added gpu check and potential nvidia fix that works on some systems (#71)

This commit is contained in:
Nicholas Georgescu
2023-07-11 16:29:23 +03:00
committed by GitHub
parent 8cda581d2c
commit 7187736a69
+13 -1
View File
@@ -23,6 +23,18 @@ Check latest cudnn and cudatoolkit version for your GPU device.
python -m pip install -r ./DeepFaceLab/requirements-cuda.txt python -m pip install -r ./DeepFaceLab/requirements-cuda.txt
``` ```
you can confirm your gpu is working correctly by running the following code and seeing what messages pop up:
```bash
python -c "import tensorflow as tf;print(tf.__version__)"
```
If the scripts can't seem to access the GPU and you're having issues with cuda version mismatches when running `nvidia-smi`, they can sometimes be remedied by simply running
```bash
conda install tensorflow-gpu==2.4.1
```
## 4. Download Pretrain (optional) ## 4. Download Pretrain (optional)
Use script 4.1 from the scripts directory. Use script 4.1 from the scripts directory.
@@ -39,4 +51,4 @@ Run all scripts with BASH shell
```bash ```bash
bash 1_clear_workspace.sh bash 1_clear_workspace.sh
``` ```
etc etc