the continuous GPT model

base GPT config, params common to all GPT versions

A single linear layer which does a 1x1 conv

InceptionC block patched for FID computation

InceptionA block patched for FID computation

this code is borrowed from https://github.com/ajbrock/BigGAN-PyTorch MIT License Copyright (c) 2019 Andy Brock

3D Video to Patch Embedding

an unassuming Transformer block

Embeds text caption into vector representations. Also handles label dropout for classifier-free guidance.

A vanilla multi-head masked self-attention layer with a projection at the end. It is possible to use torch.nn.MultiheadAttention here but I a

Calculate pairwise distances between vectors. Adapted from https://github.com/kynkaat/improved-precision-and-recall-metric/blob/f60f25e5ad93

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

Drop paths (Stochastic Depth) per sample (when applied in main path of residual blocks).

First InceptionE block patched for FID computation

Second InceptionE block patched for FID computation

Pretrained InceptionV3 network returning feature maps

Embeds class labels into vector representations. Also handles label dropout for classifier-free guidance.

Embeds class labels into vector representations. Also handles label dropout for classifier-free guidance.

A helper for comparing manifolds of feature vectors. Adapted from https://github.com/kynkaat/improved-precision-and-recall-metric/blob/f60f2

Defines a PatchGAN discriminator as in Pix2Pix --> see https://github.com/junyanz/pytorch-CycleGAN-and-pix2pix/blob/master/models/networks.py

see https://github.com/MishaLaskin/vqvae/blob/d761a999e2267766400dc646d82d3ac3657771d4/models/quantizer.py __________________________________

Generic dataset for videos files stored in folders. Videos of the same class are expected to be stored in a single folder. Multiple folders