Skip to content

GitLab

Commit 75d93027 authored by bailuo's avatar bailuo
Browse files

init

parents
Pipeline #2479 failed with stages
in 0 seconds
Hide whitespace changes
Inline Side-by-side
Showing with 1524 additions and 0 deletions
sam2/.github/workflows/check_fmt.yml 0 → 100644
View file @ 75d93027
name: SAM2/fmt
on:
pull_request:
branches:
- main
jobs:
ufmt_check:
runs-on: ubuntu-latest
steps:
- name: Check formatting
uses: omnilib/ufmt@action-v1
with:
path: sam2 tools
version: "2.0.0b2"
python-version: "3.10"
black-version: "24.2.0"
usort-version: "1.0.2"
sam2/.gitignore 0 → 100644
View file @ 75d93027
.vscode/
.DS_Store
__pycache__/
*-checkpoint.ipynb
.venv
*.egg*
build/*
_C.*
outputs/*
checkpoints/*.pt
sam2/.watchmanconfig 0 → 100644
View file @ 75d93027
{}
\ No newline at end of file
sam2/CODE_OF_CONDUCT.md 0 → 100644
View file @ 75d93027
# Code of Conduct
## Our Pledge
In the interest of fostering an open and welcoming environment, we as
contributors and maintainers pledge to make participation in our project and
our community a harassment-free experience for everyone, regardless of age, body
size, disability, ethnicity, sex characteristics, gender identity and expression,
level of experience, education, socio-economic status, nationality, personal
appearance, race, religion, or sexual identity and orientation.
## Our Standards
Examples of behavior that contributes to creating a positive environment
include:
* Using welcoming and inclusive language
* Being respectful of differing viewpoints and experiences
* Gracefully accepting constructive criticism
* Focusing on what is best for the community
* Showing empathy towards other community members
Examples of unacceptable behavior by participants include:
* The use of sexualized language or imagery and unwelcome sexual attention or
advances
* Trolling, insulting/derogatory comments, and personal or political attacks
* Public or private harassment
* Publishing others' private information, such as a physical or electronic
address, without explicit permission
* Other conduct which could reasonably be considered inappropriate in a
professional setting
## Our Responsibilities
Project maintainers are responsible for clarifying the standards of acceptable
behavior and are expected to take appropriate and fair corrective action in
response to any instances of unacceptable behavior.
Project maintainers have the right and responsibility to remove, edit, or
reject comments, commits, code, wiki edits, issues, and other contributions
that are not aligned to this Code of Conduct, or to ban temporarily or
permanently any contributor for other behaviors that they deem inappropriate,
threatening, offensive, or harmful.
## Scope
This Code of Conduct applies within all project spaces, and it also applies when
an individual is representing the project or its community in public spaces.
Examples of representing a project or community include using an official
project e-mail address, posting via an official social media account, or acting
as an appointed representative at an online or offline event. Representation of
a project may be further defined and clarified by project maintainers.
This Code of Conduct also applies outside the project spaces when there is a
reasonable belief that an individual's behavior may have a negative impact on
the project or its community.
## Enforcement
Instances of abusive, harassing, or otherwise unacceptable behavior may be
reported by contacting the project team at <opensource-conduct@fb.com>. All
complaints will be reviewed and investigated and will result in a response that
is deemed necessary and appropriate to the circumstances. The project team is
obligated to maintain confidentiality with regard to the reporter of an incident.
Further details of specific enforcement policies may be posted separately.
Project maintainers who do not follow or enforce the Code of Conduct in good
faith may face temporary or permanent repercussions as determined by other
members of the project's leadership.
## Attribution
This Code of Conduct is adapted from the [Contributor Covenant][homepage], version 1.4,
available at https://www.contributor-covenant.org/version/1/4/code-of-conduct.html
[homepage]: https://www.contributor-covenant.org
For answers to common questions about this code of conduct, see
https://www.contributor-covenant.org/faq
sam2/CONTRIBUTING.md 0 → 100644
View file @ 75d93027
# Contributing to segment-anything
We want to make contributing to this project as easy and transparent as
possible.
## Pull Requests
We actively welcome your pull requests.
1. Fork the repo and create your branch from `main`.
2. If you've added code that should be tested, add tests.
3. If you've changed APIs, update the documentation.
4. Ensure the test suite passes.
5. Make sure your code lints, using the `ufmt format` command. Linting requires `black==24.2.0`, `usort==1.0.2`, and `ufmt==2.0.0b2`, which can be installed via `pip install -e ".[dev]"`.
6. If you haven't already, complete the Contributor License Agreement ("CLA").
## Contributor License Agreement ("CLA")
In order to accept your pull request, we need you to submit a CLA. You only need
to do this once to work on any of Facebook's open source projects.
Complete your CLA here: <https://code.facebook.com/cla>
## Issues
We use GitHub issues to track public bugs. Please ensure your description is
clear and has sufficient instructions to be able to reproduce the issue.
Facebook has a [bounty program](https://www.facebook.com/whitehat/) for the safe
disclosure of security bugs. In those cases, please go through the process
outlined on that page and do not file a public issue.
## License
By contributing to segment-anything, you agree that your contributions will be licensed
under the LICENSE file in the root directory of this source tree.
sam2/INSTALL.md 0 → 100644
View file @ 75d93027
## Installation
### Requirements
- Linux with Python ≥ 3.10, PyTorch ≥ 2.3.1 and [torchvision](https://github.com/pytorch/vision/) that matches the PyTorch installation. Install them together at https://pytorch.org to ensure this.
* Note older versions of Python or PyTorch may also work. However, the versions above are strongly recommended to provide all features such as `torch.compile`.
- [CUDA toolkits](https://developer.nvidia.com/cuda-toolkit-archive) that match the CUDA version for your PyTorch installation. This should typically be CUDA 12.1 if you follow the default installation command.
- If you are installing on Windows, it's strongly recommended to use [Windows Subsystem for Linux (WSL)](https://learn.microsoft.com/en-us/windows/wsl/install) with Ubuntu.
Then, install SAM 2 from the root of this repository via
```bash
pip install -e ".[notebooks]"
```
Note that you may skip building the SAM 2 CUDA extension during installation via environment variable `SAM2_BUILD_CUDA=0`, as follows:
```bash
# skip the SAM 2 CUDA extension
SAM2_BUILD_CUDA=0 pip install -e ".[notebooks]"
```
This would also skip the post-processing step at runtime (removing small holes and sprinkles in the output masks, which requires the CUDA extension), but shouldn't affect the results in most cases.
