(self, seqs)

(self, data)

(data, arange, batch_size)

(data,arange,dataset)

(self, q, k, v, mask=None)

(self, q, k, v, mask=None)

(self, x, y)

(self, seqs)

(self, seqs, segs, seqs_, nsp_labels)

(self, x, y)

(self, seqs, segs, seqs_, loss_mask, nsp_labels)

(self, x, y)

(self,x,y)

(self,x,y)

(self,x,y)

(self,x,y)

(self,seqs)

(self, seqs, segs, seqs_, nsp_labels)

(self, x, y)

(self,seqs,segs,seqs_, loss_mask,nsp_labels)

(self,x,y)

()

(model, data)

()

()

(model, data, step)

(model, data, step)

(model, data, step=10000, name="bert")

(model, data)

()

()

()

(model: Transformer, data)

()

()

(model,data)

()

()

()

(emb_dim=32,n_layer=3,n_head=4)

()

(model,data)

(self,x,y)

(self,x,y)

(self,x,y)

(self, x, y, seq_len)

(self, x, y, seq_len)

(self, x, y, seq_len)

(case=0)

(case=0)

(self, src, v2i, i2v)

(self, src, i2v, v2i)

(self, src, v2i, i2v)

(self, index)

(self,idx)

(self, index)

(self, enc_v_dim, dec_v_dim, emb_dim, units, attention_layer_size, max_pred_len, start_token, end_token)

(self, v_dim, emb_dim)

(self, enc_v_dim, dec_v_dim, emb_dim, units, max_pred_len, start_token, end_token)

(self, enc_v_dim, dec_v_dim, emb_dim, units, max_pred_len, start_token, end_token)

(self, model_dim, max_len, n_layer, n_head, n_vocab, lr, max_seg=3, drop_rate=0.1, padding_idx=0)

(self, n)

(self, data_dir="./MRPC/", rows=None, proxy=None)

(self, data_dir="./MRPC/", rows=None, proxy=None)

(self, x, y, v2i, i2v)

(self, v_dim, emb_dim, units, n_layers, lr)

(self, model_dim, max_len, n_layer, n_head, n_vocab, lr, max_seg=3, drop_rate=0.1, padding_idx=0)

(self, n_head, model_dim, drop_rate)

(self, model_dim)

(self, n_head, model_dim, drop_rate)

(self, n_head, model_dim, drop_rate)

(self, n_head, model_dim, drop_rate, n_layer)

(self, max_len, model_dim, n_vocab)

(self, model_dim, max_len, n_layer, n_head, n_vocab, drop_rate=0.1, padding_idx=0)

(self, model_dim, max_len, n_layer, n_head, n_vocab, lr, max_seg=3, drop_rate=0.1, padding_idx=0)

(self, v_dim, emb_dim)

(self,dec_v_dim,**kwargs)

(self, data, log_dir='logs/seq2seq_attention', histogram_freq=1, write_graph=True, write_images=True,

(self, data, log_dir='logs/CBOW', histogram_freq=1, write_graph=True, write_images=True, embe

(self, data, log_dir='logs/seq2seq', histogram_freq=1, write_graph=True, write_images=True, e

(self, data, log_dir='logs/cnn-lm', histogram_freq=1, write_graph=True, write_images=True, em

(self, n_head)

(self, n_head)

(self, n_head, n_layer)

(self, n_head)

(self, n_head, n_layer)

(self, max_len, model_dim, n_vocab)

(self, model_dim, max_len, n_encoder_layer, n_decoder_layer, n_head, n_vocab, padding_idx=0)

(self, data, log_dir='logs/transformer', histogram_freq=1, write_graph=True, write_images=True,

(self, data, log_dir='logs/skip-gram', histogram_freq=1, write_graph=True, write_images=True,

(self,enc_v_dim, dec_v_dim, emb_dim, units, max_pred_len, start_token, end_token)

(self,enc_v_dim, dec_v_dim, emb_dim, units, max_pred_len, start_token, end_token)

(self,v_dim,emb_dim)

(self,enc_v_dim, dec_v_dim, emb_dim, units, max_pred_len, start_token, end_token)

(self,n)

(self,x,y,v2i,i2v)

(self, data_dir="./MRPC/", rows=None, proxy=None)

(self,data_dir="./MRPC/",rows = None, proxy= None)

(self, v_dim, emb_dim, units, n_layers, lr)

(self, model_dim, max_len, num_layer, num_head, n_vocab, lr, max_seg=3, drop_rate=0.2,padding_idx=0)