Set robust tokens for attack

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

Flatten a torch tensor `x` and convert it to numpy.

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

### Args: module: module to prune name: parameter name within `module` on which pruning will act. amount: decide the amou

Construct a Variance Preserving SDE. Args: model: diffusion model score_type: [guided_diffusion, score_sde, ddpm]

Construct a Variance Preserving SDE. Args: model: diffusion model score_type: [guided_diffusion, score_sde, ddpm]

Construct a Variance Preserving SDE. Args: model: diffusion model score_type: [guided_diffusion, score_sde, ddpm]

Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array or a func. :param timesteps: a tensor of i

Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array or a func. :param timesteps: a tensor of i

Extract values from a 1-D numpy array for a batch of indices. :param arr: the 1-D numpy array or a func. :param timesteps: a tensor of i

x: input tensor, shape (b, c, w, h). dhf_indicator: input tensor, shape(b,), indicating which image is applied to dhf.

Generate masked perturbations w.r.t. the patchout strategy (This code is copied from https://github.com/zhipeng-wei/PNA-PatchOut)

get image path list from image folder

Returns a (1 - alpha) lower confidence bound on a bernoulli proportion. This function uses the Clopper-Pearson method. :param NA: t