### Building the SAM 2 CUDA extension
By default, we allow the installation to proceed even if the SAM 2 CUDA extension fails to build. (In this case, the build errors are hidden unless using `-v` for verbose output in `pip install`.)
If you see a message like `Skipping the post-processing step due to the error above` at runtime or `Failed to build the SAM 2 CUDA extension due to the error above` during installation, it indicates that the SAM 2 CUDA extension failed to build in your environment. In this case, **you can still use SAM 2 for both image and video applications**. The post-processing step (removing small holes and sprinkles in the output masks) will be skipped, but this shouldn't affect the results in most cases.
If you would like to enable this post-processing step, you can reinstall SAM 2 on a GPU machine with environment variable `SAM2_BUILD_ALLOW_ERRORS=0` to force building the CUDA extension (and raise errors if it fails to build), as follows
```bash
pip uninstall -y SAM-2 && \
rm -f ./sam2/*.so && \
SAM2_BUILD_ALLOW_ERRORS=0 pip install -v -e ".[notebooks]"
```
Note that PyTorch needs to be installed first before building the SAM 2 CUDA extension. It's also necessary to install [CUDA toolkits](https://developer.nvidia.com/cuda-toolkit-archive) that match the CUDA version for your PyTorch installation. (This should typically be CUDA 12.1 if you follow the default installation command.) After installing the CUDA toolkits, you can check its version via `nvcc --version`.
Please check the section below on common installation issues if the CUDA extension fails to build during installation or load at runtime.
### Common Installation Issues
Click each issue for its solutions:
<details>
<summary>
I got `ImportError: cannot import name '_C' from 'sam2'`
</summary>
<br/>
This is usually because you haven't run the `pip install -e ".[notebooks]"` step above or the installation failed. Please install SAM 2 first, and see the other issues if your installation fails.
In some systems, you may need to run `python setup.py build_ext --inplace` in the SAM 2 repo root as suggested in https://github.com/facebookresearch/sam2/issues/77.
</details>
<details>
<summary>
I got `MissingConfigException: Cannot find primary config 'configs/sam2.1/sam2.1_hiera_l.yaml'`
</summary>
<br/>
This is usually because you haven't run the `pip install -e .` step above, so `sam2` isn't in your Python's `sys.path`. Please run this installation step. In case it still fails after the installation step, you may try manually adding the root of this repo to `PYTHONPATH` via
```bash
export SAM2_REPO_ROOT=/path/to/sam2 # path to this repo
export PYTHONPATH="${SAM2_REPO_ROOT}:${PYTHONPATH}"
```
to manually add `sam2_configs` into your Python's `sys.path`.
</details>
<details>
<summary>
I got `RuntimeError: Error(s) in loading state_dict for SAM2Base` when loading the new SAM 2.1 checkpoints
</summary>
<br/>
This is likely because you have installed a previous version of this repo, which doesn't have the new modules to support the SAM 2.1 checkpoints yet. Please try the following steps:
1. pull the latest code from the `main` branch of this repo
2. run `pip uninstall -y SAM-2` to uninstall any previous installations
3. then install the latest repo again using `pip install -e ".[notebooks]"`
In case the steps above still don't resolve the error, please try running in your Python environment the following
```python
from sam2.modeling import sam2_base
print(sam2_base.__file__)
```
and check whether the content in the printed local path of `sam2/modeling/sam2_base.py` matches the latest one in https://github.com/facebookresearch/sam2/blob/main/sam2/modeling/sam2_base.py (e.g. whether your local file has `no_obj_embed_spatial`) to indentify if you're still using a previous installation.
</details>
<details>
<summary>
My installation failed with `CUDA_HOME environment variable is not set`
</summary>
<br/>
This usually happens because the installation step cannot find the CUDA toolkits (that contain the NVCC compiler) to build a custom CUDA kernel in SAM 2. Please install [CUDA toolkits](https://developer.nvidia.com/cuda-toolkit-archive) or the version that matches the CUDA version for your PyTorch installation. If the error persists after installing CUDA toolkits, you may explicitly specify `CUDA_HOME` via
```
export CUDA_HOME=/usr/local/cuda # change to your CUDA toolkit path
```
and rerun the installation.
Also, you should make sure
```
python -c 'import torch; from torch.utils.cpp_extension import CUDA_HOME; print(torch.cuda.is_available(), CUDA_HOME)'
```
print `(True, a directory with cuda)` to verify that the CUDA toolkits are correctly set up.
If you are still having problems after verifying that the CUDA toolkit is installed and the `CUDA_HOME` environment variable is set properly, you may have to add the `--no-build-isolation` flag to the pip command:
```
pip install --no-build-isolation -e .
```
</details>
<details>
<summary>
I got `undefined symbol: _ZN3c1015SmallVectorBaseIjE8grow_podEPKvmm` (or similar errors)
</summary>
<br/>
This usually happens because you have multiple versions of dependencies (PyTorch or CUDA) in your environment. During installation, the SAM 2 library is compiled against one version library while at run time it links against another version. This might be due to that you have different versions of PyTorch or CUDA installed separately via `pip` or `conda`. You may delete one of the duplicates to only keep a single PyTorch and CUDA version.
In particular, if you have a lower PyTorch version than 2.3.1, it's recommended to upgrade to PyTorch 2.3.1 or higher first. Otherwise, the installation script will try to upgrade to the latest PyTorch using `pip`, which could sometimes lead to duplicated PyTorch installation if you have previously installed another PyTorch version using `conda`.
We have been building SAM 2 against PyTorch 2.3.1 internally. However, a few user comments (e.g. https://github.com/facebookresearch/sam2/issues/22, https://github.com/facebookresearch/sam2/issues/14) suggested that downgrading to PyTorch 2.1.0 might resolve this problem. In case the error persists, you may try changing the restriction from `torch>=2.3.1` to `torch>=2.1.0` in both [`pyproject.toml`](pyproject.toml) and [`setup.py`](setup.py) to allow PyTorch 2.1.0.
</details>
<details>
<summary>
I got `CUDA error: no kernel image is available for execution on the device`
</summary>
<br/>
A possible cause could be that the CUDA kernel is somehow not compiled towards your GPU's CUDA [capability](https://developer.nvidia.com/cuda-gpus). This could happen if the installation is done in an environment different from the runtime (e.g. in a slurm system).
You can try pulling the latest code from the SAM 2 repo and running the following
```
export TORCH_CUDA_ARCH_LIST=9.0 8.0 8.6 8.9 7.0 7.2 7.5 6.0`
```
to manually specify the CUDA capability in the compilation target that matches your GPU.
