"docs/vscode:/vscode.git/clone" did not exist on "ead64de98e2836e7986b6d05d08aaa97b7094614"
Commit 7bd56758 authored by ziyannchen's avatar ziyannchen
Browse files

fix typo

parent ea13481c
...@@ -103,7 +103,7 @@ conda activate diffbir ...@@ -103,7 +103,7 @@ conda activate diffbir
pip install -r requirements.txt pip install -r requirements.txt
``` ```
Note the installation is only compatiable with **Linux** users. If you are working on different platforms, please check [xOS Installation](assets/docs/installation_xOS.md). Note the installation is only compatible with **Linux** users. If you are working on different platforms, please check [xOS Installation](assets/docs/installation_xOS.md).
<!-- ```shell <!-- ```shell
# clone this repo # clone this repo
......
...@@ -8,7 +8,7 @@ You can choose to run on **CPU** without `xformers` and `triton` installed. ...@@ -8,7 +8,7 @@ You can choose to run on **CPU** without `xformers` and `triton` installed.
To use **CUDA**, please refer to [issue#24](https://github.com/XPixelGroup/DiffBIR/issues/24) to try solve the problem of `triton` installation. To use **CUDA**, please refer to [issue#24](https://github.com/XPixelGroup/DiffBIR/issues/24) to try solve the problem of `triton` installation.
# MacOS # MacOS
<!-- Currenly only CPU device is supported to run DiffBIR on Apple Silicon since most GPU acceleration packages are compatiable with CUDA only. <!-- Currenly only CPU device is supported to run DiffBIR on Apple Silicon since most GPU acceleration packages are compatible with CUDA only.
We are still trying to support MPS device. Stay tuned for our progress! --> We are still trying to support MPS device. Stay tuned for our progress! -->
......
...@@ -78,7 +78,7 @@ def _extract_into_tensor(arr, timesteps, broadcast_shape): ...@@ -78,7 +78,7 @@ def _extract_into_tensor(arr, timesteps, broadcast_shape):
# float64 as default. float64 is not supported by mps device. # float64 as default. float64 is not supported by mps device.
res = torch.from_numpy(arr).to(device=timesteps.device)[timesteps].float() res = torch.from_numpy(arr).to(device=timesteps.device)[timesteps].float()
except: except:
# to be compatiable with mps # to be compatible with mps
res = torch.from_numpy(arr.astype(np.float32)).to(device=timesteps.device)[timesteps].float() res = torch.from_numpy(arr.astype(np.float32)).to(device=timesteps.device)[timesteps].float()
while len(res.shape) < len(broadcast_shape): while len(res.shape) < len(broadcast_shape):
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment