You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
*[Conda](https://conda.io/projects/conda/en/latest/user-guide/install/index.html?highlight=conda) or [Python Pip](https://pip.pypa.io/en/stable/installing/), we recommend the user to use Pip.
44
44
*[PyTorch](http://pytorch.org/)
45
45
*[Faiss](https://github.com/facebookresearch/faiss) (recommended) for fast nearest neighbor search (CPU or GPU).
46
46
47
47
Available on CPU or GPU, in Python 2 or 3. Faiss is *optional* for GPU users - though Faiss-GPU will greatly speed up the nearest neighbor search - and *highly recommended* for CPU users. Faiss can be installed using "conda install faiss-cpu -c pytorch" or "conda install faiss-gpu -c pytorch".
48
48
49
-
If the default Pytorch does not work, please try this command:
49
+
If you use Conda to install pytorch, and if the default Pytorch does not work, please try this command:
50
50
```
51
51
conda install pytorch --channel pytorch
52
52
```
53
53
54
+
For the other libs, if using conda, the command will be : ```conda install numpy```
55
+
56
+
If you use pip, only this command is good enough to install all of the necessary requirements.
57
+
```
58
+
pip install -r requirements.txt
59
+
```
54
60
55
61
### Run the code: adversarial training and refinement (CPU|GPU)
56
62
A sample command to learn a mapping using adversarial training and iterative Procrustes refinement:
0 commit comments