mirror of
https://github.com/hzwer/ECCV2022-RIFE.git
synced 2025-12-14 15:37:46 +01:00
Dockerfile now uses the same train_log folder as the scripts
This commit is contained in:
@@ -81,7 +81,7 @@ ffmpeg -r 10 -f image2 -i output/img%d.png -s 448x256 -vf "split[s0][s1];[s0]pal
|
||||
```
|
||||
|
||||
### Run in docker
|
||||
Place the pre-trained models in the `./docker/pretrained_models directory`
|
||||
Place the pre-trained models in `train_log/\*.pkl` (as above)
|
||||
|
||||
Building the container:
|
||||
```
|
||||
|
||||
@@ -15,7 +15,7 @@ ADD docker/inference_video /usr/local/bin/inference_video
|
||||
RUN chmod +x /usr/local/bin/inference_video
|
||||
|
||||
# add pre-trained models
|
||||
COPY docker/pretrained_models /rife/train_log
|
||||
COPY train_log /rife/train_log
|
||||
|
||||
WORKDIR /host
|
||||
ENTRYPOINT ["/bin/bash"]
|
||||
|
||||
Reference in New Issue
Block a user