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
Project details
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-0.0.2b20210316.tar.gz
(8.2 kB
view hashes)
Built Distribution
Close
Hashes for rfconv-0.0.2b20210316-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 91ae66a404125f446193d53d8f7aa0759f32c655ace9032af011a69401eb6aec |
|
MD5 | 1b471bc6b049aaf65f12ba1bd24ad4c4 |
|
BLAKE2b-256 | 52e4d32e54276cd74c0163fa3dd5532637c6b9aba1d4a3b91c95ec8bf90fef5e |