</details>
<details>
<summary>
I got `RuntimeError: No available kernel. Aborting execution.` (or similar errors)
</summary>
<br/>
This is probably because your machine doesn't have a GPU or a compatible PyTorch version for Flash Attention (see also https://discuss.pytorch.org/t/using-f-scaled-dot-product-attention-gives-the-error-runtimeerror-no-available-kernel-aborting-execution/180900 for a discussion in PyTorch forum). You may be able to resolve this error by replacing the line
```python
OLD_GPU, USE_FLASH_ATTN, MATH_KERNEL_ON = get_sdpa_settings()
```
in [`sam2/modeling/sam/transformer.py`](sam2/modeling/sam/transformer.py) with
```python
OLD_GPU, USE_FLASH_ATTN, MATH_KERNEL_ON = True, True, True
```
to relax the attention kernel setting and use other kernels than Flash Attention.
</details>
<details>
<summary>
I got `Error compiling objects for extension`
</summary>
<br/>
You may see error log of:
> unsupported Microsoft Visual Studio version! Only the versions between 2017 and 2022 (inclusive) are supported! The nvcc flag '-allow-unsupported-compiler' can be used to override this version check; however, using an unsupported host compiler may cause compilation failure or incorrect run time execution. Use at your own risk.
This is probably because your versions of CUDA and Visual Studio are incompatible. (see also https://stackoverflow.com/questions/78515942/cuda-compatibility-with-visual-studio-2022-version-17-10 for a discussion in stackoverflow).<br>
You may be able to fix this by adding the `-allow-unsupported-compiler` argument to `nvcc` after L48 in the [setup.py](https://github.com/facebookresearch/sam2/blob/main/setup.py). <br>
After adding the argument, `get_extension()` will look like this:
```python
def get_extensions():
srcs = ["sam2/csrc/connected_components.cu"]
compile_args = {
"cxx": [],
"nvcc": [
"-DCUDA_HAS_FP16=1",
"-D__CUDA_NO_HALF_OPERATORS__",
"-D__CUDA_NO_HALF_CONVERSIONS__",
"-D__CUDA_NO_HALF2_OPERATORS__",
"-allow-unsupported-compiler" # Add this argument
],
}
ext_modules = [CUDAExtension("sam2._C", srcs, extra_compile_args=compile_args)]
return ext_modules
```
</details>
sam2/LICENSE 0 → 100644
View file @ 75d93027
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License.
sam2/LICENSE_cctorch 0 → 100644
View file @ 75d93027
BSD 3-Clause License
Copyright (c) 2020, the respective contributors, as shown by the AUTHORS file.
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice, this
list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
3. Neither the name of the copyright holder nor the names of its
contributors may be used to endorse or promote products derived from
this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
sam2/MANIFEST.in 0 → 100644
View file @ 75d93027
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
recursive-include sam2 *.yaml #include all config files
sam2/README.md 0 → 100644
View file @ 75d93027
# SAM 2: Segment Anything in Images and Videos
**[AI at Meta, FAIR](https://ai.meta.com/research/)**
[Nikhila Ravi](https://nikhilaravi.com/), [Valentin Gabeur](https://gabeur.github.io/), [Yuan-Ting Hu](https://scholar.google.com/citations?user=E8DVVYQAAAAJ&hl=en), [Ronghang Hu](https://ronghanghu.com/), [Chaitanya Ryali](https://scholar.google.com/citations?user=4LWx24UAAAAJ&hl=en), [Tengyu Ma](https://scholar.google.com/citations?user=VeTSl0wAAAAJ&hl=en), [Haitham Khedr](https://hkhedr.com/), [Roman Rädle](https://scholar.google.de/citations?user=Tpt57v0AAAAJ&hl=en), [Chloe Rolland](https://scholar.google.com/citations?hl=fr&user=n-SnMhoAAAAJ), [Laura Gustafson](https://scholar.google.com/citations?user=c8IpF9gAAAAJ&hl=en), [Eric Mintun](https://ericmintun.github.io/), [Junting Pan](https://junting.github.io/), [Kalyan Vasudev Alwala](https://scholar.google.co.in/citations?user=m34oaWEAAAAJ&hl=en), [Nicolas Carion](https://www.nicolascarion.com/), [Chao-Yuan Wu](https://chaoyuan.org/), [Ross Girshick](https://www.rossgirshick.info/), [Piotr Dollár](https://pdollar.github.io/), [Christoph Feichtenhofer](https://feichtenhofer.github.io/)
[[`Paper`](https://ai.meta.com/research/publications/sam-2-segment-anything-in-images-and-videos/)] [[`Project`](https://ai.meta.com/sam2)] [[`Demo`](https://sam2.metademolab.com/)] [[`Dataset`](https://ai.meta.com/datasets/segment-anything-video)] [[`Blog`](https://ai.meta.com/blog/segment-anything-2)] [[`BibTeX`](#citing-sam-2)]
![SAM 2 architecture](assets/model_diagram.png?raw=true)
**Segment Anything Model 2 (SAM 2)** is a foundation model towards solving promptable visual segmentation in images and videos. We extend SAM to video by considering images as a video with a single frame. The model design is a simple transformer architecture with streaming memory for real-time video processing. We build a model-in-the-loop data engine, which improves model and data via user interaction, to collect [**our SA-V dataset**](https://ai.meta.com/datasets/segment-anything-video), the largest video segmentation dataset to date. SAM 2 trained on our data provides strong performance across a wide range of tasks and visual domains.
![SA-V dataset](assets/sa_v_dataset.jpg?raw=true)
## Latest updates
**09/30/2024 -- SAM 2.1 Developer Suite (new checkpoints, training code, web demo) is released**
- A new suite of improved model checkpoints (denoted as **SAM 2.1**) are released. See [Model Description](#model-description) for details.
* To use the new SAM 2.1 checkpoints, you need the latest model code from this repo. If you have installed an earlier version of this repo, please first uninstall the previous version via `pip uninstall SAM-2`, pull the latest code from this repo (with `git pull`), and then reinstall the repo following [Installation](#installation) below.
- The training (and fine-tuning) code has been released. See [`training/README.md`](training/README.md) on how to get started.
- The frontend + backend code for the SAM 2 web demo has been released. See [`demo/README.md`](demo/README.md) for details.
## Installation
SAM 2 needs to be installed first before use. The code requires `python>=3.10`, as well as `torch>=2.3.1` and `torchvision>=0.18.1`. Please follow the instructions [here](https://pytorch.org/get-started/locally/) to install both PyTorch and TorchVision dependencies. You can install SAM 2 on a GPU machine using:
```bash
git clone https://github.com/facebookresearch/sam2.git && cd sam2
pip install -e .
