From 8c8204cf4527bc2adff43e2a445fb4790a693605 Mon Sep 17 00:00:00 2001 From: deep pomf Date: Wed, 11 Apr 2018 18:12:28 -0400 Subject: [PATCH] fix #5 --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 325c3c0..ae4b7e0 100644 --- a/README.md +++ b/README.md @@ -58,13 +58,13 @@ The decensorship process is fairly involved. A user interface will eventually be Using image editing software like Photoshop or GIMP, paint the areas you want to decensor the color with RGB values of (0,255,0). You can change the mask color in config. For each censored region, crop 128 x 128 size images containing the censored regions from your images and save them as new ".png" images. -Move the cropped images to the "decensor_input_images" directory. Decensor the images by running +Move the cropped images to the "decensor_input" directory. Decensor the images by running ``` $ python decensor.py ``` -Decensored images will be saved to the "decensor_output_images" directory. Paste the decensored images back into the original image. +Decensored images will be saved to the "decensor_output" directory. Paste the decensored images back into the original image. ## II. Train the pretrained model on custom dataset