pytorch implementation of seesaw loss
Project description
SeesawLoss implementation using PyTorch
Install
pip install seesawloss
Usage
from seesawloss import SeesawLoss
...
criterion = SeesawLoss(num_classes=1000)
...
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
seesawloss-0.1.1.tar.gz
(3.1 kB
view details)
File details
Details for the file seesawloss-0.1.1.tar.gz.
File metadata
- Download URL: seesawloss-0.1.1.tar.gz
- Upload date:
- Size: 3.1 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.0 CPython/3.8.10
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
ef91429e86a84c16766b95207ad6bc7180cafbbc6b55b9fae59277995f511a9b
|
|
| MD5 |
d97a0181a9dc84fe3f03a1289870beda
|
|
| BLAKE2b-256 |
3ee3662d8fbddad40e25c3de0c0fd02359eb4adb1e1d2cf20ef891512f25a45c
|
