fitst commit
This commit is contained in:
7
.flake8
Executable file
7
.flake8
Executable file
@@ -0,0 +1,7 @@
|
||||
[flake8]
|
||||
ignore = W503, E203, E221, C901, C408, E741, C407, B017, F811, C101, EXE001, EXE002
|
||||
max-line-length = 100
|
||||
max-complexity = 18
|
||||
select = B,C,E,F,W,T4,B9
|
||||
per-file-ignores =
|
||||
**/__init__.py:F401,F403,E402
|
||||
42
.gitignore
vendored
Executable file
42
.gitignore
vendored
Executable file
@@ -0,0 +1,42 @@
|
||||
.nfs*
|
||||
|
||||
# compilation and distribution
|
||||
__pycache__
|
||||
_ext
|
||||
*.pyc
|
||||
*.pyd
|
||||
*.so
|
||||
*.dll
|
||||
*.egg-info/
|
||||
build/
|
||||
dist/
|
||||
wheels/
|
||||
|
||||
# pytorch/python/numpy formats
|
||||
*.pth
|
||||
*.pkl
|
||||
*.npy
|
||||
*.ts
|
||||
model_ts*.txt
|
||||
|
||||
# onnx models
|
||||
*.onnx
|
||||
|
||||
# ipython/jupyter notebooks
|
||||
**/.ipynb_checkpoints/
|
||||
|
||||
# Editor temporaries
|
||||
*.swn
|
||||
*.swo
|
||||
*.swp
|
||||
*~
|
||||
|
||||
# editor settings
|
||||
.idea
|
||||
.vscode
|
||||
_darcs
|
||||
|
||||
# demo
|
||||
**/node_modules
|
||||
yarn.lock
|
||||
package-lock.json
|
||||
80
CODE_OF_CONDUCT.md
Executable file
80
CODE_OF_CONDUCT.md
Executable file
@@ -0,0 +1,80 @@
|
||||
# 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
|
||||
31
CONTRIBUTING.md
Executable file
31
CONTRIBUTING.md
Executable file
@@ -0,0 +1,31 @@
|
||||
# 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 `linter.sh` script in the project's root directory. Linting requires `black==23.*`, `isort==5.12.0`, `flake8`, and `mypy`.
|
||||
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.
|
||||
201
LICENSE
Executable file
201
LICENSE
Executable file
@@ -0,0 +1,201 @@
|
||||
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.
|
||||
183
README.md
Executable file
183
README.md
Executable file
@@ -0,0 +1,183 @@
|
||||
## Latest updates -- SAM 2: Segment Anything in Images and Videos
|
||||
|
||||
Please check out our new release on [**Segment Anything Model 2 (SAM 2)**](https://github.com/facebookresearch/segment-anything-2).
|
||||
|
||||
* SAM 2 code: https://github.com/facebookresearch/segment-anything-2
|
||||
* SAM 2 demo: https://sam2.metademolab.com/
|
||||
* SAM 2 paper: https://arxiv.org/abs/2408.00714
|
||||
|
||||
|
||||
|
||||
**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.
|
||||
|
||||
# Segment Anything
|
||||
|
||||
**[Meta AI Research, FAIR](https://ai.facebook.com/research/)**
|
||||
|
||||
[Alexander Kirillov](https://alexander-kirillov.github.io/), [Eric Mintun](https://ericmintun.github.io/), [Nikhila Ravi](https://nikhilaravi.com/), [Hanzi Mao](https://hanzimao.me/), Chloe Rolland, Laura Gustafson, [Tete Xiao](https://tetexiao.com), [Spencer Whitehead](https://www.spencerwhitehead.com/), Alex Berg, Wan-Yen Lo, [Piotr Dollar](https://pdollar.github.io/), [Ross Girshick](https://www.rossgirshick.info/)
|
||||
|
||||
[[`Paper`](https://ai.facebook.com/research/publications/segment-anything/)] [[`Project`](https://segment-anything.com/)] [[`Demo`](https://segment-anything.com/demo)] [[`Dataset`](https://segment-anything.com/dataset/index.html)] [[`Blog`](https://ai.facebook.com/blog/segment-anything-foundation-model-image-segmentation/)] [[`BibTeX`](#citing-segment-anything)]
|
||||
|
||||
|
||||
|
||||
The **Segment Anything Model (SAM)** produces high quality object masks from input prompts such as points or boxes, and it can be used to generate masks for all objects in an image. It has been trained on a [dataset](https://segment-anything.com/dataset/index.html) of 11 million images and 1.1 billion masks, and has strong zero-shot performance on a variety of segmentation tasks.
|
||||
|
||||
<p float="left">
|
||||
<img src="assets/masks1.png?raw=true" width="37.25%" />
|
||||
<img src="assets/masks2.jpg?raw=true" width="61.5%" />
|
||||
</p>
|
||||
|
||||
## Installation
|
||||
|
||||
The code requires `python>=3.8`, as well as `pytorch>=1.7` and `torchvision>=0.8`. Please follow the instructions [here](https://pytorch.org/get-started/locally/) to install both PyTorch and TorchVision dependencies. Installing both PyTorch and TorchVision with CUDA support is strongly recommended.
|
||||
|
||||
Install Segment Anything:
|
||||
|
||||
```
|
||||
pip install git+https://github.com/facebookresearch/segment-anything.git
|
||||
```
|
||||
|
||||
or clone the repository locally and install with
|
||||
|
||||
```
|
||||
git clone git@github.com:facebookresearch/segment-anything.git
|
||||
cd segment-anything; pip install -e .
|
||||
```
|
||||
|
||||
The following optional dependencies are necessary for mask post-processing, saving masks in COCO format, the example notebooks, and exporting the model in ONNX format. `jupyter` is also required to run the example notebooks.
|
||||
|
||||
```
|
||||
pip install opencv-python pycocotools matplotlib onnxruntime onnx
|
||||
```
|
||||
|
||||
## <a name="GettingStarted"></a>Getting Started
|
||||
|
||||
First download a [model checkpoint](#model-checkpoints). Then the model can be used in just a few lines to get masks from a given prompt:
|
||||
|
||||
```
|
||||
from segment_anything import SamPredictor, sam_model_registry
|
||||
sam = sam_model_registry["<model_type>"](checkpoint="<path/to/checkpoint>")
|
||||
predictor = SamPredictor(sam)
|
||||
predictor.set_image(<your_image>)
|
||||
masks, _, _ = predictor.predict(<input_prompts>)
|
||||
```
|
||||
|
||||
or generate masks for an entire image:
|
||||
|
||||
```
|
||||
from segment_anything import SamAutomaticMaskGenerator, sam_model_registry
|
||||
sam = sam_model_registry["<model_type>"](checkpoint="<path/to/checkpoint>")
|
||||
mask_generator = SamAutomaticMaskGenerator(sam)
|
||||
masks = mask_generator.generate(<your_image>)
|
||||
```
|
||||
|
||||
Additionally, masks can be generated for images from the command line:
|
||||
|
||||
```
|
||||
python scripts/amg.py --checkpoint <path/to/checkpoint> --model-type <model_type> --input <image_or_folder> --output <path/to/output>
|
||||
```
|
||||
|
||||
See the examples notebooks on [using SAM with prompts](/notebooks/predictor_example.ipynb) and [automatically generating masks](/notebooks/automatic_mask_generator_example.ipynb) for more details.
|
||||
|
||||
<p float="left">
|
||||
<img src="assets/notebook1.png?raw=true" width="49.1%" />
|
||||
<img src="assets/notebook2.png?raw=true" width="48.9%" />
|
||||
</p>
|
||||
|
||||
## ONNX Export
|
||||
|
||||
SAM's lightweight mask decoder can be exported to ONNX format so that it can be run in any environment that supports ONNX runtime, such as in-browser as showcased in the [demo](https://segment-anything.com/demo). Export the model with
|
||||
|
||||
```
|
||||
python scripts/export_onnx_model.py --checkpoint <path/to/checkpoint> --model-type <model_type> --output <path/to/output>
|
||||
```
|
||||
|
||||
See the [example notebook](https://github.com/facebookresearch/segment-anything/blob/main/notebooks/onnx_model_example.ipynb) for details on how to combine image preprocessing via SAM's backbone with mask prediction using the ONNX model. It is recommended to use the latest stable version of PyTorch for ONNX export.
|
||||
|
||||
### Web demo
|
||||
|
||||
The `demo/` folder has a simple one page React app which shows how to run mask prediction with the exported ONNX model in a web browser with multithreading. Please see [`demo/README.md`](https://github.com/facebookresearch/segment-anything/blob/main/demo/README.md) for more details.
|
||||
|
||||
## <a name="Models"></a>Model Checkpoints
|
||||
|
||||
Three model versions of the model are available with different backbone sizes. These models can be instantiated by running
|
||||
|
||||
```
|
||||
from segment_anything import sam_model_registry
|
||||
sam = sam_model_registry["<model_type>"](checkpoint="<path/to/checkpoint>")
|
||||
```
|
||||
|
||||
Click the links below to download the checkpoint for the corresponding model type.
|
||||
|
||||
- **`default` or `vit_h`: [ViT-H SAM model.](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth)**
|
||||
- `vit_l`: [ViT-L SAM model.](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth)
|
||||
- `vit_b`: [ViT-B SAM model.](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth)
|
||||
|
||||
## Dataset
|
||||
|
||||
See [here](https://ai.facebook.com/datasets/segment-anything/) for an overview of the datastet. The dataset can be downloaded [here](https://ai.facebook.com/datasets/segment-anything-downloads/). By downloading the datasets you agree that you have read and accepted the terms of the SA-1B Dataset Research License.
|
||||
|
||||
We save masks per image as a json file. It can be loaded as a dictionary in python in the below format.
|
||||
|
||||
```python
|
||||
{
|
||||
"image" : image_info,
|
||||
"annotations" : [annotation],
|
||||
}
|
||||
|
||||
image_info {
|
||||
"image_id" : int, # Image id
|
||||
"width" : int, # Image width
|
||||
"height" : int, # Image height
|
||||
"file_name" : str, # Image filename
|
||||
}
|
||||
|
||||
annotation {
|
||||
"id" : int, # Annotation id
|
||||
"segmentation" : dict, # Mask saved in COCO RLE format.
