Creates a 3x3 camera intrinsics matrix from the camera field of view, specified in degrees. Note the intrinsics are returned as normalized by

https://github.com/zhhoper/DPR/blob/master/utils/utils_SH.py get SH basis based on normal normal is a Nx3 matrix retu

Fast CUDA implementation of `bias_act()` using custom ops.

Slow reference implementation of `bias_act()` using standard TensorFlow ops.

r"""Check that the given object is pickleable, raising an exception if it is not. This function is expected to be considerably more efficient

Slow and memory-inefficient reference implementation of `filtered_lrelu()` using existing `upfirdn2n()` and `bias_act()` ops.

r"""Query the source code of a given Python module.

r"""Get or create a Python module for the given source code.

r"""Synchronize the global cumulative counters across devices and processes. Called internally by `Collector.update()`.

Slow reference implementation of `upfirdn2d()` using standard PyTorch ops.

r"""Returns the averages accumulated between the last two calls to `update()` as an `dnnlib.EasyDict`. The contents are as follows:

Convert axis-angle representation to rotation matrix. Args: theta: size = [B, 3] Returns: Rotation matrix corresponding to the

Calculate quality metrics for previous training run or pretrained network pickle. Examples: \b # Previous training run: look up options

Finds the python object with the given name and calls it as a function.

Convert an image dataset into a dataset archive usable with StyleGAN2 ADA PyTorch. The input dataset format is guessed from the --source argument

Convert legacy network pickle into the native PyTorch format. The tool is able to load the main network configurations exported using the TensorF

Find camera translation that brings 3D joints S closest to 2D the corresponding joints_2d. Input: S: (25, 3) 3D joint locations jo

Render a latent vector interpolation video. Examples: \b # Render a 4x2 grid of interpolations for seeds 0 through 31. python gen_vi

Generate images using pretrained network pickle. Examples: \b # Generate an image using pre-trained FFHQ model. python gen_samples.p

Defines planes by the three vectors that form the "axes" of the plane. Should work with arbitrary number of planes and planes of arbitrar

https://github.com/zhhoper/DPR/blob/master/testNetwork_demo_512.py

Finds the python object with the given name.

https://github.com/zhhoper/DPR/blob/master/utils/utils_SH.py get shading based on normals and SH normal is Nx3 matrix

Determine whether the given object is a top-level function, i.e., defined at module scope using 'def'.

Determine whether the given object is a valid URL string.

Train a GAN using the techniques described in the paper "Alias-Free Generative Adversarial Networks". Examples: \b # Train StyleGAN3

r"""Returns the number of scalars that were accumulated for the given statistic between the last two calls to `update()`, or zero if n

r"""Class decorator that extends a given class to save its source code when pickled. Example: from torch_utils import persistence

Does a projection of a 3D point onto a batch of 2D planes, returning 2D plane coordinates. Takes plane axes of shape n_planes, 3, 3

Convert quaternion coefficients to rotation matrix. Args: quat: size = [B, 4] 4 <===>(w, x, y, z) Returns: Rotation matrix cor

r"""Broadcasts the given set of scalars to all interested instances of `Collector`, across device and process boundaries. This function is ex

Return depths of importance sampled points along rays. See NeRF importance sampling for more.

Sample @N_importance samples from @bins with distribution defined by @weights. Inputs: bins: (N_rays, N_samples_+1) where

for the sh matrix created by sh tools, we create the vector of the sh

convert vector of sh to matrix