derwind https://blog.hatena.ne.jp/derwind/ らんだむな記憶 https://randommemory.hatenablog.com/ machine_learning 分類器への入力部分を見ると、 class AttentionDecoder: def forward(self, xs, enc_hs): ... # enc_hs = ['吾輩', 'は', ...], dec_hs = ['i', 'am', ...], c = '吾輩' c = self.attention_forward(enc_hs, dec_hs) # '吾輩'+'i' out = np.concatename((c, dec_hs), axis=") score = self.affine.forward(out) return score となっているので、attention … 190 <iframe src="https://hatenablog-parts.com/embed?url=https%3A%2F%2Frandommemory.hatenablog.com%2Fentry%2F2022%2F03%2F05%2F003017" title="Attention (4) - らんだむな記憶" class="embed-card embed-blogcard" scrolling="no" frameborder="0" style="display: block; width: 100%; height: 190px; max-width: 500px; margin: 10px 0px;"></iframe> Hatena Blog https://hatena.blog 2022-03-05 00:30:17 rich https://randommemory.hatenablog.com/entry/2022/03/05/003017 1.0 100%