原书出处
Natural Language Processing in Action, Second Edition
self.convolvers = [] self.poolers = [] total_out_len = 0 for i, kernel_len in enumerate(self.kernel_lengths): self.convolvers.append( nn.Conv1d(in_channels=self.embedding_size, out_channels=self.out_channels, kernel_size=kernel_len, stride=self.stride)) print(f'conv[{i}].weight.shape: {self.convolvers[-1].weight.shape}') conv_output_len = calc_conv_out_seq_len( seq_len=self.seq_len, kernel_len=kernel_len, stride=self.stride) print(f'conv_output_len: {conv_output_len}') self.poolers.append( nn.MaxPool1d(kernel_size=conv_output_len, stride=self.stride)) total_out_len += calc_conv_out_seq_len(
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Natural Language Processing in Action, Second Edition/_epub-src/OEBPS/Text/chapter-7.html
EPUB SHA-256:0e9a35e49ca446e322e5524e53f39fb6bee5b2b23d9cda10ef052aca770b0b36