head
# python tools/get_vp_segm.py
```
### Prompt free
```bash
# Generate LVIS with single class for evaluation during training
python tools/generate_lvis_sc.py
# Similar to visual prompt, because only the specialized prompt embedding is trained, we can adopt the detection pipeline with less training time
python tools/convert_segm2det.py
python train_pe_free.py
# After training, please use tools/get_pf_free_segm.py to add the segmentation head
# python tools/get_pf_free_segm.py
```
## Export
After re-parameterization, YOLOE-v8 / YOLOE-11 can be exported into the identical format as YOLOv8 / YOLO11, with **zero overhead for inference**.
```bash
pip install onnx coremltools onnxslim
python export.py
```
## Benchmark
- For TensorRT, please refer to `benchmark.sh`.
- For CoreML, please use the benchmark tool from [XCode 14](https://developer.apple.com/videos/play/wwdc2022/10027/).
- For prompt-free setting, please refer to `tools/benchmark_pf.py`.
## Acknowledgement
The code base is built with [ultralytics](https://github.com/ultralytics/ultralytics), [YOLO-World](https://github.com/AILab-CVC/YOLO-World), [MobileCLIP](https://github.com/apple/ml-mobileclip), [lvis-api](https://github.com/lvis-dataset/lvis-api), [CLIP](https://github.com/openai/CLIP), and [GenerateU](https://github.com/FoundationVision/GenerateU).
Thanks for the great implementations!
## Citation
If our code or models help your work, please cite our paper:
```BibTeX
@misc{wang2025yoloerealtimeseeing,
title={YOLOE: Real-Time Seeing Anything},
author={Ao Wang and Lihao Liu and Hui Chen and Zijia Lin and Jungong Han and Guiguang Ding},
year={2025},
eprint={2503.07465},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2503.07465},
}
```
app.py 0 → 100644
View file @ af155c51
import torch
import numpy as np
import gradio as gr
import supervision as sv
from scipy.ndimage import binary_fill_holes
from ultralytics import YOLOE
from ultralytics.utils.torch_utils import smart_inference_mode
from ultralytics.models.yolo.yoloe.predict_vp import YOLOEVPSegPredictor
from gradio_image_prompter import ImagePrompter
from huggingface_hub import hf_hub_download
def init_model(model_id, is_pf=False):
filename = f"{model_id}-seg.pt" if not is_pf else f"{model_id}-seg-pf.pt"
path = hf_hub_download(repo_id="jameslahm/yoloe", filename=filename)
model = YOLOE(path)
model.eval()
model.to("cuda" if torch.cuda.is_available() else "cpu")
return model
@smart_inference_mode()
def yoloe_inference(image, prompts, target_image, model_id, image_size, conf_thresh, iou_thresh, prompt_type):
model = init_model(model_id)
kwargs = {}
if prompt_type == "Text":
texts = prompts["texts"]
model.set_classes(texts, model.get_text_pe(texts))
elif prompt_type == "Visual":
kwargs = dict(
prompts=prompts,
predictor=YOLOEVPSegPredictor
)
if target_image:
model.predict(source=image, imgsz=image_size, conf=conf_thresh, iou=iou_thresh, return_vpe=True, **kwargs)
model.set_classes(["object0"], model.predictor.vpe)
model.predictor = None # unset VPPredictor
image = target_image
kwargs = {}
elif prompt_type == "Prompt-free":
vocab = model.get_vocab(prompts["texts"])
model = init_model(model_id, is_pf=True)
model.set_vocab(vocab, names=prompts["texts"])
model.model.model[-1].is_fused = True
model.model.model[-1].conf = 0.001
model.model.model[-1].max_det = 1000
results = model.predict(source=image, imgsz=image_size, conf=conf_thresh, iou=iou_thresh, **kwargs)
detections = sv.Detections.from_ultralytics(results[0])
resolution_wh = image.size
thickness = sv.calculate_optimal_line_thickness(resolution_wh=resolution_wh)
text_scale = sv.calculate_optimal_text_scale(resolution_wh=resolution_wh)
labels = [
f"{class_name} {confidence:.2f}"
for class_name, confidence
in zip(detections['class_name'], detections.confidence)
]
annotated_image = image.copy()
annotated_image = sv.MaskAnnotator(
color_lookup=sv.ColorLookup.INDEX,
opacity=0.4
).annotate(scene=annotated_image, detections=detections)
annotated_image = sv.BoxAnnotator(
color_lookup=sv.ColorLookup.INDEX,
thickness=thickness
).annotate(scene=annotated_image, detections=detections)
annotated_image = sv.LabelAnnotator(
color_lookup=sv.ColorLookup.INDEX,
text_scale=text_scale,
smart_position=True
).annotate(scene=annotated_image, detections=detections, labels=labels)
return annotated_image
def app():
with gr.Blocks():
with gr.Row():
with gr.Column():
with gr.Row():
raw_image = gr.Image(type="pil", label="Image", visible=True, interactive=True)
box_image = ImagePrompter(type="pil", label="DrawBox", visible=False, interactive=True)