```
If you are installing on Windows, it's strongly recommended to use [Windows Subsystem for Linux (WSL)](https://learn.microsoft.com/en-us/windows/wsl/install) with Ubuntu.
To use the SAM 2 predictor and run the example notebooks, `jupyter` and `matplotlib` are required and can be installed by:
```bash
pip install -e ".[notebooks]"
```
Note:
1. It's recommended to create a new Python environment via [Anaconda](https://www.anaconda.com/) for this installation and install PyTorch 2.3.1 (or higher) via `pip` following https://pytorch.org/. If you have a PyTorch version lower than 2.3.1 in your current environment, the installation command above will try to upgrade it to the latest PyTorch version using `pip`.
2. The step above requires compiling a custom CUDA kernel with the `nvcc` compiler. If it isn't already available on your machine, please install the [CUDA toolkits](https://developer.nvidia.com/cuda-toolkit-archive) with a version that matches your PyTorch CUDA version.
3. If you see a message like `Failed to build the SAM 2 CUDA extension` during installation, you can ignore it and still use SAM 2 (some post-processing functionality may be limited, but it doesn't affect the results in most cases).
Please see [`INSTALL.md`](./INSTALL.md) for FAQs on potential issues and solutions.
## Getting Started
### Download Checkpoints
First, we need to download a model checkpoint. All the model checkpoints can be downloaded by running:
```bash
cd checkpoints && \
./download_ckpts.sh && \
cd ..
```
or individually from:
- [sam2.1_hiera_tiny.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_tiny.pt)
- [sam2.1_hiera_small.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_small.pt)
- [sam2.1_hiera_base_plus.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_base_plus.pt)
- [sam2.1_hiera_large.pt](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt)
(note that these are the improved checkpoints denoted as SAM 2.1; see [Model Description](#model-description) for details.)
Then SAM 2 can be used in a few lines as follows for image and video prediction.
### Image prediction
SAM 2 has all the capabilities of [SAM](https://github.com/facebookresearch/segment-anything) on static images, and we provide image prediction APIs that closely resemble SAM for image use cases. The `SAM2ImagePredictor` class has an easy interface for image prompting.
```python
import torch
from sam2.build_sam import build_sam2
from sam2.sam2_image_predictor import SAM2ImagePredictor
checkpoint = "./checkpoints/sam2.1_hiera_large.pt"
model_cfg = "configs/sam2.1/sam2.1_hiera_l.yaml"
predictor = SAM2ImagePredictor(build_sam2(model_cfg, checkpoint))
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
predictor.set_image(<your_image>)
masks, _, _ = predictor.predict(<input_prompts>)
```
Please refer to the examples in [image_predictor_example.ipynb](./notebooks/image_predictor_example.ipynb) (also in Colab [here](https://colab.research.google.com/github/facebookresearch/sam2/blob/main/notebooks/image_predictor_example.ipynb)) for static image use cases.
SAM 2 also supports automatic mask generation on images just like SAM. Please see [automatic_mask_generator_example.ipynb](./notebooks/automatic_mask_generator_example.ipynb) (also in Colab [here](https://colab.research.google.com/github/facebookresearch/sam2/blob/main/notebooks/automatic_mask_generator_example.ipynb)) for automatic mask generation in images.
### Video prediction
For promptable segmentation and tracking in videos, we provide a video predictor with APIs for example to add prompts and propagate masklets throughout a video. SAM 2 supports video inference on multiple objects and uses an inference state to keep track of the interactions in each video.
```python
import torch
from sam2.build_sam import build_sam2_video_predictor
checkpoint = "./checkpoints/sam2.1_hiera_large.pt"
model_cfg = "configs/sam2.1/sam2.1_hiera_l.yaml"
predictor = build_sam2_video_predictor(model_cfg, checkpoint)
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
state = predictor.init_state(<your_video>)
# add new prompts and instantly get the output on the same frame
frame_idx, object_ids, masks = predictor.add_new_points_or_box(state, <your_prompts>):
# propagate the prompts to get masklets throughout the video
for frame_idx, object_ids, masks in predictor.propagate_in_video(state):
...
```
Please refer to the examples in [video_predictor_example.ipynb](./notebooks/video_predictor_example.ipynb) (also in Colab [here](https://colab.research.google.com/github/facebookresearch/sam2/blob/main/notebooks/video_predictor_example.ipynb)) for details on how to add click or box prompts, make refinements, and track multiple objects in videos.
## Load from 🤗 Hugging Face
Alternatively, models can also be loaded from [Hugging Face](https://huggingface.co/models?search=facebook/sam2) (requires `pip install huggingface_hub`).
For image prediction:
```python
import torch
from sam2.sam2_image_predictor import SAM2ImagePredictor
predictor = SAM2ImagePredictor.from_pretrained("facebook/sam2-hiera-large")
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
predictor.set_image(<your_image>)
masks, _, _ = predictor.predict(<input_prompts>)
```
For video prediction:
```python
import torch
from sam2.sam2_video_predictor import SAM2VideoPredictor
predictor = SAM2VideoPredictor.from_pretrained("facebook/sam2-hiera-large")
with torch.inference_mode(), torch.autocast("cuda", dtype=torch.bfloat16):
state = predictor.init_state(<your_video>)
# add new prompts and instantly get the output on the same frame
frame_idx, object_ids, masks = predictor.add_new_points_or_box(state, <your_prompts>):
# propagate the prompts to get masklets throughout the video
for frame_idx, object_ids, masks in predictor.propagate_in_video(state):
...
```
## Model Description
### SAM 2.1 checkpoints
The table below shows the improved SAM 2.1 checkpoints released on September 29, 2024.
