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-0.0.2b20210323.tar.gz
(8.2 kB
view details)
Built Distribution
File details
Details for the file rfconv-0.0.2b20210323.tar.gz.
File metadata
- Download URL: rfconv-0.0.2b20210323.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.4.1 importlib_metadata/3.7.3 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 | 9e5737133aaf34a21803e104db9b84b7debfa176e0960b0e81e3dfa25959c6cd |
|
| MD5 | e92c573b1278a662255ac17210f5934a |
|
| BLAKE2b-256 | ee4a3db0e49455526410e2c898e76c54cdc579134344008e9bef4634787ff2d8 |
File details
Details for the file rfconv-0.0.2b20210323-py3-none-any.whl.
File metadata
- Download URL: rfconv-0.0.2b20210323-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/3.7.3 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 | 2a9d64924271d227cbbed108fde7640309bd93b1fe50988ae776f013534bf062 |
|
| MD5 | 206447e703dd0c68f0df76111216d6e5 |
|
| BLAKE2b-256 | 8da105871c17fd9c5b17a2f5a38f15e2892c5548f83419ba332345f4c4e3bdf5 |
