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-0.0.2b20210206.tar.gz
(8.2 kB
view details)
Built Distribution
File details
Details for the file rfconv-0.0.2b20210206.tar.gz.
File metadata
- Download URL: rfconv-0.0.2b20210206.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 | b316bf97f81669a30831a40498805cb7dd12534360af5eca72207d22d0d99da4 |
|
| MD5 | 843223a6280d69f6ada044d1fbbda83d |
|
| BLAKE2b-256 | bde717c1ee4831a2bc64fb80b004cd5e6e120a0096013f21f147884ffba36830 |
File details
Details for the file rfconv-0.0.2b20210206-py3-none-any.whl.
File metadata
- Download URL: rfconv-0.0.2b20210206-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 | 5f6275225d0b97740dde47420d92ac3618e206e44bd13c7ea4dac255f35fb831 |
|
| MD5 | 60ae35534fd81b59df1ba5eed2c7411b |
|
| BLAKE2b-256 | 5e14a820aef7fb2540089fdba9d3672f12f7e63d572611a206dde18b23a5527d |