mask_image = gr.ImageEditor(type="pil", label="DrawMask", visible=False, interactive=True, layers=False, canvas_size=(640, 640))
target_image = gr.Image(type="pil", label="Target Image", visible=False, interactive=True)
yoloe_infer = gr.Button(value="Detect & Segment Objects")
prompt_type = gr.Textbox(value="Text", visible=False)
with gr.Tab("Text") as text_tab:
texts = gr.Textbox(label="Input Texts", value='person,bus', placeholder='person,bus', visible=True, interactive=True)
with gr.Tab("Visual") as visual_tab:
with gr.Row():
visual_prompt_type = gr.Dropdown(choices=["bboxes", "masks"], value="bboxes", label="Visual Type", interactive=True)
visual_usage_type = gr.Radio(choices=["Intra-Image", "Cross-Image"], value="Intra-Image", label="Intra/Cross Image", interactive=True)
with gr.Tab("Prompt-Free") as prompt_free_tab:
gr.HTML(
"""
<p style='text-align: center'>
<b>Prompt-Free Mode is On</b>
</p>
""", show_label=False)
model_id = gr.Dropdown(
label="Model",
choices=[
"yoloe-v8s",
"yoloe-v8m",
"yoloe-v8l",
"yoloe-11s",
"yoloe-11m",
"yoloe-11l",
],
value="yoloe-v8l",
)
image_size = gr.Slider(
label="Image Size",
minimum=320,
maximum=1280,
step=32,
value=640,
)
conf_thresh = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.25,
)
iou_thresh = gr.Slider(
label="IoU Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.70,
)
with gr.Column():
output_image = gr.Image(type="numpy", label="Annotated Image", visible=True)
def update_text_image_visibility():
return gr.update(value="Text"), gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
def update_visual_image_visiblity(visual_prompt_type, visual_usage_type):
if visual_prompt_type == "bboxes":
return gr.update(value="Visual"), gr.update(visible=False), gr.update(visible=True), gr.update(visible=False), gr.update(visible=(visual_usage_type == "Cross-Image"))
elif visual_prompt_type == "masks":
return gr.update(value="Visual"), gr.update(visible=False), gr.update(visible=False), gr.update(visible=True), gr.update(visible=(visual_usage_type == "Cross-Image"))
def update_pf_image_visibility():
return gr.update(value="Prompt-free"), gr.update(visible=True), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
text_tab.select(
fn=update_text_image_visibility,
inputs=None,
outputs=[prompt_type, raw_image, box_image, mask_image, target_image]
)
visual_tab.select(
fn=update_visual_image_visiblity,
inputs=[visual_prompt_type, visual_usage_type],
outputs=[prompt_type, raw_image, box_image, mask_image, target_image]
)
prompt_free_tab.select(
fn=update_pf_image_visibility,
inputs=None,
outputs=[prompt_type, raw_image, box_image, mask_image, target_image]
)
def update_visual_prompt_type(visual_prompt_type):
if visual_prompt_type == "bboxes":
return gr.update(visible=True), gr.update(visible=False)
if visual_prompt_type == "masks":
return gr.update(visible=False), gr.update(visible=True)
return gr.update(visible=False), gr.update(visible=False)
def update_visual_usage_type(visual_usage_type):
if visual_usage_type == "Intra-Image":
return gr.update(visible=False)
if visual_usage_type == "Cross-Image":
return gr.update(visible=True)
return gr.update(visible=False)
visual_prompt_type.change(
fn=update_visual_prompt_type,
inputs=[visual_prompt_type],
outputs=[box_image, mask_image]
)
visual_usage_type.change(
fn=update_visual_usage_type,
inputs=[visual_usage_type],
outputs=[target_image]
)
def run_inference(raw_image, box_image, mask_image, target_image, texts, model_id, image_size, conf_thresh, iou_thresh, prompt_type, visual_prompt_type, visual_usage_type):
# add text/built-in prompts
if prompt_type == "Text" or prompt_type == "Prompt-free":
target_image = None
image = raw_image
if prompt_type == "Prompt-free":
with open('tools/ram_tag_list.txt', 'r') as f:
texts = [x.strip() for x in f.readlines()]
else:
texts = [text.strip() for text in texts.split(',')]
prompts = {
"texts": texts
}
# add visual prompt
elif prompt_type == "Visual":
if visual_usage_type != "Cross-Image":
target_image = None
if visual_prompt_type == "bboxes":
image, points = box_image["image"], box_image["points"]
points = np.array(points)
if len(points) == 0:
gr.Warning("No boxes are provided. No image output.", visible=True)
return gr.update(value=None)
bboxes = np.array([p[[0, 1, 3, 4]] for p in points if p[2] == 2])
prompts = {
"bboxes": bboxes,
"cls": np.array([0] * len(bboxes))
}
elif visual_prompt_type == "masks":
image, masks = mask_image["background"], mask_image["layers"][0]
# image = image.convert("RGB")
masks = np.array(masks.convert("L"))
masks = binary_fill_holes(masks).astype(np.uint8)
masks[masks > 0] = 1
