# TensorFlow Graphics
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
[![Build](https://github.com/tensorflow/graphics/workflows/Build/badge.svg?branch=master)](https://github.com/tensorflow/graphics/actions)
[![Code coverage](https://img.shields.io/coveralls/github/tensorflow/graphics.svg)](https://coveralls.io/github/tensorflow/graphics)
[![PyPI project status](https://img.shields.io/pypi/status/tensorflow-graphics.svg)](https://pypi.org/project/tensorflow-graphics/)
[![Supported Python version](https://img.shields.io/pypi/pyversions/tensorflow-graphics.svg)](https://pypi.org/project/tensorflow-graphics/)
[![PyPI release version](https://img.shields.io/pypi/v/tensorflow-graphics.svg)](https://pypi.org/project/tensorflow-graphics/)
[![Downloads](https://pepy.tech/badge/tensorflow-graphics)](https://pepy.tech/project/tensorflow-graphics)
The last few years have seen a rise in novel differentiable graphics layers
which can be inserted in neural network architectures. From spatial transformers
to differentiable graphics renderers, these new layers leverage the knowledge
acquired over years of computer vision and graphics research to build new and
more efficient network architectures. Explicitly modeling geometric priors and
constraints into neural networks opens up the door to architectures that can be
trained robustly, efficiently, and more importantly, in a self-supervised
fashion.
## Overview
At a high level, a computer graphics pipeline requires a representation of 3D
objects and their absolute positioning in the scene, a description of the
material they are made of, lights and a camera. This scene description is then
interpreted by a renderer to generate a synthetic rendering.
<div align="center">
<img border="0" src="https://storage.googleapis.com/tensorflow-graphics/git/readme/graphics.jpg" width="600">
</div>
In comparison, a computer vision system would start from an image and try to
infer the parameters of the scene. This allows the prediction of which objects
are in the scene, what materials they are made of, and their three-dimensional
position and orientation.
<div align="center">
<img border="0" src="https://storage.googleapis.com/tensorflow-graphics/git/readme/cv.jpg" width="600">
</div>
Training machine learning systems capable of solving these complex 3D vision
tasks most often requires large quantities of data. As labelling data is a
costly and complex process, it is important to have mechanisms to design machine
learning models that can comprehend the three dimensional world while being
trained without much supervision. Combining computer vision and computer
graphics techniques provides a unique opportunity to leverage the vast amounts
of readily available unlabelled data. As illustrated in the image below, this
can, for instance, be achieved using analysis by synthesis where the vision
system extracts the scene parameters and the graphics system renders back an
image based on them. If the rendering matches the original image, the vision
system has accurately extracted the scene parameters. In this setup, computer
vision and computer graphics go hand in hand, forming a single machine learning
system similar to an autoencoder, which can be trained in a self-supervised
manner.
<div align="center">
<img border="0" src="https://storage.googleapis.com/tensorflow-graphics/git/readme/cv_graphics.jpg" width="600">
</div>
Tensorflow Graphics is being developed to help tackle these types of challenges
and to do so, it provides a set of differentiable graphics and geometry layers
(e.g. cameras, reflectance models, spatial transformations, mesh convolutions)
and 3D viewer functionalities (e.g. 3D TensorBoard) that can be used to train
and debug your machine learning models of choice.
## Installing TensorFlow Graphics
See the [install](https://github.com/tensorflow/graphics/blob/master/tensorflow_graphics/g3doc/install.md)
documentation for instructions on how to install TensorFlow Graphics.
## API Documentation
You can find the API documentation
[here](https://github.com/tensorflow/graphics/blob/master/tensorflow_graphics/g3doc/api_docs/python/tfg.md).
## Compatibility
TensorFlow Graphics is fully compatible with the latest stable release of
TensorFlow, tf-nightly, and tf-nightly-2.0-preview. All the functions are
compatible with graph and eager execution.
## Debugging
Tensorflow Graphics heavily relies on L2 normalized tensors, as well as having
the inputs to specific function be in a pre-defined range. Checking for all of
this takes cycles, and hence is not activated by default. It is recommended to
turn these checks on during a couple epochs of training to make sure that
everything behaves as expected. This
[page](https://github.com/tensorflow/graphics/blob/master/tensorflow_graphics/g3doc/debug_mode.md)
provides the instructions to enable these checks.
## Colab tutorials
To help you get started with some of the functionalities provided by TF
Graphics, some Colab notebooks are available below and roughly ordered by
difficulty. These Colabs touch upon a large range of topics including, object
pose estimation, interpolation, object materials, lighting, non-rigid surface
deformation, spherical harmonics, and mesh convolutions.
NOTE: the tutorials are maintained carefully. However, they are not considered
part of the API and they can change at any time without warning. It is not
advised to write code that takes dependency on them.
