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-0.0.2b20210108.tar.gz
(8.2 kB
view details)
Built Distribution
File details
Details for the file rfconv-0.0.2b20210108.tar.gz.
File metadata
- Download URL: rfconv-0.0.2b20210108.tar.gz
- Upload date:
- Size: 8.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.6.1 requests/2.25.1 setuptools/47.1.0 requests-toolbelt/0.9.1 tqdm/4.55.1 CPython/3.7.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 90aed97565839515893a879cb90332503f6cc78297945fe69ad95a72747720c6 |
|
| MD5 | 0a8497f6ad53ec19cec0b40e3a2bfbf2 |
|
| BLAKE2b-256 | 2e94f5d34dc0a156da5fdfe01b4775b20c8dd9ee0e9b571c6c80c00fa212a4b3 |
File details
Details for the file rfconv-0.0.2b20210108-py3-none-any.whl.
File metadata
- Download URL: rfconv-0.0.2b20210108-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/1.6.1 requests/2.25.1 setuptools/47.1.0 requests-toolbelt/0.9.1 tqdm/4.55.1 CPython/3.7.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 78016c1ad66efb5617b2343a92aecd90847eddd501e85d74c9b76392db112396 |
|
| MD5 | 4f25533ef21e51cceab196ad9e8ec48f |
|
| BLAKE2b-256 | 3acae884115cfd81106a7930c578ea9ea767a5cd95f63aa98ca642934bd621bd |
