mlflow predict own model.

Dockerfile

@@ -37,3 +37,5 @@ COPY ./train_mlflow.py ./
 RUN chmod +x train_mlflow.py
 COPY ./generate_MLmodel.py ./
 RUN chmod +x generate_MLmodel.py
+COPY ./mlflow_predict.py ./
+RUN chmod +x mlflow_predict.py

Jenkinsfile_predict

@@ -0,0 +1,42 @@
+pipeline {
+	agent any 
+//	triggers {
+//		upstream(upstreamProjects: "s426206-train/master", 
+//		threshold: hudson.model.Result.SUCCESS) 	
+//	}
+    parameters {
+      buildSelector(
+          defaultSelector: lastSuccessful(),
+          description: 'Which build to use for copying artifacts for predict',
+          name: 'BUILD_SELECTOR_PREDICT')
+        string(
+            defaultValue: 'input_example.json',
+            description: 'Input name',
+            name: 'INPUT',
+            trim: false
+        )
+    }
+	stages {
+		stage('checkout') {
+			steps {
+				checkout([$class: 'GitSCM', branches: [[name: '*/master']], doGenerateSubmoduleConfigurations: false, extensions: [], submoduleCfg: [], userRemoteConfigs: [[url: 'https://git.wmi.amu.edu.pl/s426206/ium_426206.git']]])
+			}
+		}
+        stage('Copy artifact') {
+                steps {
+                    copyArtifacts filter: 'my_model/**/*', fingerprintArtifacts: false, projectName: 's426206-training/master', selector: buildParameter('BUILD_SELECTOR_PREDICT')
+                }
+            }		
+		stage('docker') {
+			steps {
+                script {
+                    def img = docker.build('rokoch/ium:01')
+                    img.inside {
+                        sh 'chmod +x mlflow_predict.py'
+                        sh 'python3 ./mlflow_predict.py $INPUT'
+                    }
+                }
+			}
+		}
+	}
+}

mlflow_predict.py

@@ -0,0 +1,17 @@
+import mlflow
+import mlflow.pytorch
+import sys
+import json
+import numpy as np
+import torch
+
+input = sys.argv[1]
+
+model = mlflow.pytorch.load_model("my_model")
+
+with open('my_model/'+input) as json_file:
+    data = json.load(json_file)
+#print(np.array(data['inputs']))
+print(model(torch.tensor(np.array(data['inputs'])).float()))
+
+