Architectures involved in the investigation of Attention Mechanisms as Feature Selection
Project description
Installation guide
This repository contains the developed architectures in the research of attention mechanisms as feature selectors.
Currently, not all architectures are available. This packages will be updated in the future (I hope that).
The code here is developed as a python package. Anyway, a magic makefile is included (for your comfort :wink:), and some specifications are included below.
Installing from PyPi
By running the next line you will install it from PyPi repo:
pip install ndsl-attn-fs-archs
Installing from source
Building the package
To build the package you just need to run:
make
or:
make build
Installing the package
To install the package just execute:
make install
Running tests
To run the included tests just execute
make test
If you want to add more tests don't forget to add them in the makefile.
Easy, right? :sunglasses:
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file ndsl-attn-fs-archs-0.0.4.tar.gz.
File metadata
- Download URL: ndsl-attn-fs-archs-0.0.4.tar.gz
- Upload date:
- Size: 11.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.1 CPython/3.7.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
24607b6b5652474b5741a8032f0b163b60e30e5d51c36ef6d47663d11a75a0a5
|
|
| MD5 |
ce2d06975cd2d6c2c1a2d2939a5d80c9
|
|
| BLAKE2b-256 |
53061ded982d1e16bf7ebef26d9a6f06fd3a761f112e2e66eaa540211f605d60
|
File details
Details for the file ndsl_attn_fs_archs-0.0.4-py3-none-any.whl.
File metadata
- Download URL: ndsl_attn_fs_archs-0.0.4-py3-none-any.whl
- Upload date:
- Size: 12.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/3.10.0 pkginfo/1.7.1 requests/2.26.0 requests-toolbelt/0.9.1 tqdm/4.62.1 CPython/3.7.11
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
002761759be18214c124c93d5874d3bb010d3b137b8cb25919ece5deb1f74215
|
|
| MD5 |
f128ea352d5182781e394b7bc3f2146a
|
|
| BLAKE2b-256 |
140ee86e77492912de3c0c32991653c0ced6e63e31490d458717ab3f07ee5e01
|
