The APMeter measures the average precision per class. The APMeter is designed to operate on `NxK` Tensors `output` and `target`, and opti

This HTML class allows us to save images and write texts into a single HTML file. It consists of functions such as <add_header> (add a text head

Applies the mish function element-wise: mish(x) = x * tanh(softplus(x)) = x * tanh(ln(1 + exp(x))) SRC: https://github.com/digantamisra98

For word-level embeddings, we convert words that are absent from the embedding lookup table to a canonical tokens (and then re-check the table).

Trainer class Note: Inherited from BaseTrainer.

The APMeter measures the average precision per class. The APMeter is designed to operate on `NxK` Tensors `output` and `target`, and opti

Computes and stores the average and current value

Base class for all models

Base class for all trainers

r"""Set the learning rate of each parameter group using a cosine annealing schedule, where :math:`\eta_{max}` is set to the initial lr and :ma

This model wraps various forms of GrOVLE embeddings: Args: mirror: the URL of a mirror from which the embeddings can be downloaded

This model produces text embeddings trained on HowTo100M using: A. Miech, J.-B. Alayrac, L. Smaira, I. Laptev, J. Sivic and A. Zisserman, En

This class wraps the embedding of text provided by HuggingFace pretrained models : The models can be found here: https://huggingface.co/trans

Meters provide a way to keep track of important statistics in an online manner. This class is abstract, but provides a sGktandard interface for al

This class includes several functions that can display/save images. It uses a Python library 'visdom' for display, and a Python library 'dominate

This model embeds text using the google-released implementation of the word2vec model introduced in: Mikolov, T., Sutskever, I., Chen, K.