| **Model** | **Size (M)** | **Speed (FPS)** | **SA-V test (J&F)** | **MOSE val (J&F)** | **LVOS v2 (J&F)** |
| :------------------: | :----------: | :--------------------: | :-----------------: | :----------------: | :---------------: |
| sam2.1_hiera_tiny <br /> ([config](sam2/configs/sam2.1/sam2.1_hiera_t.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_tiny.pt)) | 38.9 | 47.2 | 76.5 | 71.8 | 77.3 |
| sam2.1_hiera_small <br /> ([config](sam2/configs/sam2.1/sam2.1_hiera_s.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_small.pt)) | 46 | 43.3 (53.0 compiled\*) | 76.6 | 73.5 | 78.3 |
| sam2.1_hiera_base_plus <br /> ([config](sam2/configs/sam2.1/sam2.1_hiera_b+.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_base_plus.pt)) | 80.8 | 34.8 (43.8 compiled\*) | 78.2 | 73.7 | 78.2 |
| sam2.1_hiera_large <br /> ([config](sam2/configs/sam2.1/sam2.1_hiera_l.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt)) | 224.4 | 24.2 (30.2 compiled\*) | 79.5 | 74.6 | 80.6 |
### SAM 2 checkpoints
The previous SAM 2 checkpoints released on July 29, 2024 can be found as follows:
| **Model** | **Size (M)** | **Speed (FPS)** | **SA-V test (J&F)** | **MOSE val (J&F)** | **LVOS v2 (J&F)** |
| :------------------: | :----------: | :--------------------: | :-----------------: | :----------------: | :---------------: |
| sam2_hiera_tiny <br /> ([config](sam2/configs/sam2/sam2_hiera_t.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/072824/sam2_hiera_tiny.pt)) | 38.9 | 47.2 | 75.0 | 70.9 | 75.3 |
| sam2_hiera_small <br /> ([config](sam2/configs/sam2/sam2_hiera_s.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/072824/sam2_hiera_small.pt)) | 46 | 43.3 (53.0 compiled\*) | 74.9 | 71.5 | 76.4 |
| sam2_hiera_base_plus <br /> ([config](sam2/configs/sam2/sam2_hiera_b+.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/072824/sam2_hiera_base_plus.pt)) | 80.8 | 34.8 (43.8 compiled\*) | 74.7 | 72.8 | 75.8 |
| sam2_hiera_large <br /> ([config](sam2/configs/sam2/sam2_hiera_l.yaml), [checkpoint](https://dl.fbaipublicfiles.com/segment_anything_2/072824/sam2_hiera_large.pt)) | 224.4 | 24.2 (30.2 compiled\*) | 76.0 | 74.6 | 79.8 |
\* Compile the model by setting `compile_image_encoder: True` in the config.
## Segment Anything Video Dataset
See [sav_dataset/README.md](sav_dataset/README.md) for details.
## Training SAM 2
You can train or fine-tune SAM 2 on custom datasets of images, videos, or both. Please check the training [README](training/README.md) on how to get started.
## Web demo for SAM 2
We have released the frontend + backend code for the SAM 2 web demo (a locally deployable version similar to https://sam2.metademolab.com/demo). Please see the web demo [README](demo/README.md) for details.
## License
The SAM 2 model checkpoints, SAM 2 demo code (front-end and back-end), and SAM 2 training code are licensed under [Apache 2.0](./LICENSE), however the [Inter Font](https://github.com/rsms/inter?tab=OFL-1.1-1-ov-file) and [Noto Color Emoji](https://github.com/googlefonts/noto-emoji) used in the SAM 2 demo code are made available under the [SIL Open Font License, version 1.1](https://openfontlicense.org/open-font-license-official-text/).
## Contributing
See [contributing](CONTRIBUTING.md) and the [code of conduct](CODE_OF_CONDUCT.md).
## Contributors
The SAM 2 project was made possible with the help of many contributors (alphabetical):
Karen Bergan, Daniel Bolya, Alex Bosenberg, Kai Brown, Vispi Cassod, Christopher Chedeau, Ida Cheng, Luc Dahlin, Shoubhik Debnath, Rene Martinez Doehner, Grant Gardner, Sahir Gomez, Rishi Godugu, Baishan Guo, Caleb Ho, Andrew Huang, Somya Jain, Bob Kamma, Amanda Kallet, Jake Kinney, Alexander Kirillov, Shiva Koduvayur, Devansh Kukreja, Robert Kuo, Aohan Lin, Parth Malani, Jitendra Malik, Mallika Malhotra, Miguel Martin, Alexander Miller, Sasha Mitts, William Ngan, George Orlin, Joelle Pineau, Kate Saenko, Rodrick Shepard, Azita Shokrpour, David Soofian, Jonathan Torres, Jenny Truong, Sagar Vaze, Meng Wang, Claudette Ward, Pengchuan Zhang.
Third-party code: we use a GPU-based connected component algorithm adapted from [`cc_torch`](https://github.com/zsef123/Connected_components_PyTorch) (with its license in [`LICENSE_cctorch`](./LICENSE_cctorch)) as an optional post-processing step for the mask predictions.
## Citing SAM 2
If you use SAM 2 or the SA-V dataset in your research, please use the following BibTeX entry.
```bibtex
@article{ravi2024sam2,
title={SAM 2: Segment Anything in Images and Videos},
author={Ravi, Nikhila and Gabeur, Valentin and Hu, Yuan-Ting and Hu, Ronghang and Ryali, Chaitanya and Ma, Tengyu and Khedr, Haitham and R{\"a}dle, Roman and Rolland, Chloe and Gustafson, Laura and Mintun, Eric and Pan, Junting and Alwala, Kalyan Vasudev and Carion, Nicolas and Wu, Chao-Yuan and Girshick, Ross and Doll{\'a}r, Piotr and Feichtenhofer, Christoph},
journal={arXiv preprint arXiv:2408.00714},
url={https://arxiv.org/abs/2408.00714},
year={2024}
}
```
sam2/backend.Dockerfile 0 → 100644
View file @ 75d93027
ARG BASE_IMAGE=pytorch/pytorch:2.3.1-cuda12.1-cudnn8-runtime
ARG MODEL_SIZE=base_plus
FROM ${BASE_IMAGE}
# Gunicorn environment variables
ENV GUNICORN_WORKERS=1
ENV GUNICORN_THREADS=2
ENV GUNICORN_PORT=5000
# SAM 2 environment variables
ENV APP_ROOT=/opt/sam2
ENV PYTHONUNBUFFERED=1
ENV SAM2_BUILD_CUDA=0
ENV MODEL_SIZE=${MODEL_SIZE}
# Install system requirements
RUN apt-get update && apt-get install -y --no-install-recommends \
ffmpeg \
libavutil-dev \
libavcodec-dev \
libavformat-dev \
libswscale-dev \
pkg-config \
build-essential \
libffi-dev
COPY setup.py .
COPY README.md .
