pykernsformer
The pykernsformer module extends the torch.nn.TransformerEncoderLayer class to include custom attention formulas.
Installation
You can install the pykernsformer package using pip as
pip install pykernsformer
Usage
pykernsformer comes with the following built in attention kernels.
| pykernsformer | Attention | Formula | Citation |
|---|---|---|---|
attention |
Regular | $softmax(\frac{QK^T}{\sqrt{d_k}})V$ | Vaswani et al. |
attention_linear |
Linear | $\frac{QK^T}{\sum_k QK^T}V$ | |
attention_periodic |
Periodic | $softmax(-\frac{2\sin^2(\pi\frac{\sqrt{2 - 2q_ik_j^T}}{p})}{\sqrt{d_k}})V$ | |
attention_LP |
Locally Periodic | $softmax(-\frac{2\sin^2(\pi\frac{\sqrt{2 - 2\hat{q}_i\hat{k}_j^T}}{p})}{\sqrt{d_k}} + \frac{{q_i}{k_j^T}}{\sqrt{d_k}})V$ | |
attention_RQ |
Rational Quadratic | $\frac{\left( 1 + \frac{1}{\alpha \sqrt{d_k}} - \frac{2QK^T}{2 \alpha \sqrt{d_k}} \right)^{-\alpha}}{\sum_k \left( 1 + \frac{1}{\alpha \sqrt{d_k}} - \frac{2QK^T}{2 \alpha \sqrt{d_k}} \right)^{-\alpha}}V$ |
You can also implement your own attention function with the following signature:
def attention_custom(query, key, value, mask=None, dropout=None):
[...]
p_attn = [...] # the attention matrix
[...]
return torch.matmul(p_attn, value), p_attn
1 maintainer
Metadata
1 maintainer
Release files for pykernsformer 0.0.4
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| pykernsformer-0.0.4.tar.gz | 2.7 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| pykernsformer-0.0.4-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 5.5 kB
Release files / pykernsformer-0.0.4.tar.gz
| Download URL | pykernsformer-0.0.4.tar.gz |
|---|---|
| Size | 2.7 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
156dc0f62a652adf97d593d6457e3cd3301ab5ee09b6a046057766e23d8b64a7
|
|
BLAKE2b-256 checksum How to use checksums |
226f749f7b77f7b073f84d0a1d14db3a5e5340e7acc9076748c0ad01ad50f74f
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/3.10.1 pkginfo/1.7.0 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.7.10
|
Release files / pykernsformer-0.0.4-py3-none-any.whl
| Download URL | pykernsformer-0.0.4-py3-none-any.whl |
|---|---|
| Size | 2.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
3609a2dc2ea652219983ffee48bd298a0b1eaa8e9d037327cfacea76b4b94bce
|
|
BLAKE2b-256 checksum How to use checksums |
4c1dc054a9bc3f7d56100e049c6c27ad4ebd053ab19f49cb4327bb5c5f383b8e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.4.1 importlib_metadata/3.10.1 pkginfo/1.7.0 requests/2.23.0 requests-toolbelt/0.9.1 tqdm/4.41.1 CPython/3.7.10
|
