forked from ccf-ai-infra/GPUCodeForces
fixes
This commit is contained in:
parent
abea784bc3
commit
679036215e
|
|
@ -5,7 +5,6 @@ You have complete freedom to choose the set of operators you want to replace. Yo
|
|||
Here's an example to show you the syntax of inline embedding custom CUDA operators in torch: The example given architecture is:
|
||||
|
||||
```python
|
||||
# cosineloss_torch.py
|
||||
import torch
|
||||
import torch.nn as nn
|
||||
import torch.nn.functional as F
|
||||
|
|
|
|||
Loading…
Reference in New Issue