seq: train_seq = ['1','2','3','4','6','7','8','9','10','13','14','15','16','18','20', '21','22','23','24','25','28','29','

Identity layer to replace last fully connected layer

The model can behave as an encoder (with only self-attention) following the architecture described in [Attention is all you need](https://ar

seq: train_seq = ['1','2','3','4','6','7','8','9','10','13','14','15','16','18','20', '21','22','23','24','25','28','29','

VisualBert Classification Model vocab_size = tokenizer length encoder_layer = 6 n_heads = 8 num_class = number of cl

Construct the embeddings from word, position and token_type embeddings and visual embeddings.

Output type of [`VisualBertForPreTraining`]. Args: loss (*optional*, returned when `labels` is provided, `torch.FloatTensor` of shap

Keeps track of most recent, average, sum, and count of a metric.

An abstract class to handle weights initialization and a simple interface for downloading and loading pretrained models.