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-0.0.2b20210329.tar.gz
(8.2 kB
view details)
Built Distribution
File details
Details for the file rfconv-0.0.2b20210329.tar.gz
.
File metadata
- Download URL: rfconv-0.0.2b20210329.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/3.9.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.7.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | c6d65aae22ff9eb9cea683f5872103dd8e3b218672e25fa88cdd96a1a194be00 |
|
MD5 | 6747f5a8198b66f2a662e9e1f32bf0dd |
|
BLAKE2b-256 | 7dbbd6ad994e2e4bb0e1032868d14690cebd5687879b52c0f083a1578707c437 |
File details
Details for the file rfconv-0.0.2b20210329-py3-none-any.whl
.
File metadata
- Download URL: rfconv-0.0.2b20210329-py3-none-any.whl
- Upload date:
- Size: 16.1 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/3.9.0 pkginfo/1.7.0 requests/2.25.1 requests-toolbelt/0.9.1 tqdm/4.59.0 CPython/3.7.10
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7afc2e32cff48798ac7eba6d70a381a0b178be245b62835eb8a954f80e9d7a64 |
|
MD5 | 636f3e7ba4d43880e74dd9f8ed01d765 |
|
BLAKE2b-256 | dbe8bf3d68578d0645e32bc80c9e5e0455dbbe518c8cdccab1c9544d4dc55584 |