|
||||
"bbox" : [x, y, w, h], # The box around the mask, in XYWH format
|
||||
"area" : int, # The area in pixels of the mask
|
||||
"predicted_iou" : float, # The model's own prediction of the mask's quality
|
||||
"stability_score" : float, # A measure of the mask's quality
|
||||
"crop_box" : [x, y, w, h], # The crop of the image used to generate the mask, in XYWH format
|
||||
"point_coords" : [[x, y]], # The point coordinates input to the model to generate the mask
|
||||
}
|
||||
```
|
||||
|
||||
Image ids can be found in sa_images_ids.txt which can be downloaded using the above [link](https://ai.facebook.com/datasets/segment-anything-downloads/) as well.
|
||||
|
||||
To decode a mask in COCO RLE format into binary:
|
||||
|
||||
```
|
||||
from pycocotools import mask as mask_utils
|
||||
mask = mask_utils.decode(annotation["segmentation"])
|
||||
```
|
||||
|
||||
See [here](https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocotools/mask.py) for more instructions to manipulate masks stored in RLE format.
|
||||
|
||||
## License
|
||||
|
||||
The model is licensed under the [Apache 2.0 license](LICENSE).
|
||||
|
||||
## Contributing
|
||||
|
||||
See [contributing](CONTRIBUTING.md) and the [code of conduct](CODE_OF_CONDUCT.md).
|
||||
|
||||
## Contributors
|
||||
|
||||
The Segment Anything project was made possible with the help of many contributors (alphabetical):
|
||||
|
||||
Aaron Adcock, Vaibhav Aggarwal, Morteza Behrooz, Cheng-Yang Fu, Ashley Gabriel, Ahuva Goldstand, Allen Goodman, Sumanth Gurram, Jiabo Hu, Somya Jain, Devansh Kukreja, Robert Kuo, Joshua Lane, Yanghao Li, Lilian Luong, Jitendra Malik, Mallika Malhotra, William Ngan, Omkar Parkhi, Nikhil Raina, Dirk Rowe, Neil Sejoor, Vanessa Stark, Bala Varadarajan, Bram Wasti, Zachary Winstrom
|
||||
|
||||
## Citing Segment Anything
|
||||
|
||||
If you use SAM or SA-1B in your research, please use the following BibTeX entry.
|
||||
|
||||
```
|
||||
@article{kirillov2023segany,
|
||||
title={Segment Anything},
|
||||
author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C. and Lo, Wan-Yen and Doll{\'a}r, Piotr and Girshick, Ross},
|
||||
journal={arXiv:2304.02643},
|
||||
year={2023}
|
||||
}
|
||||
```
|
||||
BIN
assets/masks1.png
Executable file
BIN
assets/masks1.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 3.5 MiB |
BIN
assets/masks2.jpg
Executable file
BIN
assets/masks2.jpg
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 130 KiB |
BIN
assets/minidemo.gif
Executable file
BIN
assets/minidemo.gif
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 1.9 MiB |
BIN
assets/model_diagram.png
Executable file
BIN
assets/model_diagram.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 568 KiB |
BIN
assets/notebook1.png
Executable file
BIN
assets/notebook1.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 854 KiB |
BIN
assets/notebook2.png
Executable file
BIN
assets/notebook2.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 1.2 MiB |
126
demo/README.md
Executable file
126
demo/README.md
Executable file
@@ -0,0 +1,126 @@
|
||||
## Segment Anything Simple Web demo
|
||||
|
||||
This **front-end only** React based web demo shows how to load a fixed image and corresponding `.npy` file of the SAM image embedding, and run the SAM ONNX model in the browser using Web Assembly with mulithreading enabled by `SharedArrayBuffer`, Web Worker, and SIMD128.
|
||||
|
||||
<img src="https://github.com/facebookresearch/segment-anything/raw/main/assets/minidemo.gif" width="500"/>
|
||||
|
||||
## Run the app
|
||||
|
||||
Install Yarn
|
||||
|
||||
```
|
||||
npm install --g yarn
|
||||
```
|
||||
|
||||
Build and run:
|
||||
|
||||
```
|
||||
yarn && yarn start
|
||||
```
|
||||
|
||||
Navigate to [`http://localhost:8081/`](http://localhost:8081/)
|
||||
|
||||
Move your cursor around to see the mask prediction update in real time.
|
||||
|
||||
## Export the image embedding
|
||||
|
||||
In the [ONNX Model Example notebook](https://github.com/facebookresearch/segment-anything/blob/main/notebooks/onnx_model_example.ipynb) upload the image of your choice and generate and save corresponding embedding.
|
||||
|
||||
Initialize the predictor:
|
||||
|
||||
```python
|
||||
checkpoint = "sam_vit_h_4b8939.pth"
|
||||
model_type = "vit_h"
|
||||
sam = sam_model_registry[model_type](checkpoint=checkpoint)
|
||||
sam.to(device='cuda')
|
||||
predictor = SamPredictor(sam)
|
||||
```
|
||||
|
||||
Set the new image and export the embedding:
|
||||
|
||||
```
|
||||
image = cv2.imread('src/assets/dogs.jpg')
|
||||
predictor.set_image(image)
|
||||
image_embedding = predictor.get_image_embedding().cpu().numpy()
|
||||
np.save("dogs_embedding.npy", image_embedding)
|
||||
```
|
||||
|
||||
Save the new image and embedding in `src/assets/data`.
|
||||
|
||||
## Export the ONNX model
|
||||
|
||||
You also need to export the quantized ONNX model from the [ONNX Model Example notebook](https://github.com/facebookresearch/segment-anything/blob/main/notebooks/onnx_model_example.ipynb).
|
||||
|
||||
Run the cell in the notebook which saves the `sam_onnx_quantized_example.onnx` file, download it and copy it to the path `/model/sam_onnx_quantized_example.onnx`.
|
||||
|
||||
Here is a snippet of the export/quantization code:
|
||||
|
||||
```
|
||||
onnx_model_path = "sam_onnx_example.onnx"
|
||||
onnx_model_quantized_path = "sam_onnx_quantized_example.onnx"
|
||||
quantize_dynamic(
|
||||
model_input=onnx_model_path,
|
||||
model_output=onnx_model_quantized_path,
|
||||
optimize_model=True,
|
||||
per_channel=False,
|
||||
reduce_range=False,
|
||||
weight_type=QuantType.QUInt8,
|
||||
)
|
||||
```
|
||||
|
||||
**NOTE: if you change the ONNX model by using a new checkpoint you need to also re-export the embedding.**
|
||||
|
||||
## Update the image, embedding, model in the app
|
||||
|
||||
Update the following file paths at the top of`App.tsx`:
|
||||
|
||||
```py
|
||||
const IMAGE_PATH = "/assets/data/dogs.jpg";
|
||||
const IMAGE_EMBEDDING = "/assets/data/dogs_embedding.npy";
|
||||
const MODEL_DIR = "/model/sam_onnx_quantized_example.onnx";
|
||||
```
|
||||
|
||||
## ONNX multithreading with SharedArrayBuffer
|
||||
|
||||
To use multithreading, the appropriate headers need to be set to create a cross origin isolation state which will enable use of `SharedArrayBuffer` (see this [blog post](https://cloudblogs.microsoft.com/opensource/2021/09/02/onnx-runtime-web-running-your-machine-learning-model-in-browser/) for more details)
|
||||
|
||||
The headers below are set in `configs/webpack/dev.js`:
|
||||
|
||||
```js
|
||||
headers: {
|
||||
"Cross-Origin-Opener-Policy": "same-origin",
|
||||
"Cross-Origin-Embedder-Policy": "credentialless",
|
||||
}
|
||||
```
|
||||
|
||||
## Structure of the app
|
||||
|
||||
**`App.tsx`**
|
||||
|
||||
- Initializes ONNX model
|
||||
- Loads image embedding and image
|
||||
- Runs the ONNX model based on input prompts
|
||||
|
||||
**`Stage.tsx`**
|
||||
|
||||
- Handles mouse move interaction to update the ONNX model prompt
|
||||
|
||||
**`Tool.tsx`**
|
||||
|
||||
- Renders the image and the mask prediction
|
||||
|
||||
**`helpers/maskUtils.tsx`**
|
||||
|
||||
- Conversion of ONNX model output from array to an HTMLImageElement
|
||||
|
||||
**`helpers/onnxModelAPI.tsx`**
|
||||
|
||||
- Formats the inputs for the ONNX model
|
||||
|
||||
**`helpers/scaleHelper.tsx`**
|
||||
|
||||
- Handles image scaling logic for SAM (longest size 1024)
|
||||
|
||||
**`hooks/`**
|
||||
|
||||
- Handle shared state for the app
|
||||
84
demo/configs/webpack/common.js
Executable file
84
demo/configs/webpack/common.js
Executable file
@@ -0,0 +1,84 @@
|
||||
// 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.
|
||||
|
||||
const { resolve } = require("path");
|
||||
const HtmlWebpackPlugin = require("html-webpack-plugin");
|
||||
const FriendlyErrorsWebpackPlugin = require("friendly-errors-webpack-plugin");
|
||||
const CopyPlugin = require("copy-webpack-plugin");
|
||||
const webpack = require("webpack");
|
||||
|
||||
module.exports = {
|
||||
entry: "./src/index.tsx",
|
||||
resolve: {
|
||||
extensions: [".js", ".jsx", ".ts", ".tsx"],
|
||||
},
|
||||
output: {
|
||||
path: resolve(__dirname, "dist"),
|
||||
},
|
||||
module: {
|
||||
rules: [
|
||||
{
|
||||
test: /\.mjs$/,
|
||||
include: /node_modules/,
|
||||
type: "javascript/auto",
|
||||
resolve: {
|
||||
fullySpecified: false,
|
||||
},
|
||||
},
|
||||
{
|
||||
test: [/\.jsx?$/, /\.tsx?$/],
|
||||
use: ["ts-loader"],
|
||||
exclude: /node_modules/,
|
||||
},
|
||||
{
|
||||
test: /\.css$/,
|
||||
use: ["style-loader", "css-loader"],
|
||||
},
|
||||
{
|
||||
test: /\.(scss|sass)$/,
|
||||
use: ["style-loader", "css-loader", "postcss-loader"],
|
||||
},
|
||||
{
|
||||
test: /\.(jpe?g|png|gif|svg)$/i,
|
||||
use: [
|
||||
"file-loader?hash=sha512&digest=hex&name=img/[contenthash].[ext]",
|
||||
"image-webpack-loader?bypassOnDebug&optipng.optimizationLevel=7&gifsicle.interlaced=false",
|
||||
],
|
||||
},
|
||||
{
|
||||
test: /\.(woff|woff2|ttf)$/,
|
||||
use: {
|
||||
loader: "url-loader",
|
||||
},
|
||||
},
|
||||
],
|
||||
},
|
||||
plugins: [
|
||||
new CopyPlugin({
|
||||
patterns: [
|
||||
{
|
||||
from: "node_modules/onnxruntime-web/dist/*.wasm",
|
||||
to: "[name][ext]",
|
||||
},
|
||||
{
|
||||
from: "model",
|
||||
to: "model",
|
||||
},
|
||||
{
|
||||
from: "src/assets",
|
||||
to: "assets",
|
||||
},
|
||||
],
|
||||
}),
|
||||
new HtmlWebpackPlugin({
|
||||
template: "./src/assets/index.html",
|
||||
}),
|
||||
new FriendlyErrorsWebpackPlugin(),
|
||||
new webpack.ProvidePlugin({
|
||||
process: "process/browser",
|
||||
}),
|
||||
],
|
||||
};
|
||||
25
demo/configs/webpack/dev.js
Executable file
25
demo/configs/webpack/dev.js
Executable file
@@ -0,0 +1,25 @@
|
||||
// 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.
