반응형
CPU vs GPU
CUDA (NVIDIA only)
write C-like code that runs directly on the GPU
highter-level APIs: cuDNN, cuBLAS, etc..
OpenCL
similar to CUDA, but on anything
slow
cuDNN much faster than unoptimized CUDA
Deep Learning Frameworks
Caffe / Caffe2
Theano/TensorFlow
Torch/PyTorch
The Point of deep learning frameworks
(1) Easily build big computational graphs
(2) Easily compute gradients in computational graphs
(3) Run it all efficiently on GPU (warp cuDNN, cuBLAS, etc)
Computational Graphs
Numpy
problems:
can't run on GPU
have to compute our own gradients
반응형
'AI > CS231n' 카테고리의 다른 글
| CS231n - Lec10. Recurrent Neural Networks (0) | 2023.09.15 |
|---|---|
| CS231n - Lec9. CNN Architecture (0) | 2023.09.12 |
| CS231n - Lec7. Training Neural Networks 2 (0) | 2023.09.11 |
| CS231n- Lec6. Training Neural Networks 1 (0) | 2023.09.10 |
| CS231n - Lec5. Convolutional Neural Networks (0) | 2023.09.08 |
