deeplotx 0.5.5__py3-none-any.whl → 0.5.6__py3-none-any.whl

deeplotx/encoder/encoder.py

@@ -25,7 +25,7 @@ class Encoder(nn.Module):
         self.embed_dim = self.encoder.config.max_position_embeddings
         logger.debug(f'{Encoder.__name__} initialized on device: {self.device}.')
 
-    def forward(self, input_ids: torch.Tensor, attention_mask: torch.Tensor) -> torch.Tensor:
+    def forward(self, input_ids: torch.Tensor, attention_mask: torch.Tensor, *args, **kwargs) -> torch.Tensor:
         def _encoder(_input_tup: tuple[torch.Tensor, torch.Tensor]) -> torch.Tensor:
             return self.encoder.forward(_input_tup[0], attention_mask=_input_tup[1]).last_hidden_state[:, 0, :]
 

deeplotx/encoder/long_text_encoder.py

@@ -25,6 +25,10 @@ class LongTextEncoder(Encoder):
     def __chunk_embedding(self, idx: int, x: torch.Tensor, mask: torch.Tensor) -> tuple[int, torch.Tensor]:
         return idx, super().forward(x, attention_mask=mask)
 
+    @override
+    def forward(self, text: str, flatten: bool = False, *args, **kwargs) -> torch.Tensor:
+        return self.encode(text=text, flatten=flatten)
+
     @override
     def encode(self, text: str, flatten: bool = False) -> torch.Tensor:
         def postprocess(tensors: list[torch.Tensor], _flatten: bool) -> torch.Tensor:

deeplotx/trainer/text_binary_classification_trainer.py

@@ -31,7 +31,7 @@ class TextBinaryClassifierTrainer(BaseTrainer):
             positive_texts = positive_texts[:min_length]
             negative_texts = negative_texts[:min_length]
         all_texts = positive_texts + negative_texts
-        text_embeddings = [self._long_text_encoder.encode(x, flatten=False, use_cache=True) for x in all_texts]
+        text_embeddings = [self._long_text_encoder.encode(x, flatten=False) for x in all_texts]
         feature_dim = text_embeddings[0].shape[-1]
         dtype = text_embeddings[0].dtype
         labels = ([torch.tensor([1.], dtype=dtype, device=self.device) for _ in range(len(positive_texts))]

{deeplotx-0.5.5.dist-info → deeplotx-0.5.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: deeplotx
-Version: 0.5.5
+Version: 0.5.6
 Summary: Easy-2-use long text NLP toolkit.
 Requires-Python: >=3.10
 Description-Content-Type: text/markdown
@@ -265,7 +265,8 @@ Dynamic: license-file
     long_text_encoder = LongTextEncoder(
         max_length=2048,  # 最大文本大小, 超出截断
         chunk_size=448,  # 块大小 (按 Token 计)
-        overlapping=32  # 块间重叠大小 (按 Token 计)
+        overlapping=32,  # 块间重叠大小 (按 Token 计)
+        cache_capacity=512  # 缓存大小
     )
 
     trainer = TextBinaryClassifierTrainer(

{deeplotx-0.5.5.dist-info → deeplotx-0.5.6.dist-info}/RECORD

@@ -1,7 +1,7 @@
 deeplotx/__init__.py,sha256=6El66QXHDrgNMsNIG9bG97WO8BhPK5btXbTikzx2ce4,1087
 deeplotx/encoder/__init__.py,sha256=BrsF5_4O-4pfihYF2wjExDOoAY-03kGJTH-Mhez4tsE,129
-deeplotx/encoder/encoder.py,sha256=p1e4Dx3-Ghdl0MGNalr0D_OnafwaJnbhscEDVq-y73A,2400
-deeplotx/encoder/long_text_encoder.py,sha256=GatkOF1QQHLtvyuikfCP4xpzfDvszJJyonaS9f7wSxg,3401
+deeplotx/encoder/encoder.py,sha256=2e1ZnZ37PkFQ5BePndmq42xmHp8YZh65Q1bd0dxejPI,2417
+deeplotx/encoder/long_text_encoder.py,sha256=4445FdVwubvDiebCWoT9wAUpYlMj6Mmd0OBxbFZ3ZIo,3565
 deeplotx/encoder/longformer_encoder.py,sha256=A8FXqd4mdHxSn_o_R689XtpT73ISDT788EgMQRGLC2g,1822
 deeplotx/nn/__init__.py,sha256=CS0UwyYKa8wI6vu6FBIYxvm-HAmw39MTMFlZDtqi6UA,444
 deeplotx/nn/auto_regression.py,sha256=7P63opWCWMqE2DigwbsL6kfXtFtJPz00Yo1RqflBz4A,572
@@ -19,12 +19,12 @@ deeplotx/similarity/set.py,sha256=zhGFxtSIXlWqvipBYzoiPahp4g0boAIoUiMfG0wl07A,68
 deeplotx/similarity/vector.py,sha256=WVbDHqykt-fvuILVrhUCtIFAOEjY_zvttrXGM9eylG0,1125
 deeplotx/trainer/__init__.py,sha256=Fl5DR9UecQc5VtBcczU9sx_HtPNoFohpuELOh-Jrsks,77
 deeplotx/trainer/base_trainer.py,sha256=z0MeAT-rRYmjeBXt0ckt7J1itYArR0Cx02wHesXUoZE,385
-deeplotx/trainer/text_binary_classification_trainer.py,sha256=BNBQdpaD8nB1dQv8naHNIravNcQC8JjOMqD-WRSrUH0,4931
+deeplotx/trainer/text_binary_classification_trainer.py,sha256=umuvikc09Op4SB43EqmYo8W3ung8DBjEOrMG3hCVFz8,4915
 deeplotx/util/__init__.py,sha256=JxqAK_WOOHcYVSTHBT1-WuBwWrPEVDTV3titeVWvNUM,74
 deeplotx/util/hash.py,sha256=qbNU3RLBWGQYFVte9WZBAkZ1BkdjCXiKLDaKPN54KFk,662
 deeplotx/util/read_file.py,sha256=ptzouvEQeeW8KU5BrWNJlXw-vFXVrpS9SkAUxsu6A8A,612
-deeplotx-0.5.5.dist-info/licenses/LICENSE,sha256=IwGE9guuL-ryRPEKi6wFPI_zOhg7zDZbTYuHbSt_SAk,35823
-deeplotx-0.5.5.dist-info/METADATA,sha256=QE1R1jodTrnPFY7cbu4mQNPt8_BgKNJuHoSDswopueo,10880
-deeplotx-0.5.5.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-deeplotx-0.5.5.dist-info/top_level.txt,sha256=hKg4pVDXZ-WWxkRfJFczRIll1Sv7VyfKCmzHLXbuh1U,9
-deeplotx-0.5.5.dist-info/RECORD,,
+deeplotx-0.5.6.dist-info/licenses/LICENSE,sha256=IwGE9guuL-ryRPEKi6wFPI_zOhg7zDZbTYuHbSt_SAk,35823
+deeplotx-0.5.6.dist-info/METADATA,sha256=vBUVgshgGG_vZmJT07C7CPEhMfBUmwbCtsIY06D_14g,10925
+deeplotx-0.5.6.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+deeplotx-0.5.6.dist-info/top_level.txt,sha256=hKg4pVDXZ-WWxkRfJFczRIll1Sv7VyfKCmzHLXbuh1U,9
+deeplotx-0.5.6.dist-info/RECORD,,