Get the distribution q(x_t | x_0). :param x_start: the [N x C x ...] tensor of noiseless inputs. :param t: the number of diff

Importance-sample timesteps for a batch. :param batch_size: the number of timesteps. :param device: the torch device to save

Create a list of timesteps to use from an original diffusion process, given the number of timesteps we want to take from equally-sized portio

Create sinusoidal timestep embeddings. :param timesteps: a 1-D Tensor of N indices, one per batch element. These may b

Update the reweighting using losses from a model. Sub-classes should override this method to update the reweighting using lo

Update the reweighting using losses from a model. Call this method from each rank with a batch of timesteps and the correspo

Get a numpy array of weights, one per diffusion step. The weights needn't be normalized, but must be positive.

Compute the entire variational lower-bound, measured in bits-per-dim, as well as other related quantities. :param model: the

calculate SSIM the same outputs as MATLAB's img1, img2: [0, 255]

Convert primitive modules to float16.

Convert primitive modules to float32, undoing convert_module_to_f16().

Convert the torso of the model to float32.

Sample x_{t+1} from the model using DDIM reverse ODE.

Generate samples from the model using DDIM. Same usage as p_sample_loop().

Get the device to use for torch.distributed.

dict to string for logger

Write all of the diagnostics from the current iteration

Apply the module to `x` given `emb` timestep embeddings.

Apply the block to a Tensor, conditioned on a timestep embedding. :param x: an [N x C x ...] Tensor of features. :param emb:

Apply QKV attention. :param qkv: an [N x (H * 3 * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor aft

Apply QKV attention. :param qkv: an [N x (3 * H * C) x T] tensor of Qs, Ks, and Vs. :return: an [N x (H * C) x T] tensor aft

Apply the model to an input batch. :param x: an [N x C x ...] Tensor of inputs. :param timesteps: a 1-D batch of timesteps.

Get directory that log files are being written to. will be None if there is no output directory (i.e., if you didn't call start)

Get a pre-defined beta schedule for the given name. The beta schedule library consists of beta schedules which remain similar in the limi

Load a PyTorch file without redundant fetches across MPI ranks.

Log the model checkpoint as W&B artifacts current_epoch: the current epoch current_step: the current batch step

Add data row-wise to the initialized table.

Log the table

Log image array onto W&B. key_name: name of the key image_array: numpy array of image.

Log list of image array onto W&B key_name: name of the key list_images: list of numpy image arrays

Log train/validation metrics onto W&B. metrics: dictionary of metrics to be logged