|
||||
|
||||
// development config
|
||||
const { merge } = require("webpack-merge");
|
||||
const commonConfig = require("./common");
|
||||
|
||||
module.exports = merge(commonConfig, {
|
||||
mode: "development",
|
||||
devServer: {
|
||||
hot: true, // enable HMR on the server
|
||||
open: true,
|
||||
// These headers enable the cross origin isolation state
|
||||
// needed to enable use of SharedArrayBuffer for ONNX
|
||||
// multithreading.
|
||||
headers: {
|
||||
"Cross-Origin-Opener-Policy": "same-origin",
|
||||
"Cross-Origin-Embedder-Policy": "credentialless",
|
||||
},
|
||||
},
|
||||
devtool: "cheap-module-source-map",
|
||||
});
|
||||
22
demo/configs/webpack/prod.js
Executable file
22
demo/configs/webpack/prod.js
Executable file
@@ -0,0 +1,22 @@
|
||||
// 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.
|
||||
|
||||
// production config
|
||||
const { merge } = require("webpack-merge");
|
||||
const { resolve } = require("path");
|
||||
const Dotenv = require("dotenv-webpack");
|
||||
const commonConfig = require("./common");
|
||||
|
||||
module.exports = merge(commonConfig, {
|
||||
mode: "production",
|
||||
output: {
|
||||
filename: "js/bundle.[contenthash].min.js",
|
||||
path: resolve(__dirname, "../../dist"),
|
||||
publicPath: "/",
|
||||
},
|
||||
devtool: "source-map",
|
||||
plugins: [new Dotenv()],
|
||||
});
|
||||
65
demo/package.json
Executable file
65
demo/package.json
Executable file
@@ -0,0 +1,65 @@
|
||||
{
|
||||
"engines": {
|
||||
"node": ">=20.0.0"
|
||||
},
|
||||
"name": "segment-anything-mini-demo",
|
||||
"version": "0.1.0",
|
||||
"license": "MIT",
|
||||
"scripts": {
|
||||
"build": "yarn run clean-dist && webpack --config=configs/webpack/prod.js && mv dist/*.wasm dist/js",
|
||||
"clean-dist": "rimraf dist/*",
|
||||
"lint": "eslint './src/**/*.{js,ts,tsx}' --quiet",
|
||||
"start": "yarn run start-dev",
|
||||
"test": "yarn run start-model-test",
|
||||
"start-dev": "webpack serve --config=configs/webpack/dev.js"
|
||||
},
|
||||
"devDependencies": {
|
||||
"@babel/core": "^7.18.13",
|
||||
"@babel/preset-env": "^7.18.10",
|
||||
"@babel/preset-react": "^7.18.6",
|
||||
"@babel/preset-typescript": "^7.18.6",
|
||||
"@pmmmwh/react-refresh-webpack-plugin": "^0.5.7",
|
||||
"@testing-library/react": "^13.3.0",
|
||||
"@types/node": "^18.7.13",
|
||||
"@types/react": "^18.0.17",
|
||||
"@types/react-dom": "^18.0.6",
|
||||
"@types/underscore": "^1.11.4",
|
||||
"@typescript-eslint/eslint-plugin": "^5.35.1",
|
||||
"@typescript-eslint/parser": "^5.35.1",
|
||||
"babel-loader": "^8.2.5",
|
||||
"copy-webpack-plugin": "^11.0.0",
|
||||
"css-loader": "^6.7.1",
|
||||
"dotenv": "^16.0.2",
|
||||
"dotenv-webpack": "^8.0.1",
|
||||
"eslint": "^8.22.0",
|
||||
"eslint-plugin-react": "^7.31.0",
|
||||
"file-loader": "^6.2.0",
|
||||
"fork-ts-checker-webpack-plugin": "^7.2.13",
|
||||
"friendly-errors-webpack-plugin": "^1.7.0",
|
||||
"html-webpack-plugin": "^5.5.0",
|
||||
"image-webpack-loader": "^8.1.0",
|
||||
"postcss-loader": "^7.0.1",
|
||||
"postcss-preset-env": "^7.8.0",
|
||||
"process": "^0.11.10",
|
||||
"rimraf": "^3.0.2",
|
||||
"sass": "^1.54.5",
|
||||
"sass-loader": "^13.0.2",
|
||||
"style-loader": "^3.3.1",
|
||||
"tailwindcss": "^3.1.8",
|
||||
"ts-loader": "^9.3.1",
|
||||
"typescript": "^4.8.2",
|
||||
"webpack": "^5.74.0",
|
||||
"webpack-cli": "^4.10.0",
|
||||
"webpack-dev-server": "^4.10.0",
|
||||
"webpack-dotenv-plugin": "^2.1.0",
|
||||
"webpack-merge": "^5.8.0"
|
||||
},
|
||||
"dependencies": {
|
||||
"npyjs": "^0.4.0",
|
||||
"onnxruntime-web": "^1.14.0",
|
||||
"react": "^18.2.0",
|
||||
"react-dom": "^18.2.0",
|
||||
"underscore": "^1.13.6",
|
||||
"react-refresh": "^0.14.0"
|
||||
}
|
||||
}
|
||||
10
demo/postcss.config.js
Executable file
10
demo/postcss.config.js
Executable file
@@ -0,0 +1,10 @@
|
||||
// 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.
|
||||
|
||||
const tailwindcss = require("tailwindcss");
|
||||
module.exports = {
|
||||
plugins: ["postcss-preset-env", 'tailwindcss/nesting', tailwindcss],
|
||||
};
|
||||
130
demo/src/App.tsx
Executable file
130
demo/src/App.tsx
Executable file
@@ -0,0 +1,130 @@
|
||||
// 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 { InferenceSession, Tensor } from "onnxruntime-web";
|
||||
import React, { useContext, useEffect, useState } from "react";
|
||||
import "./assets/scss/App.scss";
|
||||
import { handleImageScale } from "./components/helpers/scaleHelper";
|
||||
import { modelScaleProps } from "./components/helpers/Interfaces";
|
||||
import { onnxMaskToImage } from "./components/helpers/maskUtils";
|
||||
import { modelData } from "./components/helpers/onnxModelAPI";
|
||||
import Stage from "./components/Stage";
|
||||
import AppContext from "./components/hooks/createContext";
|
||||
const ort = require("onnxruntime-web");
|
||||
/* @ts-ignore */
|
||||
import npyjs from "npyjs";
|
||||
|
||||
// Define image, embedding and model paths
|
||||
const IMAGE_PATH = "/assets/data/dogs.jpg";
|
||||
const IMAGE_EMBEDDING = "/assets/data/dogs_embedding.npy";
|
||||
const MODEL_DIR = "/model/sam_onnx_quantized_example.onnx";
|
||||
|
||||
const App = () => {
|
||||
const {
|
||||
clicks: [clicks],
|
||||
image: [, setImage],
|
||||
maskImg: [, setMaskImg],
|
||||
} = useContext(AppContext)!;
|
||||
const [model, setModel] = useState<InferenceSession | null>(null); // ONNX model
|
||||
const [tensor, setTensor] = useState<Tensor | null>(null); // Image embedding tensor
|
||||
|
||||
// The ONNX model expects the input to be rescaled to 1024.
|
||||
// The modelScale state variable keeps track of the scale values.
|
||||
const [modelScale, setModelScale] = useState<modelScaleProps | null>(null);
|
||||
|
||||
// Initialize the ONNX model. load the image, and load the SAM
|
||||
// pre-computed image embedding
|
||||
useEffect(() => {
|
||||
// Initialize the ONNX model
|
||||
const initModel = async () => {
|
||||
try {
|
||||
if (MODEL_DIR === undefined) return;
|
||||
const URL: string = MODEL_DIR;
|
||||
const model = await InferenceSession.create(URL);
|
||||
setModel(model);
|
||||
} catch (e) {
|
||||
console.log(e);
|
||||
}
|
||||
};
|
||||
initModel();
|
||||
|
||||
// Load the image
|
||||
const url = new URL(IMAGE_PATH, location.origin);
|
||||
loadImage(url);
|
||||
|
||||
// Load the Segment Anything pre-computed embedding
|
||||
Promise.resolve(loadNpyTensor(IMAGE_EMBEDDING, "float32")).then(
|
||||
(embedding) => setTensor(embedding)
|
||||
);
|
||||
}, []);
|
||||
|
||||
const loadImage = async (url: URL) => {
|
||||
try {
|
||||
const img = new Image();
|
||||
img.src = url.href;
|
||||
img.onload = () => {
|
||||
const { height, width, samScale } = handleImageScale(img);
|
||||
setModelScale({
|
||||
height: height, // original image height
|
||||
width: width, // original image width
|
||||
samScale: samScale, // scaling factor for image which has been resized to longest side 1024
|
||||
});
|
||||
img.width = width;
|
||||
img.height = height;
|
||||
setImage(img);
|
||||
};
|
||||
} catch (error) {
|
||||
console.log(error);
|
||||
}
|
||||
};
|
||||
|
||||
// Decode a Numpy file into a tensor.
