# CoinCheung/pytorch-loss

<https://repo.masters-masters.com/en/repos/CoinCheung/pytorch-loss>

[Home](https://repo.masters-masters.com/en) › [CoinCheung](https://repo.masters-masters.com/en/owners/CoinCheung) › [pytorch-loss](https://repo.masters-masters.com/en/repos/CoinCheung/pytorch-loss)

CoinCheung/pytorch-loss has 2,252 stars on GitHub. Its RepoMasters card: RC tier. label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss…

| Field | Value |
| --- | --- |
| Owner | [CoinCheung](https://repo.masters-masters.com/en/owners/CoinCheung) |
| Stars | 2,252 |
| Forks | 370 |
| Language | [Python](https://repo.masters-masters.com/en/languages/python) |
| License | MIT |
| Created | 2019 |
| Topics | pytorch, dice-loss, triplet-loss, amsoftmax, cuda, label-smoothing, focal-loss, mish, ema, lovasz-softmax |
| Tier | [RC (2,000 to 4,999 ★)](https://repo.masters-masters.com/en/ranks/blockbuster) |
| View on GitHub | [CoinCheung/pytorch-loss](https://github.com/CoinCheung/pytorch-loss) |

## Repository

label-smooth, amsoftmax, partial-fc, focal-loss, triplet-loss, lovasz-softmax. Maybe useful

The tier for repos with 2,000 to 4,999 ★. Published odds per card pulled: 3%. Rarity: Epic.

## More repos by CoinCheung

- [CoinCheung/BiSeNet · ★ 1,642 · Python · Beta](https://repo.masters-masters.com/en/repos/CoinCheung/BiSeNet)
- [CoinCheung/DeepLab-v3-plus-cityscapes · ★ 191 · Python · Prototype](https://repo.masters-masters.com/en/repos/CoinCheung/DeepLab-v3-plus-cityscapes)
- [CoinCheung/triplet-reid-pytorch · ★ 103 · Python · Prototype](https://repo.masters-masters.com/en/repos/CoinCheung/triplet-reid-pytorch)

## Nearby in Python

- [custom-components/ble\_monitor · ★ 2,252 · Python · RC](https://repo.masters-masters.com/en/repos/custom-components/ble_monitor)
- [Hao0321/video-autopilot-kit · ★ 2,252 · Python · RC](https://repo.masters-masters.com/en/repos/Hao0321/video-autopilot-kit)
- [dexmal/opendm · ★ 2,252 · Python · RC](https://repo.masters-masters.com/en/repos/dexmal/opendm)

---
Data: GitHub · Illustration drawn by RepoMasters from the repo’s ID and its language color.