if masks.sum() == 0:
gr.Warning("No masks are provided. No image output.", visible=True)
return gr.update(value=None)
prompts = {
"masks": masks[None],
"cls": np.array([0])
}
return yoloe_inference(image, prompts, target_image, model_id, image_size, conf_thresh, iou_thresh, prompt_type)
yoloe_infer.click(
fn=run_inference,
inputs=[raw_image, box_image, mask_image, target_image, texts, model_id, image_size, conf_thresh, iou_thresh, prompt_type, visual_prompt_type, visual_usage_type],
outputs=[output_image],
)
###################### Examples ##########################
text_examples = gr.Examples(
examples=[[
"ultralytics/assets/bus.jpg",
"person,bus",
"yoloe-v8l",
640,
0.25,
0.7]],
inputs=[raw_image, texts, model_id, image_size, conf_thresh, iou_thresh],
visible=True, cache_examples=False, label="Text Prompt Examples")
box_examples = gr.Examples(
examples=[[
{"image": "ultralytics/assets/bus_box.jpg", "points": [[235, 408, 2, 342, 863, 3]]},
"ultralytics/assets/zidane.jpg",
"yoloe-v8l",
640,
0.2,
0.7,
]],
inputs=[box_image, target_image, model_id, image_size, conf_thresh, iou_thresh],
visible=False, cache_examples=False, label="Box Visual Prompt Examples")
mask_examples = gr.Examples(
examples=[[
{"background": "ultralytics/assets/bus.jpg", "layers": ["ultralytics/assets/bus_mask.png"], "composite": "ultralytics/assets/bus_composite.jpg"},
"ultralytics/assets/zidane.jpg",
"yoloe-v8l",
640,
0.15,
0.7,
]],
inputs=[mask_image, target_image, model_id, image_size, conf_thresh, iou_thresh],
visible=False, cache_examples=False, label="Mask Visual Prompt Examples")
pf_examples = gr.Examples(
examples=[[
"ultralytics/assets/bus.jpg",
"yoloe-v8l",
640,
0.25,
0.7,
]],
inputs=[raw_image, model_id, image_size, conf_thresh, iou_thresh],
visible=False, cache_examples=False, label="Prompt-free Examples")
# Components update
def load_box_example(visual_usage_type):
return (gr.update(visible=True, value={"image": "ultralytics/assets/bus_box.jpg", "points": [[235, 408, 2, 342, 863, 3]]}),
gr.update(visible=(visual_usage_type=="Cross-Image")))
def load_mask_example(visual_usage_type):
return gr.update(visible=True), gr.update(visible=(visual_usage_type=="Cross-Image"))
box_examples.load_input_event.then(
fn=load_box_example,
inputs=visual_usage_type,
outputs=[box_image, target_image]
)
mask_examples.load_input_event.then(
fn=load_mask_example,
inputs=visual_usage_type,
outputs=[mask_image, target_image]
)
# Examples update
def update_text_examples():
return gr.Dataset(visible=True), gr.Dataset(visible=False), gr.Dataset(visible=False), gr.Dataset(visible=False)
def update_pf_examples():
return gr.Dataset(visible=False), gr.Dataset(visible=False), gr.Dataset(visible=False), gr.Dataset(visible=True)
def update_visual_examples(visual_prompt_type):
if visual_prompt_type == "bboxes":
return gr.Dataset(visible=False), gr.Dataset(visible=True), gr.Dataset(visible=False), gr.Dataset(visible=False),
elif visual_prompt_type == "masks":
return gr.Dataset(visible=False), gr.Dataset(visible=False), gr.Dataset(visible=True), gr.Dataset(visible=False),
text_tab.select(
fn=update_text_examples,
inputs=None,
outputs=[text_examples.dataset, box_examples.dataset, mask_examples.dataset, pf_examples.dataset]
)
visual_tab.select(
fn=update_visual_examples,
inputs=[visual_prompt_type],
outputs=[text_examples.dataset, box_examples.dataset, mask_examples.dataset, pf_examples.dataset]
)
prompt_free_tab.select(
fn=update_pf_examples,
inputs=None,
outputs=[text_examples.dataset, box_examples.dataset, mask_examples.dataset, pf_examples.dataset]
)
visual_prompt_type.change(
fn=update_visual_examples,
inputs=[visual_prompt_type],
outputs=[text_examples.dataset, box_examples.dataset, mask_examples.dataset, pf_examples.dataset]
)
visual_usage_type.change(
fn=update_visual_examples,
inputs=[visual_prompt_type],
outputs=[text_examples.dataset, box_examples.dataset, mask_examples.dataset, pf_examples.dataset]
)
gradio_app = gr.Blocks()
with gradio_app:
gr.HTML(
"""
<h1 style='text-align: center'>
<img src="/file=figures/logo.png" width="2.5%" style="display:inline;padding-bottom:4px">
YOLOE: Real-Time Seeing Anything
</h1>
""")
gr.HTML(
"""
<h3 style='text-align: center'>
<a href='https://arxiv.org/abs/2503.07465' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yoloe' target='_blank'>github</a>
</h3>
""")
gr.Markdown(
"""
We introduce **YOLOE(ye)**, a highly **efficient**, **unified**, and **open** object detection and segmentation model, like human eye, under different prompt mechanisms, like *texts*, *visual inputs*, and *prompt-free paradigm*.
