[dolphinscheduler-website] branch master updated: upload img Lizhi case study(en) (#559)

[leonbao]

This is an automated email from the ASF dual-hosted git repository.

leonbao pushed a commit to branch master
in repository https://gitbox.apache.org/repos/asf/dolphinscheduler-website.git


The following commit(s) were added to refs/heads/master by this push:
     new d0d5bef  upload img Lizhi case study(en) (#559)
d0d5bef is described below

commit d0d5befab4a6485e9e62794ebd29915f0e7796aa
Author: debrachena <93305662+debrach...@users.noreply.github.com>
AuthorDate: Wed Dec 1 19:17:22 2021 +0800

    upload img Lizhi case study(en) (#559)
    
    * create Lizhi case study blog
    
    create Lizhi case study blog
    
    * Update blog.js
    
    * upload img
    
    upload img
    
    * update img
    
    update img
    
    * update img
    
    * upload img
    
    upload img
    
    * Delete present 1.jpg
    
    * Delete present 2.jpg
    
    * Delete present 3.jpg
---
 blog/en-us/Lizhi case study(en) blog correction.md |  40 ++++++++++++++-------
 img/present1.jpg                                   | Bin 0 -> 24709 bytes
 img/present2.jpg                                   | Bin 0 -> 24026 bytes
 img/present3.jpg                                   | Bin 0 -> 24242 bytes
 img/streamline.png                                 | Bin 0 -> 24101 bytes
 5 files changed, 28 insertions(+), 12 deletions(-)

diff --git a/blog/en-us/Lizhi case study(en) blog correction.md 
b/blog/en-us/Lizhi case study(en) blog correction.md
index 0465a17..b34e45a 100644
--- a/blog/en-us/Lizhi case study(en) blog correction.md        
+++ b/blog/en-us/Lizhi case study(en) blog correction.md        
@@ -53,9 +53,14 @@ At the technical level of the platform, Lizhi optimizes the 
extended modules for
 
 A simple xgboost case:
 
-<div align=center>
-<img 
src="https://imgpp.com/images/2021/11/30/32db43420c7c44e28ff2fb7be27ec79c.md.png"/>
-</div>
+<p align="center">
+  <img src="/img/streamline.png" alt="streamline"  width="60%" />
+  <p align="center">
+        <em>streamline</em>
+  </p>
+</p>
+
+
 
 ### 1. Obtaining training samples
 
@@ -67,9 +72,14 @@ At present, Lizhi does not directly select data from Hive, 
and joins the union,
 
 Transformer& custom preprocessing configuration file, use the same 
configuration for online training, and feature preprocessing is performed after 
the feature is obtained. It contains the itemType and its feature set to be 
predicted, the user’s userType and its feature set, as well as the associated 
and crossed itemType and its feature set. Define the transformer function for 
each feature preprocessing, supports custom transformer and hot update, 
xgboost, and tf model feature preprocessi [...]
 
-<div align=center>
-<img src="https://imgpp.com/images/2021/11/30/1afaee9a4142648f0.md.jpg"/>
-</div>
+<p align="center">
+  <img src="/img/present1.jpg" alt="training data preprocess"  width="60%" />
+  <p align="center">
+        <em>Training data preprocess</em>
+  </p>
+</p>
+
+
 
 
 ### 3. Xgboost training
@@ -77,18 +87,24 @@ Transformer& custom preprocessing configuration file, use 
the same configuration
 It supports w2v, xgboost, tf model training modules. The training modules are 
first packaged with TensorFlow or PyTorch and then packaged into 
DolphinScheduler modules.
 For example, in the xgboost training process, use Python to package the 
xgboost training script into the xgboost training node of DolphinScheduler, and 
show the parameters required for training on the interface. The file exported 
by “training set data preprocessing” is input to the training node through HDFS.
 
-<div align=center>
-<img src="https://imgpp.com/images/2021/11/23/3.md.png"/>
-</div>
+<p align="center">
+  <img src="/img/present3.jpg" alt="Xgboost training"  width="60%" />
+  <p align="center">
+        <em>Xgboost training</em>
+  </p>
+</p>
 
 ### 4. Model release
 
 
 The release model will send the model and preprocessing configuration files to 
HDFS and insert records into the model release table. The model service will 
automatically identify the new model, update the model, and provide online 
prediction services to the external.
 
-<div align=center>
-<img src="https://imgpp.com/images/2021/11/30/2c4b9ff8072e348ee.md.jpg"/>
-</div>
+<p align="center">
+  <img src="/img/present2.jpg" alt="Model release"  width="60%" />
+  <p align="center">
+        <em>model release</em>
+  </p>
+</p>
 
 
 Haibin Yu said that due to historical and technical limitations, Lizhi has not 
yet built a machine learning platform like Ali PAI, but the practice has proved 
that similar platform functions can be achieved based on DolphinScheduler.
diff --git a/img/present1.jpg b/img/present1.jpg
new file mode 100644
index 0000000..5503fc0
Binary files /dev/null and b/img/present1.jpg differ
diff --git a/img/present2.jpg b/img/present2.jpg
new file mode 100644
index 0000000..c17e645
Binary files /dev/null and b/img/present2.jpg differ
diff --git a/img/present3.jpg b/img/present3.jpg
new file mode 100644
index 0000000..eda8184
Binary files /dev/null and b/img/present3.jpg differ
diff --git a/img/streamline.png b/img/streamline.png
new file mode 100644
index 0000000..3ed685d
Binary files /dev/null and b/img/streamline.png differ