post-release v0.1.1 updates.

Reviewed By: nikhilaravi

Differential Revision: D20218481

fbshipit-source-id: b153282cc30ad75de970c89ae64526b6be62ee95
This commit is contained in:
Jeremy Reizenstein 2020-03-09 06:35:10 -07:00 committed by Facebook Github Bot
parent 112d32eaf0
commit 5a1d7143d8
2 changed files with 25 additions and 11 deletions

View File

@ -45,10 +45,10 @@ pip install scikit-image matplotlib imageio
pip install black isort flake8 flake8-bugbear flake8-comprehensions
```
## Build/Install Pytorch3d
## Installing prebuilt binaries for Pytorch3d
After installing the above dependencies, run one of the following commands:
### 1. Install from Anaconda Cloud
### 1. Install with CUDA support from Anaconda Cloud, on Linux only
```
# Anaconda Cloud
@ -60,14 +60,26 @@ Or, to install a nightly (non-official, alpha) build:
# Anaconda Cloud
conda install pytorch3d -c pytorch3d-nightly
```
### 2. Install without CUDA support from PyPI, on Linux and Mac
```
pip install pytorch3d
```
### 2. Install from GitHub
## Building / installing from source.
CUDA support will be included if CUDA is enabled or if the environment variable
`FORCE_CUDA` is set to `1`.
### 1. Install from GitHub
```
pip install 'git+https://github.com/facebookresearch/pytorch3d.git'
# (add --user if you don't have permission)
```
### 3. Install from a local clone
**Install from Github on macOS:**
```
MACOSX_DEPLOYMENT_TARGET=10.14 CC=clang CXX=clang++ pip install 'git+https://github.com/facebookresearch/pytorch3d.git'
```
### 2. Install from a local clone
```
git clone https://github.com/facebookresearch/pytorch3d.git
cd pytorch3d && pip install -e .

View File

@ -38,13 +38,15 @@ class MeshRenderer(nn.Module):
def forward(self, meshes_world, **kwargs) -> torch.Tensor:
"""
Render a batch of images from a batch of meshes by rasterizing and then shading.
Render a batch of images from a batch of meshes by rasterizing and then
shading.
NOTE: If the blur radius for rasterization is > 0.0, some pixels can have one or
more barycentric coordinates lying outside the range [0, 1]. For a pixel with
out of bounds barycentric coordinates with respect to a face f, clipping is required
before interpolating the texture uv coordinates and z buffer so that the colors and
depths are limited to the range for the corresponding face.
NOTE: If the blur radius for rasterization is > 0.0, some pixels can
have one or more barycentric coordinates lying outside the range [0, 1].
For a pixel with out of bounds barycentric coordinates with respect to a
face f, clipping is required before interpolating the texture uv
coordinates and z buffer so that the colors and depths are limited to
the range for the corresponding face.
"""
fragments = self.rasterizer(meshes_world, **kwargs)
raster_settings = kwargs.get(