"""
)
gr.Markdown(
"""
If desired objects are not identified, pleaset set a **smaller** confidence threshold, e.g., for visual prompts with handcrafted shape or cross-image prompts.
"""
)
gr.Markdown(
"""
Drawing **multiple** boxes or handcrafted shapes as visual prompt in an image is also supported, which leads to more accurate prompt.
"""
)
with gr.Row():
with gr.Column():
app()
if __name__ == '__main__':
gradio_app.launch(allowed_paths=["figures"])
benchmark.sh 0 → 100644
View file @ af155c51
set -e
set -x
MODEL=$1
trtexec --onnx="${MODEL}.onnx" \
--fp16 \
--saveEngine="${MODEL}.engine" \
--timingCacheFile="${MODEL}.engine.timing.cache" \
--warmUp=500 \
--duration=10 \
--useCudaGraph \
--useSpinWait \
--noDataTransfers > /dev/null
trtexec \
--fp16 \
--loadEngine="${MODEL}.engine" \
--timingCacheFile="${MODEL}.engine.timing.cache" \
--warmUp=500 \
--duration=10 \
--useCudaGraph \
--useSpinWait \
--noDataTransfers
\ No newline at end of file
docker/Dockerfile 0 → 100644
View file @ af155c51
FROM image.sourcefind.cn:5000/dcu/admin/base/pytorch:2.4.1-ubuntu22.04-dtk25.04-py3.10-fixpy
ENV DEBIAN_FRONTEND=noninteractive
# RUN yum update && yum install -y git cmake wget build-essential
# RUN source /opt/dtk-dtk25.04/env.sh
# # 安装pip相关依赖
COPY requirements.txt requirements.txt
RUN pip3 install -r requirements.txt -i http://mirrors.aliyun.com/pypi/simple/ --trusted-host mirrors.aliyun.com
docker/requirements.txt 0 → 100644
View file @ af155c51
-e .
-e third_party/lvis-api
-e third_party/ml-mobileclip
-e third_party/CLIP
\ No newline at end of file
docker_origin/Dockerfile 0 → 100644
View file @ af155c51
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Builds ultralytics/ultralytics:latest image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Image is CUDA-optimized for YOLO11 single/multi-GPU training and inference
# Start FROM PyTorch image https://hub.docker.com/r/pytorch/pytorch or nvcr.io/nvidia/pytorch:23.03-py3
FROM pytorch/pytorch:2.5.0-cuda12.4-cudnn9-runtime
# Set environment variables
# Avoid DDP error "MKL_THREADING_LAYER=INTEL is incompatible with libgomp.so.1 library" https://github.com/pytorch/pytorch/issues/37377
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_BREAK_SYSTEM_PACKAGES=1 \
MKL_THREADING_LAYER=GNU \
OMP_NUM_THREADS=1
# Downloads to user config dir
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \
https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \
/root/.config/Ultralytics/
# Install linux packages
# g++ required to build 'tflite_support' and 'lap' packages, libusb-1.0-0 required for 'tflite_support' package
# libsm6 required by libqxcb to create QT-based windows for visualization; set 'QT_DEBUG_PLUGINS=1' to test in docker
RUN apt-get update && \
apt-get install -y --no-install-recommends \
gcc git zip unzip wget curl htop libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 libsm6 \
&& rm -rf /var/lib/apt/lists/*
# Security updates
# https://security.snyk.io/vuln/SNYK-UBUNTU1804-OPENSSL-3314796
RUN apt upgrade --no-install-recommends -y openssl tar
# Create working directory
WORKDIR /ultralytics
# Copy contents and configure git
COPY . .
RUN sed -i '/^\[http "https:\/\/github\.com\/"\]/,+1d' .git/config
ADD https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt .
