mathdatech/Python
1
0
Fork 0
mirror of https://github.com/TheAlgorithms/Python.git synced 2025-03-23 06:59:47 +00:00
Code Issues Packages Projects Releases Wiki Activity

[pre-commit.ci] auto fixes from pre-commit.com hooks

Browse Source 
for more information, see https://pre-commit.ci
This commit is contained in:
pre-commit-ci[bot] 2024-10-20 16:46:42 +00:00
parent 9e9a3131a3
commit 041571772e
1 changed files with 7 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
neural_network/sliding_window_attention.py
View File

@ -1,7 +1,7 @@
""" """
- - - - - -- - - - - - - - - - - - - - - - - - - - - - - - - - - - -- - - - - - - - - - - - - - - - - - - - - - -
Name - - sliding_window_attention.py Name - - sliding_window_attention.py
Goal - - Implement a neural network architecture using sliding window attention for sequence Goal - - Implement a neural network architecture using sliding window attention for sequence
modeling tasks. modeling tasks.
Detail: Total 5 layers neural network Detail: Total 5 layers neural network
* Input layer * Input layer
@ -12,9 +12,9 @@ Author: Stephen Lee
Github: 245885195@qq.com Github: 245885195@qq.com
Date: 2024.10.20 Date: 2024.10.20
References: References:
1. Choromanska, A., et al. (2020). "On the Importance of Initialization and Momentum in 1. Choromanska, A., et al. (2020). "On the Importance of Initialization and Momentum in
Deep Learning." *Proceedings of the 37th International Conference on Machine Learning*. Deep Learning." *Proceedings of the 37th International Conference on Machine Learning*.
2. Dai, Z., et al. (2020). "Transformers are RNNs: Fast Autoregressive Transformers 2. Dai, Z., et al. (2020). "Transformers are RNNs: Fast Autoregressive Transformers
with Linear Attention." *arXiv preprint arXiv:2006.16236*. with Linear Attention." *arXiv preprint arXiv:2006.16236*.
3. [Attention Mechanisms in Neural Networks](https://en.wikipedia.org/wiki/Attention_(machine_learning)) 3. [Attention Mechanisms in Neural Networks](https://en.wikipedia.org/wiki/Attention_(machine_learning))
- - - - - -- - - - - - - - - - - - - - - - - - - - - - - - - - - - -- - - - - - - - - - - - - - - - - - - - - - -
@ -52,7 +52,7 @@ class SlidingWindowAttention:
Forward pass for the sliding window attention. Forward pass for the sliding window attention.
Args: Args:
input_tensor (np.ndarray): Input tensor of shape (batch_size, seq_length, input_tensor (np.ndarray): Input tensor of shape (batch_size, seq_length,
embed_dim). embed_dim).
Returns: Returns:
@ -93,7 +93,9 @@ if __name__ == "__main__":
# usage # usage
rng = np.random.default_rng() rng = np.random.default_rng()
x = rng.standard_normal((2, 10, 4)) # Batch size 2, sequence length 10, embedding dimension 4 x = rng.standard_normal(
(2, 10, 4)
) # Batch size 2, sequence length 10, embedding dimension 4
attention = SlidingWindowAttention(embed_dim=4, window_size=3) attention = SlidingWindowAttention(embed_dim=4, window_size=3)
output = attention.forward(x) output = attention.forward(x)
print(output) print(output)