Rectified Convolution
Project description
RFConv
Rectified Convolution
Pretrained Model
| model | baseline | rectified |
|---|---|---|
| ResNet-50 | 76.66 | 77.10 |
| ResNet-101 | 78.13 | 78.74 |
| ResNeXt-50_32x4d | 78.17 | 78.48 |
| ResNeSt-50_2s8x | 78.73 | 79.38 |
Verify Models:
Prepare ImageNet dataset:
cd scripts/dataset/
# assuming you have downloaded the dataset in the current folder
python prepare_imagenet.py --download-dir ./
Test Model
# use resnest50 as an example
cd scripts/
python verify.py --model resnet50 --crop-size 224
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
rfconv-0.0.2b20210126.tar.gz
(8.2 kB
view details)
Built Distribution
File details
Details for the file rfconv-0.0.2b20210126.tar.gz.
File metadata
- Download URL: rfconv-0.0.2b20210126.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/47.1.0 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.7.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | cb34a747a0df6d85f03d50338a4cd442cb5f4d17a2a3bbe2aea8b0be2773b438 |
|
| MD5 | 57eb05a1cd4d5da6da7fcb38d0c99e23 |
|
| BLAKE2b-256 | 4c8d26443922fa979babd4aaff9e5849bdc4cd3fb7c6daedad5e085628abd2ea |
File details
Details for the file rfconv-0.0.2b20210126-py3-none-any.whl.
File metadata
- Download URL: rfconv-0.0.2b20210126-py3-none-any.whl
- Upload date:
- Size: 16.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.7.0 requests/2.25.1 setuptools/47.1.0 requests-toolbelt/0.9.1 tqdm/4.56.0 CPython/3.7.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 889c99195714fd3d00cc9842edccf0277990e64f03b07e0ca9a278a98241a677 |
|
| MD5 | 7f14024a2c785b410f4113c0676fba2b |
|
| BLAKE2b-256 | a03cee1830c528a1ac4b21ef160bf92dcafc9c0d7e70a9af57454cd3add50479 |