|
||||
const loadNpyTensor = async (tensorFile: string, dType: string) => {
|
||||
let npLoader = new npyjs();
|
||||
const npArray = await npLoader.load(tensorFile);
|
||||
const tensor = new ort.Tensor(dType, npArray.data, npArray.shape);
|
||||
return tensor;
|
||||
};
|
||||
|
||||
// Run the ONNX model every time clicks has changed
|
||||
useEffect(() => {
|
||||
runONNX();
|
||||
}, [clicks]);
|
||||
|
||||
const runONNX = async () => {
|
||||
try {
|
||||
if (
|
||||
model === null ||
|
||||
clicks === null ||
|
||||
tensor === null ||
|
||||
modelScale === null
|
||||
)
|
||||
return;
|
||||
else {
|
||||
// Preapre the model input in the correct format for SAM.
|
||||
// The modelData function is from onnxModelAPI.tsx.
|
||||
const feeds = modelData({
|
||||
clicks,
|
||||
tensor,
|
||||
modelScale,
|
||||
});
|
||||
if (feeds === undefined) return;
|
||||
// Run the SAM ONNX model with the feeds returned from modelData()
|
||||
const results = await model.run(feeds);
|
||||
const output = results[model.outputNames[0]];
|
||||
// The predicted mask returned from the ONNX model is an array which is
|
||||
// rendered as an HTML image using onnxMaskToImage() from maskUtils.tsx.
|
||||
setMaskImg(onnxMaskToImage(output.data, output.dims[2], output.dims[3]));
|
||||
}
|
||||
} catch (e) {
|
||||
console.log(e);
|
||||
}
|
||||
};
|
||||
|
||||
return <Stage />;
|
||||
};
|
||||
|
||||
export default App;
|
||||
BIN
demo/src/assets/data/dogs.jpg
Executable file
BIN
demo/src/assets/data/dogs.jpg
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 438 KiB |
18
demo/src/assets/index.html
Executable file
18
demo/src/assets/index.html
Executable file
@@ -0,0 +1,18 @@
|
||||
<!DOCTYPE html>
|
||||
<html lang="en" dir="ltr" prefix="og: https://ogp.me/ns#" class="w-full h-full">
|
||||
<head>
|
||||
<meta charset="utf-8" />
|
||||
<meta
|
||||
name="viewport"
|
||||
content="width=device-width, initial-scale=1, shrink-to-fit=no"
|
||||
/>
|
||||
<title>Segment Anything Demo</title>
|
||||
|
||||
<!-- Meta Tags -->
|
||||
<meta property="og:type" content="website" />
|
||||
<meta property="og:title" content="Segment Anything Demo" />
|
||||
</head>
|
||||
<body class="w-full h-full">
|
||||
<div id="root" class="w-full h-full"></div>
|
||||
</body>
|
||||
</html>
|
||||
3
demo/src/assets/scss/App.scss
Executable file
3
demo/src/assets/scss/App.scss
Executable file
@@ -0,0 +1,3 @@
|
||||
@tailwind base;
|
||||
@tailwind components;
|
||||
@tailwind utilities;
|
||||
49
demo/src/components/Stage.tsx
Executable file
49
demo/src/components/Stage.tsx
Executable file
@@ -0,0 +1,49 @@
|
||||
// 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 React, { useContext } from "react";
|
||||
import * as _ from "underscore";
|
||||
import Tool from "./Tool";
|
||||
import { modelInputProps } from "./helpers/Interfaces";
|
||||
import AppContext from "./hooks/createContext";
|
||||
|
||||
const Stage = () => {
|
||||
const {
|
||||
clicks: [, setClicks],
|
||||
image: [image],
|
||||
} = useContext(AppContext)!;
|
||||
|
||||
const getClick = (x: number, y: number): modelInputProps => {
|
||||
const clickType = 1;
|
||||
return { x, y, clickType };
|
||||
};
|
||||
|
||||
// Get mouse position and scale the (x, y) coordinates back to the natural
|
||||
// scale of the image. Update the state of clicks with setClicks to trigger
|
||||
// the ONNX model to run and generate a new mask via a useEffect in App.tsx
|
||||
const handleMouseMove = _.throttle((e: any) => {
|
||||
let el = e.nativeEvent.target;
|
||||
const rect = el.getBoundingClientRect();
|
||||
let x = e.clientX - rect.left;
|
||||
let y = e.clientY - rect.top;
|
||||
const imageScale = image ? image.width / el.offsetWidth : 1;
|
||||
x *= imageScale;
|
||||
y *= imageScale;
|
||||
const click = getClick(x, y);
|
||||
if (click) setClicks([click]);
|
||||
}, 15);
|
||||
|
||||
const flexCenterClasses = "flex items-center justify-center";
|
||||
return (
|
||||
<div className={`${flexCenterClasses} w-full h-full`}>
|
||||
<div className={`${flexCenterClasses} relative w-[90%] h-[90%]`}>
|
||||
<Tool handleMouseMove={handleMouseMove} />
|
||||
</div>
|
||||
</div>
|
||||
);
|
||||
};
|
||||
|
||||
export default Stage;
|
||||
73
demo/src/components/Tool.tsx
Executable file
73
demo/src/components/Tool.tsx
Executable file
@@ -0,0 +1,73 @@
|
||||
// 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 React, { useContext, useEffect, useState } from "react";
|
||||
import AppContext from "./hooks/createContext";
|
||||
import { ToolProps } from "./helpers/Interfaces";
|
||||
import * as _ from "underscore";
|
||||
|
||||
const Tool = ({ handleMouseMove }: ToolProps) => {
|
||||
const {
|
||||
image: [image],
|
||||
maskImg: [maskImg, setMaskImg],
|
||||
} = useContext(AppContext)!;
|
||||
|
||||
// Determine if we should shrink or grow the images to match the
|
||||
// width or the height of the page and setup a ResizeObserver to
|
||||
// monitor changes in the size of the page
|
||||
const [shouldFitToWidth, setShouldFitToWidth] = useState(true);
|
||||
const bodyEl = document.body;
|
||||
const fitToPage = () => {
|
||||
if (!image) return;
|
||||
const imageAspectRatio = image.width / image.height;
|
||||
const screenAspectRatio = window.innerWidth / window.innerHeight;
|
||||
setShouldFitToWidth(imageAspectRatio > screenAspectRatio);
|
||||
};
|
||||
const resizeObserver = new ResizeObserver((entries) => {
|
||||
for (const entry of entries) {
|
||||
if (entry.target === bodyEl) {
|
||||
fitToPage();
|
||||
}
|
||||
}
|
||||
});
|
||||
useEffect(() => {
|
||||
fitToPage();
|
||||
resizeObserver.observe(bodyEl);
|
||||
return () => {
|
||||
resizeObserver.unobserve(bodyEl);
|
||||
};
|
||||
}, [image]);
|
||||
|
||||
const imageClasses = "";
|
||||
const maskImageClasses = `absolute opacity-40 pointer-events-none`;
|
||||
|
||||
// Render the image and the predicted mask image on top
|
||||
return (
|
||||
<>
|
||||
{image && (
|
||||
<img
|
||||
onMouseMove={handleMouseMove}
|
||||
onMouseOut={() => _.defer(() => setMaskImg(null))}
|
||||
onTouchStart={handleMouseMove}
|
||||
src={image.src}
|
||||
className={`${
|
||||
shouldFitToWidth ? "w-full" : "h-full"
|
||||
} ${imageClasses}`}
|
||||
></img>
|
||||
)}
|
||||
{maskImg && (
|
||||
<img
|
||||
src={maskImg.src}
|
||||
className={`${
|
||||
shouldFitToWidth ? "w-full" : "h-full"
|
||||
} ${maskImageClasses}`}
|
||||
></img>
|
||||
)}
|
||||
</>
|
||||
);
|
||||
};
|
||||
|
||||
export default Tool;
|
||||
29
demo/src/components/helpers/Interfaces.tsx
Executable file
29
demo/src/components/helpers/Interfaces.tsx
Executable file
@@ -0,0 +1,29 @@
|
||||
// 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 { Tensor } from "onnxruntime-web";
|
||||
|
||||
export interface modelScaleProps {
|
||||
samScale: number;
|
||||
height: number;
|
||||
width: number;
|
||||
}
|
||||
|
||||
export interface modelInputProps {
|
||||
x: number;
|
||||
y: number;
|
||||
clickType: number;
|
||||
}
|
||||
|
||||
export interface modeDataProps {
|
||||
clicks?: Array<modelInputProps>;
|
||||
tensor: Tensor;
|
||||
modelScale: modelScaleProps;
|
||||
}
|
||||
|
||||
export interface ToolProps {
|
||||
handleMouseMove: (e: any) => void;
|
||||
}
|
||||
47
demo/src/components/helpers/maskUtils.tsx
Executable file
47
demo/src/components/helpers/maskUtils.tsx
Executable file
@@ -0,0 +1,47 @@
|
||||
// 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.
|
||||
|
||||
// Convert the onnx model mask prediction to ImageData
|
||||
function arrayToImageData(input: any, width: number, height: number) {
|
||||
const [r, g, b, a] = [0, 114, 189, 255]; // the masks's blue color
|
||||
const arr = new Uint8ClampedArray(4 * width * height).fill(0);
|
||||
for (let i = 0; i < input.length; i++) {
|
||||
|
||||
// Threshold the onnx model mask prediction at 0.0
|
||||
// This is equivalent to thresholding the mask using predictor.model.mask_threshold
|
||||
// in python
|
||||
if (input[i] > 0.0) {
|
||||
arr[4 * i + 0] = r;
|
||||
arr[4 * i + 1] = g;
|
||||
arr[4 * i + 2] = b;
|
||||
arr[4 * i + 3] = a;
|
||||
}
|
||||
}
|
||||
return new ImageData(arr, height, width);
|
||||
}
|
||||
|
||||
// Use a Canvas element to produce an image from ImageData
|
||||
function imageDataToImage(imageData: ImageData) {
|
||||
const canvas = imageDataToCanvas(imageData);
|
||||
const image = new Image();
|
||||
image.src = canvas.toDataURL();
|
||||
return image;
|
||||
}
|
||||
|
||||
// Canvas elements can be created from ImageData
|
||||
function imageDataToCanvas(imageData: ImageData) {
|
||||
const canvas = document.createElement("canvas");
|
||||
const ctx = canvas.getContext("2d");
|
||||
canvas.width = imageData.width;
|
||||
canvas.height = imageData.height;
|
||||
ctx?.putImageData(imageData, 0, 0);
|
||||
return canvas;
|
||||
}
|
||||
|
||||
// Convert the onnx model mask output to an HTMLImageElement
|
||||
export function onnxMaskToImage(input: any, width: number, height: number) {
|
||||
return imageDataToImage(arrayToImageData(input, width, height));
|
||||
}
|
||||
71
demo/src/components/helpers/onnxModelAPI.tsx
Executable file
71
demo/src/components/helpers/onnxModelAPI.tsx
Executable file
@@ -0,0 +1,71 @@
|
||||
// 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 { Tensor } from "onnxruntime-web";
|
||||
import { modeDataProps } from "./Interfaces";
|
||||
|
||||
const modelData = ({ clicks, tensor, modelScale }: modeDataProps) => {
|
||||
const imageEmbedding = tensor;
|
||||
let pointCoords;
|
||||
let pointLabels;
|
||||
let pointCoordsTensor;
|
||||
let pointLabelsTensor;
|
||||
|
||||
// Check there are input click prompts
|
||||
if (clicks) {
|
||||
let n = clicks.length;
|
||||
|
||||
// If there is no box input, a single padding point with
|
||||
// label -1 and coordinates (0.0, 0.0) should be concatenated
|
||||
// so initialize the array to support (n + 1) points.
