(vocab_size=None)

(self, model, net_out, target)

(self, input_size, kernel_size=1, padding=0, num_heads=1, weight_softmax=False, bias=False, w

(self, args)

(self, params, lr=None, eps=(1e-30, 1e-3), clip_threshold=1.0, decay_rate=-0.8, beta1=None, w

(self, params, lr=required, momentum=0, weight_decay=0)

(self, params, lr=2e-3, betas=(0.9, 0.999), eps=1e-8, weight_decay=0, bias_correction=True)

( self, pad='<pad>', eos='</s>', unk='<unk>', mask='<mask>', c

( self, sample_rate, max_sample_size=None, min_sample_size=None, shuff

(self, models)

(self, args, encoder)

(self, encoder, decoder)

(self, args, dictionary, embed_tokens)

(self, block, layers, num_classes=10)

(self, block, layers, num_classes=10)

(self)