RUN pip install --upgrade pip setuptools
RUN pip install -e ".[interactive-demo]"
# https://github.com/Kosinkadink/ComfyUI-VideoHelperSuite/issues/69#issuecomment-1826764707
RUN rm /opt/conda/bin/ffmpeg && ln -s /bin/ffmpeg /opt/conda/bin/ffmpeg
# Make app directory. This directory will host all files required for the
# backend and SAM 2 inference files.
RUN mkdir ${APP_ROOT}
# Copy backend server files
COPY demo/backend/server ${APP_ROOT}/server
# Copy SAM 2 inference files
COPY sam2 ${APP_ROOT}/server/sam2
# Download SAM 2.1 checkpoints
ADD https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_tiny.pt ${APP_ROOT}/checkpoints/sam2.1_hiera_tiny.pt
ADD https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_small.pt ${APP_ROOT}/checkpoints/sam2.1_hiera_small.pt
ADD https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_base_plus.pt ${APP_ROOT}/checkpoints/sam2.1_hiera_base_plus.pt
ADD https://dl.fbaipublicfiles.com/segment_anything_2/092824/sam2.1_hiera_large.pt ${APP_ROOT}/checkpoints/sam2.1_hiera_large.pt
WORKDIR ${APP_ROOT}/server
# https://pythonspeed.com/articles/gunicorn-in-docker/
CMD gunicorn --worker-tmp-dir /dev/shm \
--worker-class gthread app:app \
--log-level info \
--access-logfile /dev/stdout \
--log-file /dev/stderr \
--workers ${GUNICORN_WORKERS} \
--threads ${GUNICORN_THREADS} \
--bind 0.0.0.0:${GUNICORN_PORT} \
--timeout 60
sam2/checkpoints/download_ckpts.sh 0 → 100755
View file @ 75d93027
#!/bin/bash
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
# Use either wget or curl to download the checkpoints
if command -v wget &> /dev/null; then
CMD="wget"
elif command -v curl &> /dev/null; then
CMD="curl -L -O"
else
echo "Please install wget or curl to download the checkpoints."
exit 1
fi
# Define the URLs for SAM 2 checkpoints
# SAM2_BASE_URL="https://dl.fbaipublicfiles.com/segment_anything_2/072824"
# sam2_hiera_t_url="${SAM2_BASE_URL}/sam2_hiera_tiny.pt"
# sam2_hiera_s_url="${SAM2_BASE_URL}/sam2_hiera_small.pt"
# sam2_hiera_b_plus_url="${SAM2_BASE_URL}/sam2_hiera_base_plus.pt"
# sam2_hiera_l_url="${SAM2_BASE_URL}/sam2_hiera_large.pt"
# Download each of the four checkpoints using wget
# echo "Downloading sam2_hiera_tiny.pt checkpoint..."
# $CMD $sam2_hiera_t_url || { echo "Failed to download checkpoint from $sam2_hiera_t_url"; exit 1; }
# echo "Downloading sam2_hiera_small.pt checkpoint..."
# $CMD $sam2_hiera_s_url || { echo "Failed to download checkpoint from $sam2_hiera_s_url"; exit 1; }
# echo "Downloading sam2_hiera_base_plus.pt checkpoint..."
# $CMD $sam2_hiera_b_plus_url || { echo "Failed to download checkpoint from $sam2_hiera_b_plus_url"; exit 1; }
# echo "Downloading sam2_hiera_large.pt checkpoint..."
# $CMD $sam2_hiera_l_url || { echo "Failed to download checkpoint from $sam2_hiera_l_url"; exit 1; }
# Define the URLs for SAM 2.1 checkpoints
SAM2p1_BASE_URL="https://dl.fbaipublicfiles.com/segment_anything_2/092824"
sam2p1_hiera_t_url="${SAM2p1_BASE_URL}/sam2.1_hiera_tiny.pt"
sam2p1_hiera_s_url="${SAM2p1_BASE_URL}/sam2.1_hiera_small.pt"
sam2p1_hiera_b_plus_url="${SAM2p1_BASE_URL}/sam2.1_hiera_base_plus.pt"
sam2p1_hiera_l_url="${SAM2p1_BASE_URL}/sam2.1_hiera_large.pt"
# SAM 2.1 checkpoints
echo "Downloading sam2.1_hiera_tiny.pt checkpoint..."
$CMD $sam2p1_hiera_t_url || { echo "Failed to download checkpoint from $sam2p1_hiera_t_url"; exit 1; }
echo "Downloading sam2.1_hiera_small.pt checkpoint..."
$CMD $sam2p1_hiera_s_url || { echo "Failed to download checkpoint from $sam2p1_hiera_s_url"; exit 1; }
echo "Downloading sam2.1_hiera_base_plus.pt checkpoint..."
$CMD $sam2p1_hiera_b_plus_url || { echo "Failed to download checkpoint from $sam2p1_hiera_b_plus_url"; exit 1; }
echo "Downloading sam2.1_hiera_large.pt checkpoint..."
$CMD $sam2p1_hiera_l_url || { echo "Failed to download checkpoint from $sam2p1_hiera_l_url"; exit 1; }
echo "All checkpoints are downloaded successfully."
sam2/demo/.gitignore 0 → 100644
View file @ 75d93027
data/uploads
data/posters
sam2/demo/README.md 0 → 100644
View file @ 75d93027
# SAM 2 Demo
Welcome to the SAM 2 Demo! This project consists of a frontend built with React TypeScript and Vite and a backend service using Python Flask and Strawberry GraphQL. Both components can be run in Docker containers or locally on MPS (Metal Performance Shaders) or CPU. However, running the backend service on MPS or CPU devices may result in significantly slower performance (FPS).
## Prerequisites
Before you begin, ensure you have the following installed on your system:
- Docker and Docker Compose
- [OPTIONAL] Node.js and Yarn for running frontend locally
- [OPTIONAL] Anaconda for running backend locally
### Installing Docker
To install Docker, follow these steps:
1. Go to the [Docker website](https://www.docker.com/get-started)
2. Follow the installation instructions for your operating system.
### [OPTIONAL] Installing Node.js and Yarn
To install Node.js and Yarn, follow these steps:
1. Go to the [Node.js website](https://nodejs.org/en/download/).
2. Follow the installation instructions for your operating system.
3. Once Node.js is installed, open a terminal or command prompt and run the following command to install Yarn:
```
npm install -g yarn
```
### [OPTIONAL] Installing Anaconda
To install Anaconda, follow these steps:
1. Go to the [Anaconda website](https://www.anaconda.com/products/distribution).
2. Follow the installation instructions for your operating system.
## Quick Start
To get both the frontend and backend running quickly using Docker, you can use the following command:
```bash
docker compose up --build
```
> [!WARNING]
> On macOS, Docker containers only support running on CPU. MPS is not supported through Docker. If you want to run the demo backend service on MPS, you will need to run it locally (see "Running the Backend Locally" below).