|
||||
pointCoords = new Float32Array(2 * (n + 1));
|
||||
pointLabels = new Float32Array(n + 1);
|
||||
|
||||
// Add clicks and scale to what SAM expects
|
||||
for (let i = 0; i < n; i++) {
|
||||
pointCoords[2 * i] = clicks[i].x * modelScale.samScale;
|
||||
pointCoords[2 * i + 1] = clicks[i].y * modelScale.samScale;
|
||||
pointLabels[i] = clicks[i].clickType;
|
||||
}
|
||||
|
||||
// Add in the extra point/label when only clicks and no box
|
||||
// The extra point is at (0, 0) with label -1
|
||||
pointCoords[2 * n] = 0.0;
|
||||
pointCoords[2 * n + 1] = 0.0;
|
||||
pointLabels[n] = -1.0;
|
||||
|
||||
// Create the tensor
|
||||
pointCoordsTensor = new Tensor("float32", pointCoords, [1, n + 1, 2]);
|
||||
pointLabelsTensor = new Tensor("float32", pointLabels, [1, n + 1]);
|
||||
}
|
||||
const imageSizeTensor = new Tensor("float32", [
|
||||
modelScale.height,
|
||||
modelScale.width,
|
||||
]);
|
||||
|
||||
if (pointCoordsTensor === undefined || pointLabelsTensor === undefined)
|
||||
return;
|
||||
|
||||
// There is no previous mask, so default to an empty tensor
|
||||
const maskInput = new Tensor(
|
||||
"float32",
|
||||
new Float32Array(256 * 256),
|
||||
[1, 1, 256, 256]
|
||||
);
|
||||
// There is no previous mask, so default to 0
|
||||
const hasMaskInput = new Tensor("float32", [0]);
|
||||
|
||||
return {
|
||||
image_embeddings: imageEmbedding,
|
||||
point_coords: pointCoordsTensor,
|
||||
point_labels: pointLabelsTensor,
|
||||
orig_im_size: imageSizeTensor,
|
||||
mask_input: maskInput,
|
||||
has_mask_input: hasMaskInput,
|
||||
};
|
||||
};
|
||||
|
||||
export { modelData };
|
||||
18
demo/src/components/helpers/scaleHelper.tsx
Executable file
18
demo/src/components/helpers/scaleHelper.tsx
Executable file
@@ -0,0 +1,18 @@
|
||||
// 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.
|
||||
|
||||
|
||||
// Helper function for handling image scaling needed for SAM
|
||||
const handleImageScale = (image: HTMLImageElement) => {
|
||||
// Input images to SAM must be resized so the longest side is 1024
|
||||
const LONG_SIDE_LENGTH = 1024;
|
||||
let w = image.naturalWidth;
|
||||
let h = image.naturalHeight;
|
||||
const samScale = LONG_SIDE_LENGTH / Math.max(h, w);
|
||||
return { height: h, width: w, samScale };
|
||||
};
|
||||
|
||||
export { handleImageScale };
|
||||
31
demo/src/components/hooks/context.tsx
Executable file
31
demo/src/components/hooks/context.tsx
Executable file
@@ -0,0 +1,31 @@
|
||||
// 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 React, { useState } from "react";
|
||||
import { modelInputProps } from "../helpers/Interfaces";
|
||||
import AppContext from "./createContext";
|
||||
|
||||
const AppContextProvider = (props: {
|
||||
children: React.ReactElement<any, string | React.JSXElementConstructor<any>>;
|
||||
}) => {
|
||||
const [clicks, setClicks] = useState<Array<modelInputProps> | null>(null);
|
||||
const [image, setImage] = useState<HTMLImageElement | null>(null);
|
||||
const [maskImg, setMaskImg] = useState<HTMLImageElement | null>(null);
|
||||
|
||||
return (
|
||||
<AppContext.Provider
|
||||
value={{
|
||||
clicks: [clicks, setClicks],
|
||||
image: [image, setImage],
|
||||
maskImg: [maskImg, setMaskImg],
|
||||
}}
|
||||
>
|
||||
{props.children}
|
||||
</AppContext.Provider>
|
||||
);
|
||||
};
|
||||
|
||||
export default AppContextProvider;
|
||||
27
demo/src/components/hooks/createContext.tsx
Executable file
27
demo/src/components/hooks/createContext.tsx
Executable file
@@ -0,0 +1,27 @@
|
||||
// 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 { createContext } from "react";
|
||||
import { modelInputProps } from "../helpers/Interfaces";
|
||||
|
||||
interface contextProps {
|
||||
clicks: [
|
||||
clicks: modelInputProps[] | null,
|
||||
setClicks: (e: modelInputProps[] | null) => void
|
||||
];
|
||||
image: [
|
||||
image: HTMLImageElement | null,
|
||||
setImage: (e: HTMLImageElement | null) => void
|
||||
];
|
||||
maskImg: [
|
||||
maskImg: HTMLImageElement | null,
|
||||
setMaskImg: (e: HTMLImageElement | null) => void
|
||||
];
|
||||
}
|
||||
|
||||
const AppContext = createContext<contextProps | null>(null);
|
||||
|
||||
export default AppContext;
|
||||
17
demo/src/index.tsx
Executable file
17
demo/src/index.tsx
Executable file
@@ -0,0 +1,17 @@
|
||||
// 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 * as React from "react";
|
||||
import { createRoot } from "react-dom/client";
|
||||
import AppContextProvider from "./components/hooks/context";
|
||||
import App from "./App";
|
||||
const container = document.getElementById("root");
|
||||
const root = createRoot(container!);
|
||||
root.render(
|
||||
<AppContextProvider>
|
||||
<App/>
|
||||
</AppContextProvider>
|
||||
);
|
||||
12
demo/tailwind.config.js
Executable file
12
demo/tailwind.config.js
Executable file
@@ -0,0 +1,12 @@
|
||||
// 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.
|
||||
|
||||
/** @type {import('tailwindcss').Config} */
|
||||
module.exports = {
|
||||
content: ["./src/**/*.{html,js,tsx}"],
|
||||
theme: {},
|
||||
plugins: [],
|
||||
};
|
||||
24
demo/tsconfig.json
Executable file
24
demo/tsconfig.json
Executable file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"compilerOptions": {
|
||||
"lib": ["dom", "dom.iterable", "esnext"],
|
||||
"allowJs": true,
|
||||
"skipLibCheck": true,
|
||||
"strict": true,
|
||||
"forceConsistentCasingInFileNames": true,
|
||||
"noEmit": false,
|
||||
"esModuleInterop": true,
|
||||
"module": "esnext",
|
||||
"moduleResolution": "node",
|
||||
"resolveJsonModule": true,
|
||||
"isolatedModules": true,
|
||||
"jsx": "react",
|
||||
"incremental": true,
|
||||
"target": "ESNext",
|
||||
"useDefineForClassFields": true,
|
||||
"allowSyntheticDefaultImports": true,
|
||||
"outDir": "./dist/",
|
||||
"sourceMap": true
|
||||
},
|
||||
"include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", "src"],
|
||||
"exclude": ["node_modules"]
|
||||
}
|
||||
32
linter.sh
Executable file
32
linter.sh
Executable file
@@ -0,0 +1,32 @@
|
||||
#!/bin/bash -e
|
||||
# Copyright (c) Facebook, Inc. and its affiliates.
|
||||
|
||||
{
|
||||
black --version | grep -E "23\." > /dev/null
|
||||
} || {
|
||||
echo "Linter requires 'black==23.*' !"
|
||||
exit 1
|
||||
}
|
||||
|
||||
ISORT_VERSION=$(isort --version-number)
|
||||
if [[ "$ISORT_VERSION" != 5.12* ]]; then
|
||||
echo "Linter requires isort==5.12.0 !"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Running isort ..."
|
||||
isort . --atomic
|
||||
|
||||
echo "Running black ..."
|
||||
black -l 100 .
|
||||
|
||||
echo "Running flake8 ..."
|
||||
if [ -x "$(command -v flake8)" ]; then
|
||||
flake8 .
|
||||
else
|
||||
python3 -m flake8 .
|
||||
fi
|
||||
|
||||
echo "Running mypy..."
|
||||
|
||||
mypy --exclude 'setup.py|notebooks' .
