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-0.0.2b20210221.tar.gz
(8.2 kB
view details)
Built Distribution
File details
Details for the file rfconv-0.0.2b20210221.tar.gz.
File metadata
- Download URL: rfconv-0.0.2b20210221.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/4.57.0 CPython/3.7.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 7ee6de13509ac09e0a5bdb7d96f87787c570ee781478d5d8a547f4f7f8c00666 |
|
| MD5 | ed51d39e22333ebff78ce90153118b88 |
|
| BLAKE2b-256 | 344204ee281ccc34f7582e8569c07e5597c21acd1a04449886ed956de1f0f3ae |
File details
Details for the file rfconv-0.0.2b20210221-py3-none-any.whl.
File metadata
- Download URL: rfconv-0.0.2b20210221-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/4.57.0 CPython/3.7.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3fecb3c3cb253c72bc723edea54b5cc42fec27d260efe376247658f9dfadbd4a |
|
| MD5 | e8bbee8e06d85d02104604cf8882ca64 |
|
| BLAKE2b-256 | ea28b1095b0565f80df179bc4b6ebc9412fb25273a273b39f379dadf7c1ebcbd |
