```
def softmax(x):
e_x = np.exp(x - np.max(x))
return e_x / e_x.sum(axis=0)
```

we see two times in the utils.py

```
def softmax(x):
e_x = np.exp(x - np.max(x))
return e_x / e_x.sum(axis=0)
```

we see two times in the utils.py

Thanks for pointing out that duplicate function definition.