This will build and start both services. You can access them at:
- **Frontend:** [http://localhost:7262](http://localhost:7262)
- **Backend:** [http://localhost:7263/graphql](http://localhost:7263/graphql)
## Running Backend with MPS Support
MPS (Metal Performance Shaders) is not supported with Docker. To use MPS, you need to run the backend on your local machine.
### Setting Up Your Environment
1. **Create Conda environment**
Create a new Conda environment for this project by running the following command or use your existing conda environment for SAM 2:
```
conda create --name sam2-demo python=3.10 --yes
```
This will create a new environment named `sam2-demo` with Python 3.10 as the interpreter.
2. **Activate the Conda environment:**
```bash
conda activate sam2-demo
```
3. **Install ffmpeg**
```bash
conda install -c conda-forge ffmpeg
```
4. **Install SAM 2 demo dependencies:**
Install project dependencies by running the following command in the SAM 2 checkout root directory:
```bash
pip install -e '.[interactive-demo]'
```
### Running the Backend Locally
Download the SAM 2 checkpoints:
```bash
(cd ./checkpoints && ./download_ckpts.sh)
```
Use the following command to start the backend with MPS support:
```bash
cd demo/backend/server/
```
```bash
PYTORCH_ENABLE_MPS_FALLBACK=1 \
APP_ROOT="$(pwd)/../../../" \
APP_URL=http://localhost:7263 \
MODEL_SIZE=base_plus \
DATA_PATH="$(pwd)/../../data" \
DEFAULT_VIDEO_PATH=gallery/05_default_juggle.mp4 \
gunicorn \
--worker-class gthread app:app \
--workers 1 \
--threads 2 \
--bind 0.0.0.0:7263 \
--timeout 60
```
Options for the `MODEL_SIZE` argument are "tiny", "small", "base_plus" (default), and "large".
> [!WARNING]
> Running the backend service on MPS devices can cause fatal crashes with the Gunicorn worker due to insufficient MPS memory. Try switching to CPU devices by setting the `SAM2_DEMO_FORCE_CPU_DEVICE=1` environment variable.
### Starting the Frontend
If you wish to run the frontend separately (useful for development), follow these steps:
1. **Navigate to demo frontend directory:**
```bash
cd demo/frontend
```
2. **Install dependencies:**
```bash
yarn install
```
3. **Start the development server:**
```bash
yarn dev --port 7262
```
This will start the frontend development server on [http://localhost:7262](http://localhost:7262).
## Docker Tips
- To rebuild the Docker containers (useful if you've made changes to the Dockerfile or dependencies):
```bash
docker compose up --build
```
- To stop the Docker containers:
```bash
docker compose down
```
## Contributing
Contributions are welcome! Please read our contributing guidelines to get started.
## License
See the LICENSE file for details.
---
By following these instructions, you should have a fully functional development environment for both the frontend and backend of the SAM 2 Demo. Happy coding!
sam2/demo/backend/server/app.py 0 → 100644
View file @ 75d93027
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
import logging
from typing import Any, Generator
from app_conf import (
GALLERY_PATH,
GALLERY_PREFIX,
POSTERS_PATH,
POSTERS_PREFIX,
UPLOADS_PATH,
UPLOADS_PREFIX,
)
from data.loader import preload_data
from data.schema import schema
from data.store import set_videos
from flask import Flask, make_response, Request, request, Response, send_from_directory
from flask_cors import CORS
from inference.data_types import PropagateDataResponse, PropagateInVideoRequest
from inference.multipart import MultipartResponseBuilder
from inference.predictor import InferenceAPI
from strawberry.flask.views import GraphQLView
logger = logging.getLogger(__name__)
app = Flask(__name__)
cors = CORS(app, supports_credentials=True)
videos = preload_data()
set_videos(videos)
inference_api = InferenceAPI()
@app.route("/healthy")
def healthy() -> Response:
return make_response("OK", 200)
@app.route(f"/{GALLERY_PREFIX}/<path:path>", methods=["GET"])
def send_gallery_video(path: str) -> Response:
try:
return send_from_directory(
GALLERY_PATH,
path,
)
except:
raise ValueError("resource not found")
@app.route(f"/{POSTERS_PREFIX}/<path:path>", methods=["GET"])
def send_poster_image(path: str) -> Response:
try:
return send_from_directory(
POSTERS_PATH,
path,
)
except:
raise ValueError("resource not found")
@app.route(f"/{UPLOADS_PREFIX}/<path:path>", methods=["GET"])
def send_uploaded_video(path: str):
try:
return send_from_directory(
UPLOADS_PATH,
path,
)
except:
raise ValueError("resource not found")
# TOOD: Protect route with ToS permission check
@app.route("/propagate_in_video", methods=["POST"])
def propagate_in_video() -> Response:
data = request.json
args = {
"session_id": data["session_id"],
"start_frame_index": data.get("start_frame_index", 0),
}
boundary = "frame"
frame = gen_track_with_mask_stream(boundary, **args)
return Response(frame, mimetype="multipart/x-savi-stream; boundary=" + boundary)
def gen_track_with_mask_stream(
boundary: str,
session_id: str,
start_frame_index: int,
) -> Generator[bytes, None, None]:
with inference_api.autocast_context():
request = PropagateInVideoRequest(
type="propagate_in_video",
session_id=session_id,
start_frame_index=start_frame_index,
)
for chunk in inference_api.propagate_in_video(request=request):
yield MultipartResponseBuilder.build(
boundary=boundary,
headers={
"Content-Type": "application/json; charset=utf-8",
"Frame-Current": "-1",
# Total frames minus the reference frame
"Frame-Total": "-1",
"Mask-Type": "RLE[]",
},
body=chunk.to_json().encode("UTF-8"),
).get_message()
class MyGraphQLView(GraphQLView):
def get_context(self, request: Request, response: Response) -> Any:
