lucid-dl 2.7.9__tar.gz → 2.8.0__tar.gz

{lucid_dl-2.7.9/lucid_dl.egg-info → lucid_dl-2.8.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lucid-dl
-Version: 2.7.9
+Version: 2.8.0
 Summary: Lumerico's Comprehensive Interface for Deep Learning
 Home-page: https://github.com/ChanLumerico/lucid
 Author: ChanLumerico

{lucid_dl-2.7.9 → lucid_dl-2.8.0}/lucid/nn/modules/__init__.py

@@ -10,3 +10,4 @@ from .attention import *
 from .transformer import *
 from .sparse import *
 from .einops import *
+from .rnn import *

lucid_dl-2.8.0/lucid/nn/modules/rnn.py

@@ -0,0 +1,97 @@
+from typing import Literal
+
+import lucid
+import lucid.nn as nn
+import lucid.nn.functional as F
+
+from lucid._tensor import Tensor
+
+from .activation import Tanh, ReLU
+
+
+__all__ = ["RNNCell"]
+
+
+def _get_activation(nonlinearity: str) -> type[nn.Module]:
+    if nonlinearity == "tanh":
+        return Tanh
+    elif nonlinearity == "relu":
+        return ReLU
+    else:
+        raise ValueError(
+            f"Invalid nonlinearity '{nonlinearity}'. "
+            "Supported nonlinearities are 'tanh' and 'relu'."
+        )
+
+
+class RNNCell(nn.Module):
+    def __init__(
+        self,
+        input_size: int,
+        hidden_size: int,
+        bias: bool = True,
+        nonlinearity: Literal["tanh", "relu"] = "tanh",
+    ) -> None:
+        super().__init__()
+        self.input_size = input_size
+        self.hidden_size = hidden_size
+        self.bias = bias
+        self.nonlinearity = _get_activation(nonlinearity)()
+
+        sqrt_k = 1.0 / (hidden_size**0.5)
+        self.weight_ih = nn.Parameter(
+            lucid.random.uniform(-sqrt_k, sqrt_k, (self.hidden_size, self.input_size))
+        )
+        self.weight_hh = nn.Parameter(
+            lucid.random.uniform(-sqrt_k, sqrt_k, (self.hidden_size, self.hidden_size))
+        )
+
+        if self.bias:
+            self.bias_ih = nn.Parameter(
+                lucid.random.uniform(-sqrt_k, sqrt_k, self.hidden_size)
+            )
+            self.bias_hh = nn.Parameter(
+                lucid.random.uniform(-sqrt_k, sqrt_k, self.hidden_size)
+            )
+        else:
+            self.bias_ih = None
+            self.bias_hh = None
+
+    def forward(self, input_: Tensor, hx: Tensor | None = None) -> Tensor:
+        if input_.ndim not in (1, 2):
+            raise ValueError(
+                "RNNCell expected input with 1 or 2 dimensions, "
+                f"got {input_.ndim} dimensions"
+            )
+
+        is_batched = input_.ndim == 2
+        if not is_batched:
+            input_ = input_.unsqueeze(axis=0)
+        batch_size = input_.shape[0]
+
+        if hx is None:
+            hx = lucid.zeros(
+                batch_size, self.hidden_size, dtype=input_.dtype, device=input_.device
+            )
+        else:
+            if hx.ndim not in (1, 2):
+                raise ValueError(
+                    "RNNCell expected hidden state with 1 or 2 dimensions, "
+                    f"got {hx.ndim} dimensions"
+                )
+            if hx.ndim == 1:
+                hx = hx.unsqueeze(axis=0)
+
+            if hx.shape[0] != batch_size or hx.shape[1] != self.hidden_size:
+                raise ValueError(
+                    "RNNCell expected hidden state with shape "
+                    f"({batch_size}, {self.hidden_size}), got {hx.shape}"
+                )
+
+        hy = F.linear(input_, self.weight_ih, self.bias_ih)
+        hy += F.linear(hx, self.weight_hh, self.bias_hh)
+        ret = self.nonlinearity(hy)
+
+        if not is_batched:
+            ret = ret.squeeze(axis=0)
+        return ret

{lucid_dl-2.7.9 → lucid_dl-2.8.0}/lucid/optim/lr_scheduler/_schedulers.py

@@ -298,4 +298,6 @@ class NoamScheduler(LRScheduler):
         decay_term = step_num**-0.5
         lr_factor = scale * min(decay_term, warmup_term)
 
-        return [base_lr * lr_factor for base_lr in self.base_lrs]
+        # Noam's schedule computes the absolute learning rate, so we ignore
+        # the optimizer's initial lr (base_lr) when returning the new values.
+        return [lr_factor for _ in self.base_lrs]

{lucid_dl-2.7.9 → lucid_dl-2.8.0/lucid_dl.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: lucid-dl
-Version: 2.7.9
+Version: 2.8.0
 Summary: Lumerico's Comprehensive Interface for Deep Learning
 Home-page: https://github.com/ChanLumerico/lucid
 Author: ChanLumerico

{lucid_dl-2.7.9 → lucid_dl-2.8.0}/lucid_dl.egg-info/SOURCES.txt

@@ -102,6 +102,7 @@ lucid/nn/modules/linear.py
 lucid/nn/modules/loss.py
 lucid/nn/modules/norm.py
 lucid/nn/modules/pool.py
+lucid/nn/modules/rnn.py
 lucid/nn/modules/sparse.py
 lucid/nn/modules/transformer.py
 lucid/nn/modules/vision.py

{lucid_dl-2.7.9 → lucid_dl-2.8.0}/setup.py

@@ -5,7 +5,7 @@ with open("README.md", "r") as fh:
 
 setuptools.setup(
     name="lucid-dl",
-    version="2.7.9",
+    version="2.8.0",
     author="ChanLumerico",
     author_email="greensox284@gmail.com",
     description="Lumerico's Comprehensive Interface for Deep Learning",