We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent 6830ff9 commit 855668aCopy full SHA for 855668a
README.md
@@ -310,6 +310,18 @@ optimizer = optim.SGD(parameters, ...)
310
311
```
312
313
+#### 8. Margin based classification loss
314
+Now support:
315
+1. ArcLoss
316
+2. CosLoss
317
+3. L2Softmax
318
+
319
+```python
320
+from torchtoolbox.nn.loss import ArcLoss, CosLoss, L2Softmax
321
+```
322
323
+You could use this like `nn.CrossEntropyLoss`
324
325
## Contribution
326
327
Welcome pull requests and issues!!!
0 commit comments