Feyza
@yza
0 reply
0 recast
0 reaction
8 replies
76 recasts
82 reactions
1 reply
38 recasts
73 reactions
0 reply
0 recast
0 reaction
30 replies
114 recasts
537 reactions
0 reply
0 recast
0 reaction
2 replies
45 recasts
235 reactions
1 reply
7 recasts
277 reactions
24 replies
116 recasts
724 reactions
27 replies
1 recast
70 reactions
The differences between the APIs of numpy, cupy and torch are so fascinating....
```
>>> import torch as np
>>> np.arange(10)
tensor([0, 1, 2, 3, 4, 5, 6, 7, 8, 9])
>>> a = np.zeros(20)
>>> a[19:-1:-2] = np.arange(10)
```
Torch doesn't let you have ranges that go backwards 🤣
Would love more consistency 43 replies
485 recasts
1991 reactions