|
||||
445
notebooks/automatic_mask_generator_example.ipynb
Executable file
445
notebooks/automatic_mask_generator_example.ipynb
Executable file
File diff suppressed because one or more lines are too long
BIN
notebooks/images/dog.jpg
Executable file
BIN
notebooks/images/dog.jpg
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 98 KiB |
BIN
notebooks/images/groceries.jpg
Executable file
BIN
notebooks/images/groceries.jpg
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 164 KiB |
BIN
notebooks/images/truck.jpg
Executable file
BIN
notebooks/images/truck.jpg
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 265 KiB |
832
notebooks/onnx_model_example.ipynb
Executable file
832
notebooks/onnx_model_example.ipynb
Executable file
@@ -0,0 +1,832 @@
|
||||
{
|
||||
"cells": [
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "901c8ef3",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Copyright (c) Meta Platforms, Inc. and affiliates."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1662bb7c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"# Produces masks from prompts using an ONNX model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7fcc21a0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"SAM's prompt encoder and mask decoder are very lightweight, which allows for efficient computation of a mask given user input. This notebook shows an example of how to export and use this lightweight component of the model in ONNX format, allowing it to run on a variety of platforms that support an ONNX runtime."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 2,
|
||||
"id": "86daff77",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:16:23.533543Z",
|
||||
"start_time": "2025-08-06T03:16:23.528904Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"data": {
|
||||
"text/html": [
|
||||
"\n",
|
||||
"<a target=\"_blank\" href=\"https://colab.research.google.com/github/facebookresearch/segment-anything/blob/main/notebooks/onnx_model_example.ipynb\">\n",
|
||||
" <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
|
||||
"</a>\n"
|
||||
],
|
||||
"text/plain": [
|
||||
"<IPython.core.display.HTML object>"
|
||||
]
|
||||
},
|
||||
"metadata": {},
|
||||
"output_type": "display_data"
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"from IPython.display import display, HTML\n",
|
||||
"display(HTML(\n",
|
||||
"\"\"\"\n",
|
||||
"<a target=\"_blank\" href=\"https://colab.research.google.com/github/facebookresearch/segment-anything/blob/main/notebooks/onnx_model_example.ipynb\">\n",
|
||||
" <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
|
||||
"</a>\n",
|
||||
"\"\"\"\n",
|
||||
"))"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "55ae4e00",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Environment Set-up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "109a5cc2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If running locally using jupyter, first install `segment_anything` in your environment using the [installation instructions](https://github.com/facebookresearch/segment-anything#installation) in the repository. The latest stable versions of PyTorch and ONNX are recommended for this notebook. If running from Google Colab, set `using_colab=True` below and run the cell. In Colab, be sure to select 'GPU' under 'Edit'->'Notebook Settings'->'Hardware accelerator'."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 4,
|
||||
"id": "39b99fc4",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:17:30.823461Z",
|
||||
"start_time": "2025-08-06T03:17:30.818737Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"using_colab = False"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 5,
|
||||
"id": "296a69be",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:18:04.726389Z",
|
||||
"start_time": "2025-08-06T03:18:04.705650Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"if using_colab:\n",
|
||||
" import torch\n",
|
||||
" import torchvision\n",
|
||||
" print(\"PyTorch version:\", torch.__version__)\n",
|
||||
" print(\"Torchvision version:\", torchvision.__version__)\n",
|
||||
" print(\"CUDA is available:\", torch.cuda.is_available())\n",
|
||||
" import sys\n",
|
||||
" !{sys.executable} -m pip install opencv-python matplotlib onnx onnxruntime\n",
|
||||
" !{sys.executable} -m pip install 'git+https://github.com/facebookresearch/segment-anything.git'\n",
|
||||
" \n",
|
||||
" !mkdir images\n",
|
||||
" !wget -P images https://raw.githubusercontent.com/facebookresearch/segment-anything/main/notebooks/images/truck.jpg\n",
|
||||
" \n",
|
||||
" !wget https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "dc4a58be",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Set-up"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "42396e8d",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Note that this notebook requires both the `onnx` and `onnxruntime` optional dependencies, in addition to `opencv-python` and `matplotlib` for visualization."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 6,
|
||||
"id": "2c712610",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:18:15.221624Z",
|
||||
"start_time": "2025-08-06T03:18:12.230502Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import torch\n",
|
||||
"import numpy as np\n",
|
||||
"import cv2\n",
|
||||
"import matplotlib.pyplot as plt\n",
|
||||
"from segment_anything import sam_model_registry, SamPredictor\n",
|
||||
"from segment_anything.utils.onnx import SamOnnxModel\n",
|
||||
"\n",
|
||||
"import onnxruntime\n",
|
||||
"from onnxruntime.quantization import QuantType\n",
|
||||
"from onnxruntime.quantization.quantize import quantize_dynamic"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 7,
|
||||
"id": "f29441b9",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:18:18.375013Z",
|
||||
"start_time": "2025-08-06T03:18:18.359691Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def show_mask(mask, ax):\n",
|
||||
" color = np.array([30/255, 144/255, 255/255, 0.6])\n",
|
||||
" h, w = mask.shape[-2:]\n",
|
||||
" mask_image = mask.reshape(h, w, 1) * color.reshape(1, 1, -1)\n",
|
||||
" ax.imshow(mask_image)\n",
|
||||
" \n",
|
||||
"def show_points(coords, labels, ax, marker_size=375):\n",
|
||||
" pos_points = coords[labels==1]\n",
|
||||
" neg_points = coords[labels==0]\n",
|
||||
" ax.scatter(pos_points[:, 0], pos_points[:, 1], color='green', marker='*', s=marker_size, edgecolor='white', linewidth=1.25)\n",
|
||||
" ax.scatter(neg_points[:, 0], neg_points[:, 1], color='red', marker='*', s=marker_size, edgecolor='white', linewidth=1.25) \n",
|
||||
" \n",
|
||||
"def show_box(box, ax):\n",
|
||||
" x0, y0 = box[0], box[1]\n",
|
||||
" w, h = box[2] - box[0], box[3] - box[1]\n",
|
||||
" ax.add_patch(plt.Rectangle((x0, y0), w, h, edgecolor='green', facecolor=(0,0,0,0), lw=2)) "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bd0f6b2b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Export an ONNX model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1540f719",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Set the path below to a SAM model checkpoint, then load the model. This will be needed to both export the model and to calculate embeddings for the model."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 8,
|
||||
"id": "76fc53f4",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:18:52.842965Z",
|
||||
"start_time": "2025-08-06T03:18:52.839365Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"checkpoint = \"/home/alab/PycharmProjects/segment-anything/checkpoint/sam_vit_h_4b8939.pth\"\n",
|
||||
"model_type = \"vit_h\""
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 9,
|
||||
"id": "11bfc8aa",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:19:02.574461Z",
|
||||
"start_time": "2025-08-06T03:18:55.883913Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sam = sam_model_registry[model_type](checkpoint=checkpoint)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "450c089c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The script `segment-anything/scripts/export_onnx_model.py` can be used to export the necessary portion of SAM. Alternatively, run the following code to export an ONNX model. If you have already exported a model, set the path below and skip to the next section. Assure that the exported ONNX model aligns with the checkpoint and model type set above. This notebook expects the model was exported with the parameter `return_single_mask=True`."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 10,
|
||||
"id": "38a8add8",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:19:08.682003Z",
|
||||
"start_time": "2025-08-06T03:19:08.677719Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"onnx_model_path = None # Set to use an already exported model, then skip to the next section."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 11,
|
||||
"id": "7da638ba",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:22:08.108690Z",
|
||||
"start_time": "2025-08-06T03:22:07.697634Z"
|
||||
}
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import warnings\n",
|
||||
"\n",
|
||||
"onnx_model_path = \"/home/alab/PycharmProjects/segment-anything/notebooks/sam_onnx_example.onnx\"\n",
|
||||
"\n",
|
||||
"onnx_model = SamOnnxModel(sam, return_single_mask=True)\n",
|
||||
"\n",
|
||||
"dynamic_axes = {\n",
|
||||
" \"point_coords\": {1: \"num_points\"},\n",
|
||||
" \"point_labels\": {1: \"num_points\"},\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"embed_dim = sam.prompt_encoder.embed_dim\n",
|
||||
"embed_size = sam.prompt_encoder.image_embedding_size\n",
|
||||
"mask_input_size = [4 * x for x in embed_size]\n",
|
||||
"dummy_inputs = {\n",
|
||||
" \"image_embeddings\": torch.randn(1, embed_dim, *embed_size, dtype=torch.float),\n",
|
||||
" \"point_coords\": torch.randint(low=0, high=1024, size=(1, 5, 2), dtype=torch.float),\n",
|
||||
" \"point_labels\": torch.randint(low=0, high=4, size=(1, 5), dtype=torch.float),\n",
|
||||
" \"mask_input\": torch.randn(1, 1, *mask_input_size, dtype=torch.float),\n",
|
||||
" \"has_mask_input\": torch.tensor([1], dtype=torch.float),\n",
|
||||
" \"orig_im_size\": torch.tensor([1500, 2250], dtype=torch.float),\n",
|
||||
"}\n",
|
||||
"output_names = [\"masks\", \"iou_predictions\", \"low_res_masks\"]\n",
|
||||
"\n",
|
||||
"with warnings.catch_warnings():\n",
|
||||
" warnings.filterwarnings(\"ignore\", category=torch.jit.TracerWarning)\n",
|
||||
" warnings.filterwarnings(\"ignore\", category=UserWarning)\n",
|
||||
" with open(onnx_model_path, \"wb\") as f:\n",
|
||||
" torch.onnx.export(\n",
|
||||
" onnx_model,\n",
|
||||
" tuple(dummy_inputs.values()),\n",
|
||||
" f,\n",
|
||||
" export_params=True,\n",
|
||||
" verbose=False,\n",
|
||||
" opset_version=17,\n",
|
||||
" do_constant_folding=True,\n",
|
||||
" input_names=list(dummy_inputs.keys()),\n",
|
||||
" output_names=output_names,\n",
|
||||
" dynamic_axes=dynamic_axes,\n",
|
||||
" ) "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "c450cf1a",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"If desired, the model can additionally be quantized and optimized. We find this improves web runtime significantly for negligible change in qualitative performance. Run the next cell to quantize the model, or skip to the next section otherwise."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": 13,
|
||||
"id": "235d39fe",
|
||||
"metadata": {
|
||||
"ExecuteTime": {
|
||||
"end_time": "2025-08-06T03:19:17.443097Z",
|
||||
"start_time": "2025-08-06T03:19:17.408587Z"
|
||||
}
|
||||
},
|
||||
"outputs": [
|
||||
{
|
||||
"ename": "TypeError",
|
||||
"evalue": "quantize_dynamic() got an unexpected keyword argument 'optimize_model'",
|
||||
"output_type": "error",
|
||||
"traceback": [
|
||||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||||
"\u001b[0;31mTypeError\u001b[0m Traceback (most recent call last)",
|
||||
