A collection of inference modules
Project description
fastinference
A collection of inference modules for fastai2 including inference speedup and interpretability
Install
We have 4 modules you can install, depending on your usecase:
- Base Library (Just inference stuff):
pip install fastinference - ONNX Inference:
pip install fastinference[onnx-cpu]orfastinference[onnx-gpu] - Interperatability (Class Confusion + SHAP):
pip install fastinference[interp] - Everything:
pip install fastinference[all]
Wonderful Contributors:
Directions for Contributing:
- Fork this repository into your GitHub Account
- Ensure that
nbdevis installed on your system - Make any changes and ensure that you run the following before commiting:
nbdev_build_libnbdev_clean_nbs
- Open a Pull Request with the library, and choose "From fork" to open one with the main repository.
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
fastinference-0.0.21.tar.gz
(29.2 kB
view details)
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 fastinference-0.0.21.tar.gz.
File metadata
- Download URL: fastinference-0.0.21.tar.gz
- Upload date:
- Size: 29.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.2.0.post20200511 requests-toolbelt/0.9.1 tqdm/4.38.0 CPython/3.7.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
572e42a851b84da215faae382fd51f01e5a0effdd93696a3230faabcfff4f787
|
|
| MD5 |
2f3156b2c00c65dc8e69479a227e55b4
|
|
| BLAKE2b-256 |
b63359bacbc1228c0321f8a36362ec41db2d087d097980428708eb7b703d2749
|
File details
Details for the file fastinference-0.0.21-py3-none-any.whl.
File metadata
- Download URL: fastinference-0.0.21-py3-none-any.whl
- Upload date:
- Size: 35.3 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.1.1 pkginfo/1.5.0.1 requests/2.23.0 setuptools/46.2.0.post20200511 requests-toolbelt/0.9.1 tqdm/4.38.0 CPython/3.7.7
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
d5ce4b3b2123f58389ffc09b0fde5e1efa30e19d6882926ae3e6bf79f9721ef9
|
|
| MD5 |
cc6e3c35aac7a4a82f582fb8fa9ce7bf
|
|
| BLAKE2b-256 |
63c723458e22b3c8c2db06fc0d45e1abe9ea6018d5c77105db049d8957672b71
|
