Collects the state dict and dump to disk.

Scale the box with horizontal and vertical scaling factors

dynamically choosing preprocessors during runtime

Turn a list of integer scalars or integer Tensor scalars into a vector, in a way that's both traceable and scriptable. In tracing, `x` sh

Single channel value as output gray value. gray = single(r,g,b). @param img:ndarray,Input image data on range[0,255]. @param channel: int

Rescales the image so that the following conditions are met: 1. Both dimensions (height and width) are divisible by 'factor'. 2. The total n

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

Split a list into n (roughly) equal-sized chunks

strip the classifier head when pretrained model is being loaded. Args: key (string): key to be striped Returns:

Suppress printing on the current device. Force printing with `force=True`.

Make sure we are sharing the input and output embeddings. Export to TorchScript can't handle parameter sharing so we are cloning them

Make sure we are sharing the input and output embeddings. Export to TorchScript can't handle parameter sharing so we are cloning them

Convert the configuration to dictionary.

Implements Top2Gating on logits.

Implements Top2Gating on logits.

Recursively unwraps a model from potential containers (as used in distributed training). Args: model (`torch.nn.Module`): The model

r"""Updates node embeddings in analogy to :math:`\gamma_{\mathbf{\Theta}}` for each node :math:`i \in \mathcal{V}`. Takes in t

Copy data from other Meter. Usage:: meter1 = Meter(delimiter=", ") meter1.update({"cls_loss": 0.99, "reg_loss": 0.88

Given path d, go up n dirs from d and return that path

Visualize a set of images using torchvision's make grid function. Expects PIL images which it will convert to tensor and optionally resize them. I

Args: windows: (num_windows*B, window_size, window_size, C) window_size (int): Window size H (int): Height of image

Convert a word to its index according to vocabulary Args: word (str): Word to be converted to index. Returns: