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-0.0.2b20210203.tar.gz
(8.2 kB
view hashes)
Built Distribution
Close
Hashes for rfconv-0.0.2b20210203-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 34da02b72cfb31da4149d3e11fe942d4e2db6b1d7188b6d593e483edb15e0705 |
|
MD5 | 9d4e6a5780a99c08322a50282fcc885b |
|
BLAKE2b-256 | 01e6989339c61cc2f45aa6363a1361ea0d2c496670f2ae1d0b9cf89abf7423fe |