Commit a5414c1c authored by npedot's avatar npedot
Browse files

fix images paths

parent 23354eb2
......@@ -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.
......
Supports Markdown
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment