github/DeepFaceLab
1
0
Fork 0
mirror of https://github.com/iperov/DeepFaceLab.git synced 2025-07-07 05:22:06 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

OpenCL support: fix bug, adding new requirements files

Browse source
This commit is contained in:
iperov 2019-02-19 20:48:39 +04:00
parent 72ba6b103c
commit b939fe9d85
4 changed files with 18 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

11
doc/doc_features.md
View file

@ -1,6 +1,10 @@
### **Features**: ### **Features**:
- Windows binary containing pre-compiled dependencies, including CUDA libraries. - works on AMD, NVIDIA, IntelHD graphics and all OpenCL1.2-compatible videocards with at least 512M video memory
- CPU-only mode [`--cpu-mode`]. 8th gen Intel core CPU able to train H64 model in 2 days.
- Windows build is standalone ready to work program and contains all dependencies (CUDA, OpenCL, ffmpeg, .bat script etc) to start working
- New models expanding upon the original faceswap model. - New models expanding upon the original faceswap model.
@ -8,10 +12,6 @@
- Face metadata embedded into extracted JPG files. - Face metadata embedded into extracted JPG files.
- CPU-only mode [`--cpu-mode`]. 8th gen Intel core CPU able to train H64 model in 2 days.
- Preview window
- Extractor and Converter run in parallel. - Extractor and Converter run in parallel.
- Debug mode option for all stages: [`--debug`] - Debug mode option for all stages: [`--debug`]
@ -23,7 +23,6 @@
Predicts faces more uniformly than dlib, resulting in a less jittered aligned output. However, MTCNN extraction will produce more false positives. Predicts faces more uniformly than dlib, resulting in a less jittered aligned output. However, MTCNN extraction will produce more false positives.
Comparison dlib (at left) vs mtcnn on hard case: Comparison dlib (at left) vs mtcnn on hard case:
![](https://i.imgur.com/5qLiiOV.gif) ![](https://i.imgur.com/5qLiiOV.gif)

2
nnlib/device.py
View file

@ -270,6 +270,8 @@ try:
ctx = plaidml.Context() ctx = plaidml.Context()
for d in plaidml.devices(ctx, return_all=True)[0]: for d in plaidml.devices(ctx, return_all=True)[0]:
details = json.loads(d.details) details = json.loads(d.details)
if details['type'] == 'CPU': #skipping opencl-CPU
continue
if 'nvidia' in details['vendor'].lower(): if 'nvidia' in details['vendor'].lower():
has_nvidia_device = True has_nvidia_device = True
plaidML_devices += [ {'id':d.id, plaidML_devices += [ {'id':d.id,

0
requirements-gpu-opencl-cuda9-cudnn7.txt → requirements-cuda9-cudnn7.txt
View file

11
requirements-opencl.txt Normal file
View file

@ -0,0 +1,11 @@
numpy==1.16.1
pathlib==1.0.1
scandir==1.6
h5py==2.7.1
Keras==2.2.4
opencv-python==4.0.0.21
tensorflow==1.11.0
plaidml-keras==0.5.0
scikit-image
tqdm
git+https://www.github.com/keras-team/keras-contrib.git