"Cell \u001b[0;32mIn[13], line 2\u001b[0m\n\u001b[1;32m 1\u001b[0m onnx_model_quantized_path \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124msam_onnx_quantized_example.onnx\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 2\u001b[0m \u001b[43mquantize_dynamic\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 3\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel_input\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43monnx_model_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 4\u001b[0m \u001b[43m \u001b[49m\u001b[43mmodel_output\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43monnx_model_quantized_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 5\u001b[0m \u001b[43m \u001b[49m\u001b[43moptimize_model\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 6\u001b[0m \u001b[43m \u001b[49m\u001b[43mper_channel\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 7\u001b[0m \u001b[43m \u001b[49m\u001b[43mreduce_range\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 8\u001b[0m \u001b[43m \u001b[49m\u001b[43mweight_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mQuantType\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mQUInt8\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 9\u001b[0m \u001b[43m)\u001b[49m\n\u001b[1;32m 10\u001b[0m onnx_model_path \u001b[38;5;241m=\u001b[39m onnx_model_quantized_path\n",
|
||||
"\u001b[0;31mTypeError\u001b[0m: quantize_dynamic() got an unexpected keyword argument 'optimize_model'"
|
||||
]
|
||||
}
|
||||
],
|
||||
"source": [
|
||||
"onnx_model_quantized_path = \"/home/alab/PycharmProjects/segment-anything/notebooks/sam_onnx_example.onnx\"\n",
|
||||
"quantize_dynamic(\n",
|
||||
" model_input=onnx_model_path,\n",
|
||||
" model_output=onnx_model_quantized_path,\n",
|
||||
" optimize_model=True,\n",
|
||||
" per_channel=False,\n",
|
||||
" reduce_range=False,\n",
|
||||
" weight_type=QuantType.QUInt8,\n",
|
||||
")\n",
|
||||
"onnx_model_path = onnx_model_quantized_path"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "927a928b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Example Image"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "6be6eb55",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"image = cv2.imread('images/truck.jpg')\n",
|
||||
"image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b7e9a27a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.figure(figsize=(10,10))\n",
|
||||
"plt.imshow(image)\n",
|
||||
"plt.axis('on')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "027b177b",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"## Using an ONNX model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "778d4593",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Here as an example, we use `onnxruntime` in python on CPU to execute the ONNX model. However, any platform that supports an ONNX runtime could be used in principle. Launch the runtime session below:"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "9689b1bf",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ort_session = onnxruntime.InferenceSession(onnx_model_path)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7708ead6",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"To use the ONNX model, the image must first be pre-processed using the SAM image encoder. This is a heavier weight process best performed on GPU. SamPredictor can be used as normal, then `.get_image_embedding()` will retreive the intermediate features."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "26e067b4",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"sam.to(device='cuda')\n",
|
||||
"predictor = SamPredictor(sam)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "7ad3f0d6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"predictor.set_image(image)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8a6f0f07",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"image_embedding = predictor.get_image_embedding().cpu().numpy()"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5e112f33",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"image_embedding.shape"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6337b654",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The ONNX model has a different input signature than `SamPredictor.predict`. The following inputs must all be supplied. Note the special cases for both point and mask inputs. All inputs are `np.float32`.\n",
|
||||
"* `image_embeddings`: The image embedding from `predictor.get_image_embedding()`. Has a batch index of length 1.\n",
|
||||
"* `point_coords`: Coordinates of sparse input prompts, corresponding to both point inputs and box inputs. Boxes are encoded using two points, one for the top-left corner and one for the bottom-right corner. *Coordinates must already be transformed to long-side 1024.* Has a batch index of length 1.\n",
|
||||
"* `point_labels`: Labels for the sparse input prompts. 0 is a negative input point, 1 is a positive input point, 2 is a top-left box corner, 3 is a bottom-right box corner, and -1 is a padding point. *If there is no box input, a single padding point with label -1 and coordinates (0.0, 0.0) should be concatenated.*\n",
|
||||
"* `mask_input`: A mask input to the model with shape 1x1x256x256. This must be supplied even if there is no mask input. In this case, it can just be zeros.\n",
|
||||
"* `has_mask_input`: An indicator for the mask input. 1 indicates a mask input, 0 indicates no mask input.\n",
|
||||
"* `orig_im_size`: The size of the input image in (H,W) format, before any transformation. \n",
|
||||
"\n",
|
||||
"Additionally, the ONNX model does not threshold the output mask logits. To obtain a binary mask, threshold at `sam.mask_threshold` (equal to 0.0)."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "bf5a9f55",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Example point input"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1c0deef0",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"input_point = np.array([[500, 375]])\n",
|
||||
"input_label = np.array([1])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "7256394c",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Add a batch index, concatenate a padding point, and transform."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "4f69903e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"onnx_coord = np.concatenate([input_point, np.array([[0.0, 0.0]])], axis=0)[None, :, :]\n",
|
||||
"onnx_label = np.concatenate([input_label, np.array([-1])], axis=0)[None, :].astype(np.float32)\n",
|
||||
"\n",
|
||||
"onnx_coord = predictor.transform.apply_coords(onnx_coord, image.shape[:2]).astype(np.float32)\n"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b188dc53",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Create an empty mask input and an indicator for no mask."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "5cb52bcf",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"onnx_mask_input = np.zeros((1, 1, 256, 256), dtype=np.float32)\n",
|
||||
"onnx_has_mask_input = np.zeros(1, dtype=np.float32)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "a99c2cc5",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Package the inputs to run in the onnx model"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b1d7ea11",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ort_inputs = {\n",
|
||||
" \"image_embeddings\": image_embedding,\n",
|
||||
" \"point_coords\": onnx_coord,\n",
|
||||
" \"point_labels\": onnx_label,\n",
|
||||
" \"mask_input\": onnx_mask_input,\n",
|
||||
" \"has_mask_input\": onnx_has_mask_input,\n",
|
||||
" \"orig_im_size\": np.array(image.shape[:2], dtype=np.float32)\n",
|
||||
"}"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "4b6409c9",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Predict a mask and threshold it."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "dc4cc082",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"masks, _, low_res_logits = ort_session.run(None, ort_inputs)\n",
|
||||
"masks = masks > predictor.model.mask_threshold"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d778a8fb",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"masks.shape"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "badb1175",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.figure(figsize=(10,10))\n",
|
||||
"plt.imshow(image)\n",
|
||||
"show_mask(masks, plt.gca())\n",
|
||||
"show_points(input_point, input_label, plt.gca())\n",
|
||||
"plt.axis('off')\n",
|
||||
"plt.show() "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "1f1d4d15",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Example mask input"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "b319da82",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"input_point = np.array([[500, 375], [1125, 625]])\n",
|
||||
"input_label = np.array([1, 1])\n",
|
||||
"\n",
|
||||
"# Use the mask output from the previous run. It is already in the correct form for input to the ONNX model.\n",
|
||||
"onnx_mask_input = low_res_logits"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "b1823b37",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Transform the points as in the previous example."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8885130f",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"onnx_coord = np.concatenate([input_point, np.array([[0.0, 0.0]])], axis=0)[None, :, :]\n",
|
||||
"onnx_label = np.concatenate([input_label, np.array([-1])], axis=0)[None, :].astype(np.float32)\n",
|
||||
"\n",
|
||||
"onnx_coord = predictor.transform.apply_coords(onnx_coord, image.shape[:2]).astype(np.float32)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "28e47b69",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"The `has_mask_input` indicator is now 1."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "3ab4483a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"onnx_has_mask_input = np.ones(1, dtype=np.float32)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "d3781955",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Package inputs, then predict and threshold the mask."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0c1ec096",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"ort_inputs = {\n",
|
||||
" \"image_embeddings\": image_embedding,\n",
|
||||
" \"point_coords\": onnx_coord,\n",
|
||||
" \"point_labels\": onnx_label,\n",
|
||||
" \"mask_input\": onnx_mask_input,\n",
|
||||
" \"has_mask_input\": onnx_has_mask_input,\n",
|
||||
" \"orig_im_size\": np.array(image.shape[:2], dtype=np.float32)\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"masks, _, _ = ort_session.run(None, ort_inputs)\n",
|
||||
"masks = masks > predictor.model.mask_threshold"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "1e36554b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.figure(figsize=(10,10))\n",
|
||||
"plt.imshow(image)\n",
|
||||
"show_mask(masks, plt.gca())\n",
|
||||
"show_points(input_point, input_label, plt.gca())\n",
|
||||
"plt.axis('off')\n",
|
||||
"plt.show() "
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "2ef211d0",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"### Example box and point input"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "51e58d2e",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"input_box = np.array([425, 600, 700, 875])\n",
|
||||
"input_point = np.array([[575, 750]])\n",
|
||||
"input_label = np.array([0])"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "6e119dcb",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Add a batch index, concatenate a box and point inputs, add the appropriate labels for the box corners, and transform. There is no padding point since the input includes a box input."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "bfbe4911",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"onnx_box_coords = input_box.reshape(2, 2)\n",
|
||||
"onnx_box_labels = np.array([2,3])\n",
|
||||
"\n",
|
||||
"onnx_coord = np.concatenate([input_point, onnx_box_coords], axis=0)[None, :, :]\n",
|
||||
"onnx_label = np.concatenate([input_label, onnx_box_labels], axis=0)[None, :].astype(np.float32)\n",
|
||||
"\n",
|
||||
"onnx_coord = predictor.transform.apply_coords(onnx_coord, image.shape[:2]).astype(np.float32)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "markdown",
|
||||
"id": "65edabd2",
|
||||
"metadata": {},
|
||||
"source": [
|
||||
"Package inputs, then predict and threshold the mask."
