diff --git a/README.md b/README.md index 32a53e77b285ca8bcd3dcc486fa69392cb188037..04334e83b4798a333c4c15efe1892656e3026bcd 100644 --- a/README.md +++ b/README.md @@ -137,7 +137,7 @@ python tools/process.py \ --output_dir photos/resized ``` -No other processing is required, the colorzation mode (see Training section below) uses single images instead of image pairs. +No other processing is required, the colorization mode (see Training section below) uses single images instead of image pairs. ## Training @@ -197,6 +197,17 @@ The test run will output an HTML file at `facades_test/index.html` that shows in <img src="docs/test-html.png" width="300px"/> +## Exporting + +You can export the model to be served or uploaded with `--mode export`. As with testing, you should specify the checkpoint to use with `--checkpoint`. + +```sh +python pix2pix.py \ + --mode export \ + --output_dir facades_export \ + --checkpoint facades_train +``` + ## Code Validation Validation of the code was performed on a Linux machine with a ~1.3 TFLOPS Nvidia GTX 750 Ti GPU and an Azure NC6 instance with a K80 GPU.