comfi-fast-grnn-torch 0.0.1__tar.gz → 0.0.3__tar.gz

comfi_fast_grnn_torch-0.0.3/MANIFEST.in

@@ -0,0 +1 @@
+include README.md

{comfi_fast_grnn_torch-0.0.1 → comfi_fast_grnn_torch-0.0.3}/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: comfi_fast_grnn_torch
-Version: 0.0.1
-Summary: A PyTorch implementation of Fast ULCNet
+Version: 0.0.3
+Summary: A PyTorch implementation of Comfi-FastGRNN
 Author-email: Nicolas Arrieta Larraza <NIAL@bang-olufsen.dk>, Niels de Koeijer <NEMK@bang-olufsen.dk>
 License: MIT
 Project-URL: Homepage, https://github.com/narrietal/Fast-ULCNet
@@ -12,8 +12,8 @@ Requires-Dist: libsegmenter==1.0.4
 Requires-Dist: torchinfo==1.8.0
 Requires-Dist: CRM_pytorch==0.1.0
 
-# fast-ulcnet-torch
-Implements FastULCNet and Comfi-FastGRNN in torch.
+# comfi-fast-grnn-torch
+Implements Comfi-FastGRNN in torch.
 
 ## Usage
 
@@ -26,21 +26,9 @@ Here is how to use the layer with default settings in a standard training loop:
 import torch
 from comfi_fast_grnn_torch import ComfiFastGRNN 
 
-# 1. Initialize the layer
-# batch_first=True is the default for this implementation
-model = ComfiFastGRNN(
+comfi_fgrnn = ComfiFastGRNN(
     input_size=32, 
     hidden_size=64, 
     num_layers=1
 )
-
-# 2. Create dummy input: (Batch Size, Sequence Length, Input Size)
-x = torch.randn(10, 50, 32)
-
-# 3. Forward pass
-# Returns output (all timesteps) and final hidden state
-output, h_n = model(x)
-
-print(f"Output shape: {output.shape}")  # torch.Size([10, 50, 64])
-print(f"Hidden state shape: {h_n.shape}") # torch.Size([1, 10, 64])
 ```

comfi_fast_grnn_torch-0.0.3/README.md

@@ -0,0 +1,20 @@
+# comfi-fast-grnn-torch
+Implements Comfi-FastGRNN in torch.
+
+## Usage
+
+The `ComfiFastGRNN` module is designed to be a drop-in replacement for standard PyTorch RNN layers (like `nn.LSTM` or `nn.GRU`), but with added support for low-rank factorization and complementary filtering.
+
+### Basic Implementation
+Here is how to use the layer with default settings in a standard training loop:
+
+```python
+import torch
+from comfi_fast_grnn_torch import ComfiFastGRNN 
+
+comfi_fgrnn = ComfiFastGRNN(
+    input_size=32, 
+    hidden_size=64, 
+    num_layers=1
+)
+```

{comfi_fast_grnn_torch-0.0.1 → comfi_fast_grnn_torch-0.0.3}/pyproject.toml

@@ -4,9 +4,9 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "comfi_fast_grnn_torch"  
-version = "0.0.1"
-description = "A PyTorch implementation of Fast ULCNet"
-readme = "README.md"
+version = "0.0.3"
+description = "A PyTorch implementation of Comfi-FastGRNN"
+readme = {file = "README.md", content-type = "text/markdown"}
 requires-python = ">=3.10"
 license = {text = "MIT"} 
 authors = [

comfi_fast_grnn_torch-0.0.3/src/comfi_fast_grnn_torch/__init__.py

@@ -0,0 +1 @@
+from .ComfiFastGRNN import ComfiFastGRNN

{comfi_fast_grnn_torch-0.0.1 → comfi_fast_grnn_torch-0.0.3}/src/comfi_fast_grnn_torch.egg-info/PKG-INFO

@@ -1,7 +1,7 @@
 Metadata-Version: 2.4
 Name: comfi_fast_grnn_torch
-Version: 0.0.1
-Summary: A PyTorch implementation of Fast ULCNet
+Version: 0.0.3
+Summary: A PyTorch implementation of Comfi-FastGRNN
 Author-email: Nicolas Arrieta Larraza <NIAL@bang-olufsen.dk>, Niels de Koeijer <NEMK@bang-olufsen.dk>
 License: MIT
 Project-URL: Homepage, https://github.com/narrietal/Fast-ULCNet
@@ -12,8 +12,8 @@ Requires-Dist: libsegmenter==1.0.4
 Requires-Dist: torchinfo==1.8.0
 Requires-Dist: CRM_pytorch==0.1.0
 
-# fast-ulcnet-torch
-Implements FastULCNet and Comfi-FastGRNN in torch.
+# comfi-fast-grnn-torch
+Implements Comfi-FastGRNN in torch.
 
 ## Usage
 
@@ -26,21 +26,9 @@ Here is how to use the layer with default settings in a standard training loop:
 import torch
 from comfi_fast_grnn_torch import ComfiFastGRNN 
 
-# 1. Initialize the layer
-# batch_first=True is the default for this implementation
-model = ComfiFastGRNN(
+comfi_fgrnn = ComfiFastGRNN(
     input_size=32, 
     hidden_size=64, 
     num_layers=1
 )
-
-# 2. Create dummy input: (Batch Size, Sequence Length, Input Size)
-x = torch.randn(10, 50, 32)
-
-# 3. Forward pass
-# Returns output (all timesteps) and final hidden state
-output, h_n = model(x)
-
-print(f"Output shape: {output.shape}")  # torch.Size([10, 50, 64])
-print(f"Hidden state shape: {h_n.shape}") # torch.Size([1, 10, 64])
 ```

{comfi_fast_grnn_torch-0.0.1 → comfi_fast_grnn_torch-0.0.3}/src/comfi_fast_grnn_torch.egg-info/SOURCES.txt

@@ -1,3 +1,4 @@
+MANIFEST.in
 README.md
 pyproject.toml
 src/comfi_fast_grnn_torch/ComfiFastGRNN.py

comfi_fast_grnn_torch-0.0.1/README.md

@@ -1,32 +0,0 @@
-# fast-ulcnet-torch
-Implements FastULCNet and Comfi-FastGRNN in torch.
-
-## Usage
-
-The `ComfiFastGRNN` module is designed to be a drop-in replacement for standard PyTorch RNN layers (like `nn.LSTM` or `nn.GRU`), but with added support for low-rank factorization and complementary filtering.
-
-### Basic Implementation
-Here is how to use the layer with default settings in a standard training loop:
-
-```python
-import torch
-from comfi_fast_grnn_torch import ComfiFastGRNN 
-
-# 1. Initialize the layer
-# batch_first=True is the default for this implementation
-model = ComfiFastGRNN(
-    input_size=32, 
-    hidden_size=64, 
-    num_layers=1
-)
-
-# 2. Create dummy input: (Batch Size, Sequence Length, Input Size)
-x = torch.randn(10, 50, 32)
-
-# 3. Forward pass
-# Returns output (all timesteps) and final hidden state
-output, h_n = model(x)
-
-print(f"Output shape: {output.shape}")  # torch.Size([10, 50, 64])
-print(f"Hidden state shape: {h_n.shape}") # torch.Size([1, 10, 64])
-```