### Beginner
<div align="center">
<table>
<tr>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/6dof_alignment.ipynb">Object pose estimation</a></th>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/intrinsics_optimization.ipynb">Camera intrinsics optimization</a></th>
</tr>
<tr>
<td align="center">
<a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/6dof_alignment.ipynb"><img border="0" src="https://storage.googleapis.com/tensorflow-graphics/notebooks/6dof_pose/thumbnail.jpg" width="200" height="200">
</a>
</td>
<td align="center">
<a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/intrinsics_optimization.ipynb"><img border="0" src="https://storage.googleapis.com/tensorflow-graphics/notebooks/intrinsics/intrinsics_thumbnail.png" width="200" height="200">
</a>
</td>
</tr>
</table>
</div>
### Intermediate
<div align="center">
<table>
<tr>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/interpolation.ipynb">B-spline and slerp interpolation</a></th>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/reflectance.ipynb">Reflectance</a></th>
<th style="text-align:center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/non_rigid_deformation.ipynb">Non-rigid surface deformation</a></th>
</tr>
<tr>
<td align="center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/interpolation.ipynb"><img border="0" src="https://storage.googleapis.com/tensorflow-graphics/notebooks/interpolation/thumbnail.png" width="200" height="200"> </td>
<td align="center"><a href="https://colab.research.google.com/github/tensorflow/graphics/blob/master/tensorflow_graphics/notebooks/reflectance.ipynb"><img border="0" src="https://storage.googleapis.com/tensorflow-graphics/notebooks/reflectance/thumbnail.png" wid
没有合适的资源?快使用搜索试试~ 我知道了~
PyPI 官网下载 | tfg-nightly-2021.8.26.tar.gz
1.该资源内容由用户上传,如若侵权请联系客服进行举报
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
2.虚拟产品一经售出概不退款(资源遇到问题,请及时私信上传者)
版权申诉
0 下载量 119 浏览量
2022-01-30
07:41:53
上传
评论
收藏 349KB GZ 举报
温馨提示
共260个文件
py:248个
txt:4个
so:2个
资源来自pypi官网。 资源全名:tfg-nightly-2021.8.26.tar.gz
资源推荐
资源详情
资源评论
收起资源包目录
PyPI 官网下载 | tfg-nightly-2021.8.26.tar.gz (260个子文件)
setup.cfg 38B
MANIFEST.in 42B
LICENSE 11KB
README.md 13KB
PKG-INFO 667B
PKG-INFO 667B
graph_convolution_test.py 32KB
quaternion_test.py 28KB
perspective_test.py 26KB
utils_test.py 26KB
models.py 24KB
rotation_matrix_3d_test.py 24KB
perspective.py 24KB
quaternion.py 24KB
math.py 23KB
graph_pooling_test.py 22KB
spherical_harmonics_test.py 21KB
ray.py 18KB
graph_convolution.py 18KB
utils.py 17KB
axis_angle_test.py 17KB
shape.py 17KB
asserts_test.py 16KB
sampler.py 16KB
sampling.py 16KB
ray_test.py 15KB
test_case.py 15KB
splat.py 14KB
spherical_harmonics.py 14KB
rotation_matrix_3d.py 14KB
shape_test.py 14KB
sampler_test.py 14KB
graph_pooling.py 14KB
matting_test.py 14KB
normals_test.py 13KB
mesh_segmentation_dataio.py 13KB
axis_angle.py 13KB
graph_convolution.py 13KB
dual_quaternion_test.py 12KB
asserts.py 12KB
helpers.py 12KB
quadratic_radial_distortion_test.py 12KB
euler_test.py 12KB
dual_quaternion.py 12KB
graph_convolution_test.py 12KB
matting.py 12KB
pix3d.py 11KB
data_loaders.py 11KB
point_light_test.py 11KB
slerp.py 11KB
test_helpers.py 10KB
safe_ops.py 10KB
vector_test.py 10KB
model.py 10KB
bspline.py 10KB
slerp_test.py 10KB
triangle_test.py 10KB
barycentrics.py 10KB
test_helpers.py 10KB
pyramid.py 10KB
quadratic_radial_distortion.py 10KB
rotation_matrix_2d_test.py 10KB
normals.py 9KB
euler.py 9KB
levenberg_marquardt.py 9KB
mipmap.py 9KB
as_conformal_as_possible.py 9KB
pyramid_test.py 9KB
rotation_matrix_2d.py 9KB
weighted_test.py 9KB
math_helpers_test.py 9KB
rasterization_backend.py 9KB
pointnet.py 8KB
point_light.py 8KB
point_test.py 8KB
blinn_phong_test.py 8KB
phong_test.py 8KB
utils.py 8KB
threejs_visualization.py 8KB
as_conformal_as_possible_test.py 8KB
lambertian_test.py 7KB
bspline_test.py 7KB
shapenet.py 7KB
transformer.py 7KB
splat_test.py 7KB
safe_ops_test.py 7KB
sampling_test.py 7KB
eval.py 7KB
camera_feature_test.py 7KB
weighted.py 7KB
blinn_phong.py 7KB
camera_feature.py 7KB
trilinear_test.py 7KB
rasterization_test_utils.py 7KB
phong.py 7KB
rasterization_backend.py 7KB
math_helpers.py 6KB
rasterization_backend_test_base.py 6KB
framebuffer.py 6KB
train.py 6KB
共 260 条
- 1
- 2
- 3
资源评论
挣扎的蓝藻
- 粉丝: 13w+
- 资源: 15万+
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功