Say hello
Project description
Download to develop
pip install -e .[dev]
Examples
import torch
from pytorchLosses import LabelSmoothingCrossEntropy,GamblersLoss,SCELoss,TruncatedLoss
a = torch.rand(4, 5)
b = torch.randint(0, 2, (4,))
loss_fun = LabelSmoothingCrossEntropy()
print(loss_fun(a,b))
print(GamblersLoss(a,b))
loss_fun = SCELoss(alpha=1.0,beta=1.0,num_classes=5).cuda()
print(loss_fun(a.cuda(),b.cuda()))
# Yet to test
loss_fun = TruncatedLoss(q=0.7, k=0.5, trainset_size=10000).cuda()
print(loss_fun(a.cuda(),b.cuda(),indexes=1))
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
pytorchLosses-0.3.0.tar.gz
(15.4 kB
view details)
Built Distribution
File details
Details for the file pytorchLosses-0.3.0.tar.gz.
File metadata
- Download URL: pytorchLosses-0.3.0.tar.gz
- Upload date:
- Size: 15.4 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/45.2.0.post20200210 requests-toolbelt/0.9.1 tqdm/4.42.1 CPython/3.7.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 178806484a6462602d90702b49f3ea875602d03e9a01772aeef7dfb95c75a7cb |
|
| MD5 | d07010f2d86e12bd2690189343819899 |
|
| BLAKE2b-256 | 094c4f0f02ecaa4aa15df1044f357a22eb8735953587d045d132a6695bb309b1 |
File details
Details for the file pytorchLosses-0.3.0-py3-none-any.whl.
File metadata
- Download URL: pytorchLosses-0.3.0-py3-none-any.whl
- Upload date:
- Size: 14.6 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/3.3.0 pkginfo/1.5.0.1 requests/2.22.0 setuptools/45.2.0.post20200210 requests-toolbelt/0.9.1 tqdm/4.42.1 CPython/3.7.6
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | e21b31e94e41f6881402a318f9b39c905c02cd85827d644a1aad0d211cea5491 |
|
| MD5 | 215089b657e991a94b540db2759967f9 |
|
| BLAKE2b-256 | f5f4bd5450c8b9ec00aa9ad9d87dabef4fc0e51153187618fa94f9e339084ce0 |
