diff --git a/.idea/workspace.xml b/.idea/workspace.xml
index 10c64f7..a4d32a5 100644
--- a/.idea/workspace.xml
+++ b/.idea/workspace.xml
@@ -3,7 +3,7 @@
-
+
@@ -17,11 +17,32 @@
-
+
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
@@ -91,6 +112,8 @@
+
+
@@ -121,6 +144,11 @@
+
+
+
+
+
@@ -225,7 +253,21 @@
1533723349354
-
+
+ 1533725197867
+
+
+
+ 1533725197867
+
+
+ 1533725908704
+
+
+
+ 1533725908704
+
+
@@ -235,12 +277,12 @@
-
+
-
+
@@ -264,7 +306,9 @@
-
+
+
+
@@ -333,8 +377,34 @@
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/README.md b/README.md
index fda1ecd..abc599e 100644
--- a/README.md
+++ b/README.md
@@ -42,6 +42,7 @@ Our model learns localized radiological findings as we imposed prior anatomical
## Inference for your own data
To run the inference on your own DICOM data, do the following:
+
0. Create a conda environment `deep_knee` using the script `create_conda_env.sh`.
1. Fetch our repository [KneeLocalizer](https://github.com/MIPT-Oulu/KneeLocalizer) and get
the file with bounding boxes, which determine the locations of the knees on the image