Glossary: Deep Learning Basics
float32, int64
Also written: float32, int64, torch.float32, torch.int64
float32 is the 32-bit decimal type used for data and weights; int64 is the 64-bit integer type PyTorch wants for class labels.
Glossary: Deep Learning Basics
Also written: float32, int64, torch.float32, torch.int64
float32 is the 32-bit decimal type used for data and weights; int64 is the 64-bit integer type PyTorch wants for class labels.