# Install pip packages
RUN python3 -m pip install --upgrade pip wheel
# Note -cu12 must be used with tensorrt)
RUN pip install -e ".[export]" tensorrt-cu12 "albumentations>=1.4.6" comet pycocotools
# Run exports to AutoInstall packages
# Edge TPU export fails the first time so is run twice here
RUN yolo export model=tmp/yolo11n.pt format=edgetpu imgsz=32 || yolo export model=tmp/yolo11n.pt format=edgetpu imgsz=32
RUN yolo export model=tmp/yolo11n.pt format=ncnn imgsz=32
# Requires <= Python 3.10, bug with paddlepaddle==2.5.0 https://github.com/PaddlePaddle/X2Paddle/issues/991
RUN pip install "paddlepaddle>=2.6.0" x2paddle
# Fix error: `np.bool` was a deprecated alias for the builtin `bool` segmentation error in Tests
RUN pip install numpy==1.23.5
# Remove extra build files
RUN rm -rf tmp /root/.config/Ultralytics/persistent_cache.json
# Usage Examples -------------------------------------------------------------------------------------------------------
# Build and Push
# t=ultralytics/ultralytics:latest && sudo docker build -f docker/Dockerfile -t $t . && sudo docker push $t
# Pull and Run with access to all GPUs
# t=ultralytics/ultralytics:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all $t
# Pull and Run with access to GPUs 2 and 3 (inside container CUDA devices will appear as 0 and 1)
# t=ultralytics/ultralytics:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus '"device=2,3"' $t
# Pull and Run with local directory access
# t=ultralytics/ultralytics:latest && sudo docker pull $t && sudo docker run -it --ipc=host --gpus all -v "$(pwd)"/shared/datasets:/datasets $t
# Kill all
# sudo docker kill $(sudo docker ps -q)
# Kill all image-based
# sudo docker kill $(sudo docker ps -qa --filter ancestor=ultralytics/ultralytics:latest)
# DockerHub tag update
# t=ultralytics/ultralytics:latest tnew=ultralytics/ultralytics:v6.2 && sudo docker pull $t && sudo docker tag $t $tnew && sudo docker push $tnew
# Clean up
# sudo docker system prune -a --volumes
# Update Ubuntu drivers
# https://www.maketecheasier.com/install-nvidia-drivers-ubuntu/
# DDP test
# python -m torch.distributed.run --nproc_per_node 2 --master_port 1 train.py --epochs 3
# GCP VM from Image
# docker.io/ultralytics/ultralytics:latest
docker_origin/Dockerfile-arm64 0 → 100644
View file @ af155c51
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Builds ultralytics/ultralytics:latest-arm64 image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Image is aarch64-compatible for Apple M1, M2, M3, Raspberry Pi and other ARM architectures
# Start FROM Ubuntu image https://hub.docker.com/_/ubuntu with "FROM arm64v8/ubuntu:22.04" (deprecated)
# Start FROM Debian image for arm64v8 https://hub.docker.com/r/arm64v8/debian (new)
FROM arm64v8/debian:bookworm-slim
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_BREAK_SYSTEM_PACKAGES=1
# Downloads to user config dir
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \
https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \
/root/.config/Ultralytics/
# Install linux packages
# g++ required to build 'tflite_support' and 'lap' packages, libusb-1.0-0 required for 'tflite_support' package
# pkg-config and libhdf5-dev (not included) are needed to build 'h5py==3.11.0' aarch64 wheel required by 'tensorflow'
RUN apt-get update && \
apt-get install -y --no-install-recommends \
python3-pip git zip unzip wget curl htop gcc libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 \
&& rm -rf /var/lib/apt/lists/*
# Create working directory
WORKDIR /ultralytics
# Copy contents and configure git
COPY . .
RUN sed -i '/^\[http "https:\/\/github\.com\/"\]/,+1d' .git/config
ADD https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt .
# Install pip packages
RUN python3 -m pip install --upgrade pip wheel
RUN pip install -e ".[export]"
# Creates a symbolic link to make 'python' point to 'python3'
RUN ln -sf /usr/bin/python3 /usr/bin/python
# Remove extra build files
RUN rm -rf /root/.config/Ultralytics/persistent_cache.json
# Usage Examples -------------------------------------------------------------------------------------------------------
# Build and Push
# t=ultralytics/ultralytics:latest-arm64 && sudo docker build --platform linux/arm64 -f docker/Dockerfile-arm64 -t $t . && sudo docker push $t
# Run
# t=ultralytics/ultralytics:latest-arm64 && sudo docker run -it --ipc=host $t
# Pull and Run
# t=ultralytics/ultralytics:latest-arm64 && sudo docker pull $t && sudo docker run -it --ipc=host $t
# Pull and Run with local volume mounted
# t=ultralytics/ultralytics:latest-arm64 && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/shared/datasets:/datasets $t
docker_origin/Dockerfile-conda 0 → 100644
View file @ af155c51
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Builds ultralytics/ultralytics:latest-conda image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Image is optimized for Ultralytics Anaconda (https://anaconda.org/conda-forge/ultralytics) installation and usage
# Start FROM miniconda3 image https://hub.docker.com/r/continuumio/miniconda3
FROM continuumio/miniconda3:latest
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_BREAK_SYSTEM_PACKAGES=1
# Downloads to user config dir
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \
https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \
/root/.config/Ultralytics/
# Install linux packages
RUN apt-get update && \
apt-get install -y --no-install-recommends \
libgl1 \
&& rm -rf /var/lib/apt/lists/*
# Copy contents
ADD https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt .
# Install conda packages
# mkl required to fix 'OSError: libmkl_intel_lp64.so.2: cannot open shared object file: No such file or directory'
RUN conda config --set solver libmamba && \
conda install pytorch torchvision pytorch-cuda=12.1 -c pytorch -c nvidia && \
conda install -c conda-forge ultralytics mkl
# conda install -c pytorch -c nvidia -c conda-forge pytorch torchvision pytorch-cuda=12.1 ultralytics mkl
# Remove extra build files
RUN rm -rf /root/.config/Ultralytics/persistent_cache.json
# Usage Examples -------------------------------------------------------------------------------------------------------
# Build and Push
# t=ultralytics/ultralytics:latest-conda && sudo docker build -f docker/Dockerfile-cpu -t $t . && sudo docker push $t
# Run
# t=ultralytics/ultralytics:latest-conda && sudo docker run -it --ipc=host $t
# Pull and Run
# t=ultralytics/ultralytics:latest-conda && sudo docker pull $t && sudo docker run -it --ipc=host $t
# Pull and Run with local volume mounted
# t=ultralytics/ultralytics:latest-conda && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/shared/datasets:/datasets $t
docker_origin/Dockerfile-cpu 0 → 100644
View file @ af155c51
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Builds ultralytics/ultralytics:latest-cpu image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Image is CPU-optimized for ONNX, OpenVINO and PyTorch YOLO11 deployments
# Use official Python base image for reproducibility (3.11.10 for export and 3.12.6 for inference)
FROM python:3.11.10-slim-bookworm
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_BREAK_SYSTEM_PACKAGES=1
# Downloads to user config dir
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \
https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \
/root/.config/Ultralytics/
# Install linux packages
# g++ required to build 'tflite_support' and 'lap' packages, libusb-1.0-0 required for 'tflite_support' package
RUN apt-get update && \
apt-get install -y --no-install-recommends \
python3-pip git zip unzip wget curl htop libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 \
&& rm -rf /var/lib/apt/lists/*
# Create working directory
WORKDIR /ultralytics
# Copy contents and configure git
COPY . .
RUN sed -i '/^\[http "https:\/\/github\.com\/"\]/,+1d' .git/config
ADD https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt .
# Install pip packages
RUN python3 -m pip install --upgrade pip wheel
RUN pip install -e ".[export]" --extra-index-url https://download.pytorch.org/whl/cpu
# Run exports to AutoInstall packages
RUN yolo export model=tmp/yolo11n.pt format=edgetpu imgsz=32
RUN yolo export model=tmp/yolo11n.pt format=ncnn imgsz=32
# Requires Python<=3.10, bug with paddlepaddle==2.5.0 https://github.com/PaddlePaddle/X2Paddle/issues/991
RUN pip install "paddlepaddle>=2.6.0" x2paddle
# Remove extra build files
RUN rm -rf tmp /root/.config/Ultralytics/persistent_cache.json
# Set default command to bash
CMD ["/bin/bash"]
# Usage Examples -------------------------------------------------------------------------------------------------------
# Build and Push
# t=ultralytics/ultralytics:latest-cpu && sudo docker build -f docker/Dockerfile-cpu -t $t . && sudo docker push $t
# Run
# t=ultralytics/ultralytics:latest-cpu && sudo docker run -it --ipc=host --name NAME $t
# Pull and Run
# t=ultralytics/ultralytics:latest-cpu && sudo docker pull $t && sudo docker run -it --ipc=host --name NAME $t
# Pull and Run with local volume mounted
# t=ultralytics/ultralytics:latest-cpu && sudo docker pull $t && sudo docker run -it --ipc=host -v "$(pwd)"/shared/datasets:/datasets $t
docker_origin/Dockerfile-jetson-jetpack4 0 → 100644
View file @ af155c51
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Builds ultralytics/ultralytics:jetson-jetpack4 image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Supports JetPack4.x for YOLO11 on Jetson Nano, TX2, Xavier NX, AGX Xavier
# Start FROM https://catalog.ngc.nvidia.com/orgs/nvidia/containers/l4t-cuda
FROM nvcr.io/nvidia/l4t-cuda:10.2.460-runtime
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1
# Downloads to user config dir
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \
https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \
/root/.config/Ultralytics/
# Add NVIDIA repositories for TensorRT dependencies
RUN wget -q -O - https://repo.download.nvidia.com/jetson/jetson-ota-public.asc | apt-key add - && \
echo "deb https://repo.download.nvidia.com/jetson/common r32.7 main" > /etc/apt/sources.list.d/nvidia-l4t-apt-source.list && \
echo "deb https://repo.download.nvidia.com/jetson/t194 r32.7 main" >> /etc/apt/sources.list.d/nvidia-l4t-apt-source.list
# Install dependencies
RUN apt-get update && \
apt-get install -y --no-install-recommends \
git python3.8 python3.8-dev python3-pip python3-libnvinfer libopenmpi-dev libopenblas-base libomp-dev gcc \
&& rm -rf /var/lib/apt/lists/*
# Create symbolic links for python3.8 and pip3
RUN ln -sf /usr/bin/python3.8 /usr/bin/python3
RUN ln -s /usr/bin/pip3 /usr/bin/pip
# Create working directory
WORKDIR /ultralytics
# Copy contents and configure git
COPY . .
RUN sed -i '/^\[http "https:\/\/github\.com\/"\]/,+1d' .git/config
ADD https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt .
