fix images paths

docs/semint-clean.md

@@ -213,11 +213,11 @@ The first step is the construction of categories for each column.
 We will use a subset of test dataset Hospital 100
 Case study: [hospital_10](../docker/docker-ldb/ldb/sample/fix_hospital.py)
 
-![hospital_10](docker/docker-ldb/ldb/profile/memory_fix_hospital_10_1.png)
+![hospital_10](../docker/docker-ldb/ldb/profile/memory_fix_hospital_10_1.png)
 
 HoloClean hospital case study: [hospital_100](../docker/docker-ldb/ldb/sample/fix_hospital.py)
 
-![hospital_100](docker/docker-ldb/ldb/profile/memory_fix_hospital_100.png)
+![hospital_100](../docker/docker-ldb/ldb/profile/memory_fix_hospital_100.png)
 
 * highlighted mapping difficulty, to get good learning the whole record should be mapped to real vectors,
 for some types of field this activity is not immediate.
@@ -227,19 +227,19 @@ Using the hospital data set 1000 and subsets consisting of:
 
 HoloClean hospital case study: [hospital_200](../docker/docker-ldb/ldb/sample/fix_hospital.py)
 
-![hospital_200](docker/docker-ldb/ldb/profile/memory_fix_hospital_200.png)
+![hospital_200](../docker/docker-ldb/ldb/profile/memory_fix_hospital_200.png)
 
 HoloClean hospital case study: [hospital_500](../docker/docker-ldb/ldb/sample/fix_hospital.py)
 
-![hospital_500](docker/docker-ldb/ldb/profile/memory_fix_hospital_500.png)
+![hospital_500](../docker/docker-ldb/ldb/profile/memory_fix_hospital_500.png)
 
 HoloClean hospital case study: [hospital_750](../docker/docker-ldb/ldb/sample/fix_hospital.py) 
 
-![hospital_750](docker/docker-ldb/ldb/profile/memory_fix_hospital_750.png)
+![hospital_750](../docker/docker-ldb/ldb/profile/memory_fix_hospital_750.png)
 
 HoloClean hospital case study: [hospital_1000](../docker/docker-ldb/ldb/sample/fix_hospital.py) > 32Gb
 
-![hospital_1000](docker/docker-ldb/ldb/profile/memory_fix_hospital_1000.png)
+![hospital_1000](../docker/docker-ldb/ldb/profile/memory_fix_hospital_1000.png)
 
 * highlighted scalability difficulty, network training, application and effectiveness times remain largely optimizable.