Merge branch 'master' of https://gitlab.nautilus.optiputer.net/ar-noc/keras-smoke-detection

.gitlab-ci.yml

@@ -9,6 +9,7 @@ build-and-push-job:
     changes:
       - "**/*.yaml"
       - "README.md"
+      - "screenshots/*.PNG"
   script:
     - echo "{\"auths\":{\"$CI_REGISTRY\":{\"username\":\"$CI_REGISTRY_USER\",\"password\":\"$CI_REGISTRY_PASSWORD\"}}}" > /kaniko/.docker/config.json
     - /kaniko/executor --context $CI_PROJECT_DIR --dockerfile $CI_PROJECT_DIR/Dockerfile --destination $CI_REGISTRY_IMAGE:${CI_COMMIT_SHA:0:8} --destination $CI_REGISTRY_IMAGE:latest
\ No newline at end of file

Dockerfile

@@ -40,8 +40,8 @@ RUN useradd -m -s /bin/bash -N -u $NB_UID $NB_USER && \
     chown $NB_USER $CONDA_DIR -R && \
     chown $NB_USER /userdata/kerasData -R && \
     mkdir -p / && \
-    chown $NB_USER / && \
-    chpasswd $NB_USER:ar-noc
+    chpasswd $NB_USER:ar-noc && \
+    usermod -aG sudo $NB_USER
 
 USER $NB_USER
 

README.md

@@ -127,7 +127,12 @@ The following must be set
 - LRFIND_PLOT_PATH = Where the learning rate finder graph should go
 - TRAINING_PLOT_PATH = Where the training plot graph (loss & accuracy graphs) shoud go 
 3. Loading Data
-There shouldn't be a need to edit this, unless another data loading solution is desired. This section also splits the data into training  
+- Use the load_dataset() function of the load_data notebook ONLY for HPWREN HWB Database 
+- Otherwise, change the script so that the following numpy arrays are generated, if you want to use the prebuild loader in the Training notebook 
+MAKE SURE THESE in load_data.ipynb ![](screenshots/loading_in.PNG)<br /> MATCH THESE in ClassificationExample.ipynb <br /> ![](screenshot/THEOTHEREND.PNG)
+- Use the def loadData(pathToFiles) in ClassificationExample.ipynb
+
+
 4. Image Load Tester
 Tests the images to see if the loading worked
 5. Model Initialization <br />