# Download onnxruntime-gpu 1.8.0 and tensorrt 8.2.0.6
# Other versions can be seen in https://elinux.org/Jetson_Zoo and https://forums.developer.nvidia.com/t/pytorch-for-jetson/72048
ADD https://nvidia.box.com/shared/static/gjqofg7rkg97z3gc8jeyup6t8n9j8xjw.whl onnxruntime_gpu-1.8.0-cp38-cp38-linux_aarch64.whl
ADD https://forums.developer.nvidia.com/uploads/short-url/hASzFOm9YsJx6VVFrDW1g44CMmv.whl tensorrt-8.2.0.6-cp38-none-linux_aarch64.whl
# Install pip packages
RUN python3 -m pip install --upgrade pip wheel
RUN pip install \
onnxruntime_gpu-1.8.0-cp38-cp38-linux_aarch64.whl \
tensorrt-8.2.0.6-cp38-none-linux_aarch64.whl \
https://github.com/ultralytics/assets/releases/download/v0.0.0/torch-1.11.0a0+gitbc2c6ed-cp38-cp38-linux_aarch64.whl \
https://github.com/ultralytics/assets/releases/download/v0.0.0/torchvision-0.12.0a0+9b5a3fe-cp38-cp38-linux_aarch64.whl
RUN pip install -e ".[export]"
# Remove extra build files
RUN rm -rf *.whl /root/.config/Ultralytics/persistent_cache.json
# Usage Examples -------------------------------------------------------------------------------------------------------
# Build and Push
# t=ultralytics/ultralytics:latest-jetson-jetpack4 && sudo docker build --platform linux/arm64 -f docker/Dockerfile-jetson-jetpack4 -t $t . && sudo docker push $t
# Run
# t=ultralytics/ultralytics:latest-jetson-jetpack4 && sudo docker run -it --ipc=host $t
# Pull and Run
# t=ultralytics/ultralytics:latest-jetson-jetpack4 && sudo docker pull $t && sudo docker run -it --ipc=host $t
# Pull and Run with NVIDIA runtime
# t=ultralytics/ultralytics:latest-jetson-jetpack4 && sudo docker pull $t && sudo docker run -it --ipc=host --runtime=nvidia $t
docker_origin/Dockerfile-jetson-jetpack5 0 → 100644
View file @ af155c51
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Builds ultralytics/ultralytics:jetson-jetson-jetpack5 image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Supports JetPack5.x for YOLO11 on Jetson Xavier NX, AGX Xavier, AGX Orin, Orin Nano and Orin NX
# Start FROM https://catalog.ngc.nvidia.com/orgs/nvidia/containers/l4t-pytorch
FROM nvcr.io/nvidia/l4t-pytorch:r35.2.1-pth2.0-py3
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_BREAK_SYSTEM_PACKAGES=1
# Downloads to user config dir
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \
https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \
/root/.config/Ultralytics/
# Install linux packages
# g++ required to build 'tflite_support' and 'lap' packages
# libusb-1.0-0 required for 'tflite_support' package when exporting to TFLite
# pkg-config and libhdf5-dev (not included) are needed to build 'h5py==3.11.0' aarch64 wheel required by 'tensorflow'
RUN apt-get update && \
apt-get install -y --no-install-recommends \
gcc git zip unzip wget curl htop libgl1 libglib2.0-0 libpython3-dev gnupg g++ libusb-1.0-0 \
&& rm -rf /var/lib/apt/lists/*
# Create working directory
WORKDIR /ultralytics
# Copy contents and configure git
COPY . .
RUN sed -i '/^\[http "https:\/\/github\.com\/"\]/,+1d' .git/config
ADD https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt .
# Remove opencv-python from Ultralytics dependencies as it conflicts with opencv-python installed in base image
RUN sed -i '/opencv-python/d' pyproject.toml
# Download onnxruntime-gpu 1.15.1 for Jetson Linux 35.2.1 (JetPack 5.1). Other versions can be seen in https://elinux.org/Jetson_Zoo#ONNX_Runtime
ADD https://nvidia.box.com/shared/static/mvdcltm9ewdy2d5nurkiqorofz1s53ww.whl onnxruntime_gpu-1.15.1-cp38-cp38-linux_aarch64.whl
# Install pip packages manually for TensorRT compatibility https://github.com/NVIDIA/TensorRT/issues/2567
RUN python3 -m pip install --upgrade pip wheel
RUN pip install onnxruntime_gpu-1.15.1-cp38-cp38-linux_aarch64.whl
RUN pip install -e ".[export]"
# Remove extra build files
RUN rm -rf *.whl /root/.config/Ultralytics/persistent_cache.json
# Usage Examples -------------------------------------------------------------------------------------------------------
# Build and Push
# t=ultralytics/ultralytics:latest-jetson-jetpack5 && sudo docker build --platform linux/arm64 -f docker/Dockerfile-jetson-jetpack5 -t $t . && sudo docker push $t
# Run
# t=ultralytics/ultralytics:latest-jetson-jetpack5 && sudo docker run -it --ipc=host $t
# Pull and Run
# t=ultralytics/ultralytics:latest-jetson-jetpack5 && sudo docker pull $t && sudo docker run -it --ipc=host $t
# Pull and Run with NVIDIA runtime
# t=ultralytics/ultralytics:latest-jetson-jetpack5 && sudo docker pull $t && sudo docker run -it --ipc=host --runtime=nvidia $t
docker_origin/Dockerfile-jetson-jetpack6 0 → 100644
View file @ af155c51
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Builds ultralytics/ultralytics:jetson-jetpack6 image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Supports JetPack6.x for YOLO11 on Jetson AGX Orin, Orin NX and Orin Nano Series
# Start FROM https://catalog.ngc.nvidia.com/orgs/nvidia/containers/l4t-jetpack
FROM nvcr.io/nvidia/l4t-jetpack:r36.3.0
# Set environment variables
ENV PYTHONUNBUFFERED=1 \
PYTHONDONTWRITEBYTECODE=1 \
PIP_NO_CACHE_DIR=1 \
PIP_BREAK_SYSTEM_PACKAGES=1
# Downloads to user config dir
ADD https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.ttf \
https://github.com/ultralytics/assets/releases/download/v0.0.0/Arial.Unicode.ttf \
/root/.config/Ultralytics/
# Install dependencies
RUN apt-get update && \
apt-get install -y --no-install-recommends \
git python3-pip libopenmpi-dev libopenblas-base libomp-dev \
&& rm -rf /var/lib/apt/lists/*
# Create working directory
WORKDIR /ultralytics
# Copy contents and configure git
COPY . .