return {"inference_api": inference_api}
# Add GraphQL route to Flask app.
app.add_url_rule(
"/graphql",
view_func=MyGraphQLView.as_view(
"graphql_view",
schema=schema,
# Disable GET queries
# https://strawberry.rocks/docs/operations/deployment
# https://strawberry.rocks/docs/integrations/flask
allow_queries_via_get=False,
# Strawberry recently changed multipart request handling, which now
# requires enabling support explicitly for views.
# https://github.com/strawberry-graphql/strawberry/issues/3655
multipart_uploads_enabled=True,
),
)
if __name__ == "__main__":
app.run(host="0.0.0.0", port=5000)
sam2/demo/backend/server/app_conf.py 0 → 100644
View file @ 75d93027
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
import logging
import os
from pathlib import Path
logger = logging.getLogger(__name__)
APP_ROOT = os.getenv("APP_ROOT", "/opt/sam2")
API_URL = os.getenv("API_URL", "http://localhost:7263")
MODEL_SIZE = os.getenv("MODEL_SIZE", "base_plus")
logger.info(f"using model size {MODEL_SIZE}")
FFMPEG_NUM_THREADS = int(os.getenv("FFMPEG_NUM_THREADS", "1"))
# Path for all data used in API
DATA_PATH = Path(os.getenv("DATA_PATH", "/data"))
# Max duration an uploaded video can have in seconds. The default is 10
# seconds.
MAX_UPLOAD_VIDEO_DURATION = float(os.environ.get("MAX_UPLOAD_VIDEO_DURATION", "10"))
# If set, it will define which video is returned by the default video query for
# desktop
DEFAULT_VIDEO_PATH = os.getenv("DEFAULT_VIDEO_PATH")
# Prefix for gallery videos
GALLERY_PREFIX = "gallery"
# Path where all gallery videos are stored
GALLERY_PATH = DATA_PATH / GALLERY_PREFIX
# Prefix for uploaded videos
UPLOADS_PREFIX = "uploads"
# Path where all uploaded videos are stored
UPLOADS_PATH = DATA_PATH / UPLOADS_PREFIX
# Prefix for video posters (1st frame of video)
POSTERS_PREFIX = "posters"
# Path where all posters are stored
POSTERS_PATH = DATA_PATH / POSTERS_PREFIX
# Make sure any of those paths exist
os.makedirs(DATA_PATH, exist_ok=True)
os.makedirs(GALLERY_PATH, exist_ok=True)
os.makedirs(UPLOADS_PATH, exist_ok=True)
os.makedirs(POSTERS_PATH, exist_ok=True)
sam2/demo/backend/server/data/data_types.py 0 → 100644
View file @ 75d93027
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
from dataclasses import dataclass
from typing import Iterable, List, Optional
import strawberry
from app_conf import API_URL
from data.resolver import resolve_videos
from dataclasses_json import dataclass_json
from strawberry import relay
@strawberry.type
class Video(relay.Node):
"""Core type for video."""
code: relay.NodeID[str]
path: str
poster_path: Optional[str]
width: int
height: int
@strawberry.field
def url(self) -> str:
return f"{API_URL}/{self.path}"
@strawberry.field
def poster_url(self) -> str:
return f"{API_URL}/{self.poster_path}"
@classmethod
def resolve_nodes(
cls,
*,
info: relay.PageInfo,
node_ids: Iterable[str],
required: bool = False,
):
return resolve_videos(node_ids, required)
@strawberry.type
class RLEMask:
"""Core type for Onevision GraphQL RLE mask."""
size: List[int]
counts: str
order: str
@strawberry.type
class RLEMaskForObject:
"""Type for RLE mask associated with a specific object id."""
object_id: int
rle_mask: RLEMask
@strawberry.type
class RLEMaskListOnFrame:
"""Type for a list of object-associated RLE masks on a specific video frame."""
frame_index: int
rle_mask_list: List[RLEMaskForObject]
@strawberry.input
class StartSessionInput:
path: str
@strawberry.type
class StartSession:
session_id: str
@strawberry.input
class PingInput:
session_id: str
@strawberry.type
class Pong:
success: bool
@strawberry.input
class CloseSessionInput:
session_id: str
@strawberry.type
class CloseSession:
success: bool
@strawberry.input
class AddPointsInput:
session_id: str
frame_index: int
clear_old_points: bool
object_id: int
labels: List[int]
points: List[List[float]]
@strawberry.input
class ClearPointsInFrameInput:
session_id: str
frame_index: int
object_id: int
@strawberry.input
class ClearPointsInVideoInput:
session_id: str
@strawberry.type
class ClearPointsInVideo:
success: bool
@strawberry.input
class RemoveObjectInput:
session_id: str
object_id: int
@strawberry.input
class PropagateInVideoInput:
session_id: str
start_frame_index: int
@strawberry.input
class CancelPropagateInVideoInput:
session_id: str
@strawberry.type
class CancelPropagateInVideo:
success: bool
@strawberry.type
class SessionExpiration:
session_id: str
expiration_time: int
max_expiration_time: int
ttl: int
sam2/demo/backend/server/data/loader.py 0 → 100644
View file @ 75d93027
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
import os
import shutil
import subprocess
from glob import glob
from pathlib import Path
from typing import Dict, Optional
import imagesize
from app_conf import GALLERY_PATH, POSTERS_PATH, POSTERS_PREFIX
from data.data_types import Video
from tqdm import tqdm
def preload_data() -> Dict[str, Video]:
"""
Preload data including gallery videos and their posters.
"""
# Dictionaries for videos and datasets on the backend.
# Note that since Python 3.7, dictionaries preserve their insert order, so
# when looping over its `.values()`, elements inserted first also appear first.
# https://stackoverflow.com/questions/39980323/are-dictionaries-ordered-in-python-3-6
all_videos = {}
video_path_pattern = os.path.join(GALLERY_PATH, "**/*.mp4")
video_paths = glob(video_path_pattern, recursive=True)
for p in tqdm(video_paths):
video = get_video(p, GALLERY_PATH)
all_videos[video.code] = video
return all_videos
def get_video(
filepath: os.PathLike,
absolute_path: Path,
file_key: Optional[str] = None,
generate_poster: bool = True,
width: Optional[int] = None,
height: Optional[int] = None,
verbose: Optional[bool] = False,
) -> Video:
"""
Get video object given
"""
# Use absolute_path to include the parent directory in the video
video_path = os.path.relpath(filepath, absolute_path.parent)
poster_path = None
if generate_poster:
poster_id = os.path.splitext(os.path.basename(filepath))[0]
poster_filename = f"{str(poster_id)}.jpg"
poster_path = f"{POSTERS_PREFIX}/{poster_filename}"
# Extract the first frame from video
poster_output_path = os.path.join(POSTERS_PATH, poster_filename)
ffmpeg = shutil.which("ffmpeg")
subprocess.call(
[
ffmpeg,
"-y",
"-i",
str(filepath),
"-pix_fmt",
"yuv420p",
"-frames:v",
"1",
"-update",
"1",
"-strict",
"unofficial",
str(poster_output_path),
],
stdout=None if verbose else subprocess.DEVNULL,
stderr=None if verbose else subprocess.DEVNULL,
)
# Extract video width and height from poster. This is important to optimize
# rendering previews in the mosaic video preview.
width, height = imagesize.get(poster_output_path)
return Video(
code=video_path,
path=video_path if file_key is None else file_key,
poster_path=poster_path,
width=width,
height=height,
)
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