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "2abfba56",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"onnx_mask_input = np.zeros((1, 1, 256, 256), dtype=np.float32)\n",
|
||||
"onnx_has_mask_input = np.zeros(1, dtype=np.float32)\n",
|
||||
"\n",
|
||||
"ort_inputs = {\n",
|
||||
" \"image_embeddings\": image_embedding,\n",
|
||||
" \"point_coords\": onnx_coord,\n",
|
||||
" \"point_labels\": onnx_label,\n",
|
||||
" \"mask_input\": onnx_mask_input,\n",
|
||||
" \"has_mask_input\": onnx_has_mask_input,\n",
|
||||
" \"orig_im_size\": np.array(image.shape[:2], dtype=np.float32)\n",
|
||||
"}\n",
|
||||
"\n",
|
||||
"masks, _, _ = ort_session.run(None, ort_inputs)\n",
|
||||
"masks = masks > predictor.model.mask_threshold"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8301bf33",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"plt.figure(figsize=(10, 10))\n",
|
||||
"plt.imshow(image)\n",
|
||||
"show_mask(masks[0], plt.gca())\n",
|
||||
"show_box(input_box, plt.gca())\n",
|
||||
"show_points(input_point, input_label, plt.gca())\n",
|
||||
"plt.axis('off')\n",
|
||||
"plt.show()"
|
||||
]
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
"kernelspec": {
|
||||
"display_name": "Python 3 (ipykernel)",
|
||||
"language": "python",
|
||||
"name": "python3"
|
||||
},
|
||||
"language_info": {
|
||||
"codemirror_mode": {
|
||||
"name": "ipython",
|
||||
"version": 3
|
||||
},
|
||||
"file_extension": ".py",
|
||||
"mimetype": "text/x-python",
|
||||
"name": "python",
|
||||
"nbconvert_exporter": "python",
|
||||
"pygments_lexer": "ipython3",
|
||||
"version": "3.9.23"
|
||||
}
|
||||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
11
notebooks/onnx_model_example.py
Executable file
11
notebooks/onnx_model_example.py
Executable file
@@ -0,0 +1,11 @@
|
||||
# 导入必要的库
|
||||
import numpy as np
|
||||
import torch
|
||||
import matplotlib.pyplot as plt
|
||||
from PIL import Image
|
||||
import requests
|
||||
from io import BytesIO
|
||||
|
||||
# 从 SAM 2 库中导入图像预测器和模型构建工具
|
||||
from sam2.build_sam import build_sam2
|
||||
from sam2.sam2_image_predictor import SAM2ImagePredictor
|
||||
1016
notebooks/predictor_example.ipynb
Executable file
1016
notebooks/predictor_example.ipynb
Executable file
File diff suppressed because one or more lines are too long
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/0.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/0.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 7.5 KiB |
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/1.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/1.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 6.8 KiB |
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/2.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/2.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 3.1 KiB |
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/3.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/3.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 3.3 KiB |
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/4.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/4.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 3.3 KiB |
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/5.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/5.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.9 KiB |
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/6.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/6.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 3.5 KiB |
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/7.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/7.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.9 KiB |
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/8.png
Executable file
BIN
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/8.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 3.4 KiB |
10
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/metadata.csv
Executable file
10
output/076ec5a6-0d99-4867-b38d-94c026000691-3-89/metadata.csv
Executable file
@@ -0,0 +1,10 @@
|
||||
id,area,bbox_x0,bbox_y0,bbox_w,bbox_h,point_input_x,point_input_y,predicted_iou,stability_score,crop_box_x0,crop_box_y0,crop_box_w,crop_box_h
|
||||
0,208104,346,119,353,794,496.0,624.0,1.0344942808151245,0.9846644997596741,0,0,1024,1024
|
||||
1,826080,0,0,1023,1023,1008.0,912.0,1.0164952278137207,0.9937294721603394,0,0,1024,1024
|
||||
2,3538,495,151,49,108,528.0,176.0,0.9655076861381531,0.960321843624115,0,0,1024,1024
|
||||
3,2837,588,340,35,124,592.0,368.0,0.9651759266853333,0.9690757393836975,0,0,1024,1024
|
||||
4,2722,420,347,34,131,432.0,432.0,0.9555162787437439,0.9638205766677856,0,0,1024,1024
|
||||
5,980,590,447,27,49,592.0,464.0,0.9420101046562195,0.9660339951515198,0,0,1024,1024
|
||||
6,10617,479,119,87,172,496.0,144.0,0.936710000038147,0.9556418061256409,0,0,1024,1024
|
||||
7,609,681,528,15,55,688.0,560.0,0.9296139478683472,0.9707317352294922,0,0,1024,1024
|
||||
8,4588,522,183,79,143,560.0,240.0,0.9280573725700378,0.9508405923843384,0,0,1024,1024
|
||||
|
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/0.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/0.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.3 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/1.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/1.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.3 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/10.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/10.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/11.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/11.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/12.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/12.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/13.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/13.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/14.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/14.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/15.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/15.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/16.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/16.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.3 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/17.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/17.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/18.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/18.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.9 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/19.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/19.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.9 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/2.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/2.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 3.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/20.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/20.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.2 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/21.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/21.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/22.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/22.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/23.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/23.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.2 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/24.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/24.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.1 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/25.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/25.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.1 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/26.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/26.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 3.4 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/3.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/3.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.3 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/4.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/4.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.9 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/5.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/5.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/6.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/6.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/7.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/7.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.9 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/8.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/8.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/9.png
Executable file
BIN
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/9.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 2.0 KiB |
28
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/metadata.csv
Executable file
28
output/ae976103-d7ec-4eed-b5d1-3e5f04d8be26/metadata.csv
Executable file
@@ -0,0 +1,28 @@
|
||||
id,area,bbox_x0,bbox_y0,bbox_w,bbox_h,point_input_x,point_input_y,predicted_iou,stability_score,crop_box_x0,crop_box_y0,crop_box_w,crop_box_h
|
||||
0,318264,4,0,533,899,354.90625,42.28125,1.025822401046753,0.9901363253593445,0,0,554,902
|
||||
1,2908,194,8,67,91,233.71875,42.28125,0.9839344024658203,0.9722222089767456,0,0,554,902
|
||||
2,10997,91,78,68,234,112.53125,267.78125,0.9781885743141174,0.9724088311195374,0,0,554,902
|
||||
3,2910,280,7,67,92,320.28125,42.28125,0.977243185043335,0.9685065746307373,0,0,554,902
|
||||
4,19292,391,302,146,207,441.46875,408.71875,0.9717334508895874,0.9758270978927612,0,0,554,902
|
||||
5,204,262,572,17,14,268.34375,577.84375,0.9706144332885742,0.9950980544090271,0,0,554,902
|
||||
6,209,261,456,18,15,268.34375,465.09375,0.9689342379570007,0.9763033390045166,0,0,554,902
|
||||
7,10832,381,81,67,231,424.15625,267.78125,0.968802273273468,0.9669151306152344,0,0,554,902
|
||||
8,190,263,398,15,15,268.34375,408.71875,0.967627227306366,0.9947643876075745,0,0,554,902
|
||||
9,206,262,283,16,15,268.34375,295.96875,0.9655775427818298,0.9855769276618958,0,0,554,902
|
||||
10,216,262,687,17,15,268.34375,690.59375,0.9645803570747375,0.9907407164573669,0,0,554,902
|
||||
11,222,262,744,17,16,268.34375,746.96875,0.9638096690177917,0.9955157041549683,0,0,554,902
|
||||
12,203,262,803,16,15,268.34375,803.34375,0.9622183442115784,0.9756097793579102,0,0,554,902
|
||||
13,216,262,629,17,16,268.34375,634.21875,0.9615152478218079,0.9862385392189026,0,0,554,902
|
||||
14,205,263,514,15,15,268.34375,521.46875,0.9610558152198792,0.9902439117431641,0,0,554,902
|
||||
15,216,261,167,17,15,268.34375,183.21875,0.9606413245201111,0.9817351698875427,0,0,554,902
|
||||
16,919,154,294,17,84,164.46875,352.34375,0.9570132493972778,0.9583777785301208,0,0,554,902
|
||||
17,237,261,224,19,16,268.34375,239.59375,0.9552502632141113,0.9915611743927002,0,0,554,902
|
||||
18,19664,4,302,147,207,129.84375,465.09375,0.9529095888137817,0.9699330925941467,0,0,554,902
|
||||
19,19614,3,131,148,378,112.53125,436.90625,0.9519698619842529,0.9640650153160095,0,0,554,902
|
||||
20,3890,224,4,93,61,302.96875,14.09375,0.9364364743232727,0.9555724859237671,0,0,554,902
|
||||
21,224,262,109,17,16,268.34375,126.84375,0.9293429255485535,0.9647576808929443,0,0,554,902
|
||||
22,203,263,69,16,15,268.34375,70.46875,0.9020635485649109,0.9708737730979919,0,0,554,902
|
||||
23,338,310,252,11,94,320.28125,295.96875,0.8969216346740723,0.9504373073577881,0,0,554,902
|
||||
24,520,261,345,21,30,268.34375,352.34375,0.8908350467681885,0.9606741666793823,0,0,554,902
|
||||
25,149,333,300,9,43,337.59375,324.15625,0.8839569091796875,0.9599999785423279,0,0,554,902
|
||||
26,39591,2,0,209,446,43.28125,42.28125,0.8828506469726562,0.9530083537101746,0,0,554,902
|
||||
|
BIN
output/dog_and_girl/0.png
Executable file
BIN
output/dog_and_girl/0.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 9.8 KiB |
BIN
output/dog_and_girl/1.png
Executable file
BIN
output/dog_and_girl/1.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 6.9 KiB |
BIN
output/dog_and_girl/10.png
Executable file
BIN
output/dog_and_girl/10.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 6.4 KiB |
BIN
output/dog_and_girl/11.png
Executable file
BIN
output/dog_and_girl/11.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.2 KiB |
BIN
output/dog_and_girl/12.png
Executable file
BIN
output/dog_and_girl/12.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.1 KiB |
BIN
output/dog_and_girl/13.png
Executable file
BIN
output/dog_and_girl/13.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.0 KiB |
BIN
output/dog_and_girl/14.png
Executable file
BIN
output/dog_and_girl/14.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 6.2 KiB |
BIN
output/dog_and_girl/15.png
Executable file
BIN
output/dog_and_girl/15.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.2 KiB |
BIN
output/dog_and_girl/16.png
Executable file
BIN
output/dog_and_girl/16.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 7.0 KiB |
BIN
output/dog_and_girl/17.png
Executable file
BIN
output/dog_and_girl/17.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.1 KiB |
BIN
output/dog_and_girl/18.png
Executable file
BIN
output/dog_and_girl/18.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.0 KiB |
BIN
output/dog_and_girl/19.png
Executable file
BIN
output/dog_and_girl/19.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.1 KiB |
BIN
output/dog_and_girl/2.png
Executable file
BIN
output/dog_and_girl/2.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 6.0 KiB |
BIN
output/dog_and_girl/20.png
Executable file
BIN
output/dog_and_girl/20.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.1 KiB |
BIN
output/dog_and_girl/21.png
Executable file
BIN
output/dog_and_girl/21.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.5 KiB |
BIN
output/dog_and_girl/22.png
Executable file
BIN
output/dog_and_girl/22.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.3 KiB |
BIN
output/dog_and_girl/23.png
Executable file
BIN
output/dog_and_girl/23.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.1 KiB |
BIN
output/dog_and_girl/24.png
Executable file
BIN
output/dog_and_girl/24.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.1 KiB |
BIN
output/dog_and_girl/25.png
Executable file
BIN
output/dog_and_girl/25.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.3 KiB |
BIN
output/dog_and_girl/26.png
Executable file
BIN
output/dog_and_girl/26.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 6.6 KiB |
BIN
output/dog_and_girl/27.png
Executable file
BIN
output/dog_and_girl/27.png
Executable file
Binary file not shown.
|
After Width: | Height: | Size: 5.0 KiB |
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user