RUN sed -i '/^\[http "https:\/\/github\.com\/"\]/,+1d' .git/config
ADD https://github.com/ultralytics/assets/releases/download/v8.3.0/yolo11n.pt .
# Download onnxruntime-gpu 1.18.0 from https://elinux.org/Jetson_Zoo and https://forums.developer.nvidia.com/t/pytorch-for-jetson/72048
ADD https://nvidia.box.com/shared/static/48dtuob7meiw6ebgfsfqakc9vse62sg4.whl onnxruntime_gpu-1.18.0-cp310-cp310-linux_aarch64.whl
# Pip install onnxruntime-gpu, torch, torchvision and ultralytics
RUN python3 -m pip install --upgrade pip wheel
RUN pip install \
onnxruntime_gpu-1.18.0-cp310-cp310-linux_aarch64.whl \
https://github.com/ultralytics/assets/releases/download/v0.0.0/torch-2.3.0-cp310-cp310-linux_aarch64.whl \
https://github.com/ultralytics/assets/releases/download/v0.0.0/torchvision-0.18.0a0+6043bc2-cp310-cp310-linux_aarch64.whl
RUN pip install -e ".[export]"
# Remove extra build files
RUN rm -rf *.whl /root/.config/Ultralytics/persistent_cache.json
# Usage Examples -------------------------------------------------------------------------------------------------------
# Build and Push
# t=ultralytics/ultralytics:latest-jetson-jetpack6 && sudo docker build --platform linux/arm64 -f docker/Dockerfile-jetson-jetpack6 -t $t . && sudo docker push $t
# Run
# t=ultralytics/ultralytics:latest-jetson-jetpack6 && sudo docker run -it --ipc=host $t
# Pull and Run
# t=ultralytics/ultralytics:latest-jetson-jetpack6 && sudo docker pull $t && sudo docker run -it --ipc=host $t
# Pull and Run with NVIDIA runtime
# t=ultralytics/ultralytics:latest-jetson-jetpack6 && sudo docker pull $t && sudo docker run -it --ipc=host --runtime=nvidia $t
docker_origin/Dockerfile-jupyter 0 → 100644
View file @ af155c51
# Ultralytics YOLO 🚀, AGPL-3.0 license
# Builds ultralytics/ultralytics:latest-jupyter image on DockerHub https://hub.docker.com/r/ultralytics/ultralytics
# Image provides JupyterLab interface for interactive YOLO development and includes tutorial notebooks
# Start from Python-based Ultralytics image for full Python environment
FROM ultralytics/ultralytics:latest-python
# Install JupyterLab for interactive development
RUN /usr/local/bin/pip install jupyterlab
# Create persistent data directory structure
RUN mkdir /data
# Configure YOLO directory paths
RUN mkdir /data/datasets && /usr/local/bin/yolo settings datasets_dir="/data/datasets"
RUN mkdir /data/weights && /usr/local/bin/yolo settings weights_dir="/data/weights"
RUN mkdir /data/runs && /usr/local/bin/yolo settings runs_dir="/data/runs"
# Start JupyterLab with tutorial notebook
ENTRYPOINT ["/usr/local/bin/jupyter", "lab", "--allow-root", "--ip=*", "/ultralytics/examples/tutorial.ipynb"]
# Usage Examples -------------------------------------------------------------------------------------------------------
# Build and Push
# t=ultralytics/ultralytics:latest-jupyter && sudo docker build -f docker/Dockerfile-jupyter -t $t . && sudo docker push $t
# Run
# t=ultralytics/ultralytics:latest-jupyter && sudo docker run -it --ipc=host -p 8888:8888 $t
# Pull and Run
# t=ultralytics/ultralytics:latest-jupyter && sudo docker pull $t && sudo docker run -it --ipc=host -p 8888:8888 $t
# Pull and Run with local volume mounted
# t=ultralytics/ultralytics:latest-jupyter && sudo docker pull $t && sudo docker run -it --ipc=host -p 8888:8888 -v "$(pwd)"/datasets:/data/datasets $t
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment