diff --git a/README.md b/README.md
index da00660fd91864126d7f41a9269c06ee0c3e7ede..6b03b8fe62b0ad6e39b6d83421d247f24db0b10a 100644
--- a/README.md
+++ b/README.md
@@ -1,18 +1,168 @@
-This repo contains the workflow for training keras models. We have used this to
-train our smoke-classification/segmentatino CNN using the HPWREN database http://hpwren.ucsd.edu/HWB/HPWREN-FIgLib/
+# Keras Container on Nautilus
-<img src="http://hpwren.ucsd.edu/HWB/HPWREN-FIgLib/20180806-Holy-sp-s-mobo-c/1533587430_+01680.jpg">
-<pre>
+This project allows for the usage of Keras on a jupter notebook in Nautilus (as an importable package). With this project, we are able to train keras models on the Nautilus cloud.
+## Getting Started
+These instructions will get you a copy of the project up and running on your namespace.
+### Prerequisites
+Nautilus namespace
+Nvidia GPU
+## Components
-HPWREN Fire Ignition image Library (FIgLib), based on images from fixed cameras at HPWREN sites.
-The primary purpose is the creation of data sets for 40 minutes before and after fire ignitions for neural network training.
-For illustration purposes video animations are included as well. The image file names are:
+The project has the following components:
+```
+- Dockerfile (Dockerfile)
+- Continous Integration Yaml (.gitlab-ci.yml)
+- An example jupter notebook (ClassificationExample.ipynb)
+- Nautilus deployment Yaml (kerasDeloyment.yaml)
+```
- origin_timestamp _ offset_(sec)_from_visible_plume_appearance .jpg
+### Dockerfile
+```
+This file is used to make the enviroment necessary to run Keras on Jupyter Notebook. Unless
+truely needed, please avoid editing this file.
+```
+
+### Continous Integration Yaml
+```
+This file is used to utilize gitlab's continous integration feature. Nautilus uses kaniko instead of docker, which can be changed back into using a docker image by replacing the current .gitlab-ci.yml with the "dockerBased-ci.yml" file.
+```
+
+### Jupter notebook
+```
+This was the notebook I used to train an wildfire classification model. The structure and import commands can be used to utilize keras in
+other notebooks. I will go over the specific details below.
+```
+
+### Nautilus Deployment Yaml
+
+If you are planning to use this implementation on another Nautilus namespace, this portion of the readme is especially important. Here are the important aspects of this yaml:
+
+
+1. Changing namespace address <br /> <br />
+ <br />
+**Change the name and the namespace entries to the current working namespace and a suitable name**
+
+2. Change the resource requests <br /> <br />
+ <br />
+**Change the numbers to suit the task**
+
+
+3. Mount volumne <br /><br />
+ <br />
+**Very important for crash-resistance. I highly recommend saving all work onto mounted directory**
+
+
+4. Choose GPU type <br /><br />
+ <br />
+If doing intensive training, choose larger/more expensive GPUs
+
+## Using the Components
+
+### Starting the development and accessing jupyter notebook
+1. Go into kerasDeloyment.yaml file
+2. Choose the RAW file format <br />
+ <br />
+
+3. copy url of RAW file <br />
+ <br />
+
+4. execute yaml file on nautilius namespace <br />
+
+
+5. exec into nautilus pod <br />
+
+
+6. Navigate to /userdata/kerasData and Start Jupyter Notebook <br /><br />
+<br />
+**Note: The port number choice does not matter, as long as there are not other processes running on that port. If a port is already in use, jupyter will automatically assign another port. Make sure to match the port number in the next step** <br /> <br />
+<br />
+_What happens when a wrong port is chosen_ <br />
+
+7. Go to your computer terminal and start port-forward, matching the port in the pod <br />
+<br />
+
+8. Go to the localhost address<br />
+<br />
+
+9. Test for keras
+Create a new notebook or use the ClassificationExample.ipynb file
+- Run the following tests <br />
+ <br /><br />
+<!-- <br /><br /> -->
+**_Make sure that the outputs return True or some name._**<br />
+**You are now ready to use Keras on a jupyter notebook hosted on Kubernetes**
+
+### Using Keras in Notebook
+
+#### EXTREMELY IMPORTANT!
+In order to prevent Keras from assigning too much GPU memory and stalling training efforts later on, run this:
+ <br />
+If you see an error, shutdown the network server and try again <br />
+<br/>
+If you see nvidia-smi memory allocation at 0/- you have suceeded in reseting the GPU <br />
+<br />
+
+Please refer to [Keras Documentation](https://keras.io/) for instructions and information
+
+I used the notebook for the following:
+- Training a CNN on the notebook for reference
+- Using a LearningRateFinder to find the optimal learning rate
+
+
+## Using the Fire-Classification training
+
+1. Write the network using Keras layers <br />
+ <br /> <br />
+2. Set the paths <br />
+ <br />
+The following must be set
+- FIRE_PATH = Path of the directory with the fire images
+- Non_FIRE_PATH = Path of the directory with images without fire
+- MODEL_PATH = Path where the saved model file should go
+- 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
+4. Image Load Tester
+Tests the images to see if the loading worked
+5. Model Initialization <br />
+<br />
+- The width, height and depth is the data format. Classes are the number of condiitons in the data. In our case: ["Fire", "Not-Fire"]
+- Change the optimization function if you know what you are doing. We are using a starndard SDG
+6. Learning Rate Finder <br />
+Run to find the place where the Network starts to learn
+ <br />
+ <br />
+More information is availbe here [pyimagesearch](https://www.pyimagesearch.com/2019/08/05/keras-learning-rate-finder/)
+
+Finally, fill out the INIT_LR from what you learned from above
+<br />
+7. Train <br />
+ <br />
+8. Get results
+ <br />
+You will find the accuracy measures in the table. Find the model in fire_detection.model
+
+
+
+
+
+
+
+## Contributors
+
+* **Byungheon Jeong** - [byungheon-jeong](https://gitlab.nautilus.optiputer.net/byungheon-jeong)
+* **Spence Chen** - [Spencer](https://gitlab.nautilus.optiputer.net/Spencer123)
+* **Isaac Nealey** - [Isacc](https://gitlab.nautilus.optiputer.net/inealey)
+* **John Graham** - [John](https://gitlab.nautilus.optiputer.net/jjgraham)
+
+## Acknowledgments
+
+* The Dockerfile is from the Dockerhub of the Keras team
+* The Fire CNN and the Learning Rate finder is adapted from Adrain's excellent blog on first-detection - [Pyimagesearch](https://www.pyimagesearch.com/2019/11/18/fire-and-smoke-detection-with-keras-and-deep-learning/)
-Use of this image data requires a credit reference to "http://hpwren.ucsd.edu/" in derivative work.
\ No newline at end of file
diff --git a/dockerBasedci.yaml b/dockerBasedci.yaml
new file mode 100644
index 0000000000000000000000000000000000000000..c74ba9ccadd84c040f2470c815a971c68b6c9287
--- /dev/null
+++ b/dockerBasedci.yaml
@@ -0,0 +1,15 @@
+image: docker:git
+before_script:
+ - docker login -u gitlab-ci-token -p $CI_BUILD_TOKEN gitlab-registry.nautilus.optiputer.net
+
+stages:
+ - build-and-push
+
+build-and-push-job:
+ stage: build-and-push
+ tags:
+ - build-as-docker
+ script:
+ - docker build --no-cache -t gitlab-registry.nautilus.optiputer.net/${CI_PROJECT_NAMESPACE}/${CI_PROJECT_NAME}:${CI_COMMIT_SHA:0:8} .
+ - docker tag gitlab-registry.nautilus.optiputer.net/${CI_PROJECT_NAMESPACE}/${CI_PROJECT_NAME}:${CI_COMMIT_SHA:0:8} gitlab-registry.nautilus.optiputer.net/${CI_PROJECT_NAMESPACE}/${CI_PROJECT_NAME}:latest
+ - docker push gitlab-registry.nautilus.optiputer.net/${CI_PROJECT_NAMESPACE}/${CI_PROJECT_NAME}
diff --git a/screenshots/eng.PNG b/screenshots/eng.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..bca2341126300604a82ee1bc318e101e23236a03
Binary files /dev/null and b/screenshots/eng.PNG differ
diff --git a/screenshots/execinto.PNG b/screenshots/execinto.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..d82f59b910374215a066856f92cc1388b694186a
Binary files /dev/null and b/screenshots/execinto.PNG differ
diff --git a/screenshots/firstBatch.PNG b/screenshots/firstBatch.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..69f5457c56fd01d240c2fc3cb9f9dd4fa9ace442
Binary files /dev/null and b/screenshots/firstBatch.PNG differ
diff --git a/screenshots/hickups.PNG b/screenshots/hickups.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..39500d5d76123a552483551f8ead519d36d93df3
Binary files /dev/null and b/screenshots/hickups.PNG differ
diff --git a/screenshots/init.png b/screenshots/init.png
new file mode 100644
index 0000000000000000000000000000000000000000..301b94fffb46cde890ba893fc949d914b41d24cc
Binary files /dev/null and b/screenshots/init.png differ
diff --git a/screenshots/initlr.png b/screenshots/initlr.png
new file mode 100644
index 0000000000000000000000000000000000000000..977b57acda7538ea22154850da63b394f9269ae8
Binary files /dev/null and b/screenshots/initlr.png differ
diff --git a/screenshots/kubectinit.PNG b/screenshots/kubectinit.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..e2b60748cd2c84080946ce369700bcd801e2b932
Binary files /dev/null and b/screenshots/kubectinit.PNG differ
diff --git a/screenshots/localhostaddress.png b/screenshots/localhostaddress.png
new file mode 100644
index 0000000000000000000000000000000000000000..1af3b23c7070fd3a28255b5fd15f393d812d726f
Binary files /dev/null and b/screenshots/localhostaddress.png differ
diff --git a/screenshots/lrf.PNG b/screenshots/lrf.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..516f506e2eebf21f83d6fa1a343af33fb7d25132
Binary files /dev/null and b/screenshots/lrf.PNG differ
diff --git a/screenshots/lrfplot.PNG b/screenshots/lrfplot.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..5ea5feba482c71cd90bb7794be9281e06ed4f2f1
Binary files /dev/null and b/screenshots/lrfplot.PNG differ
diff --git a/screenshots/modelbuild.PNG b/screenshots/modelbuild.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..5efc64ed32aa63519c9eeb2fcea739e30640ce0c
Binary files /dev/null and b/screenshots/modelbuild.PNG differ
diff --git a/screenshots/nautilusDeploymentGPUrequest.PNG b/screenshots/nautilusDeploymentGPUrequest.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..c2202de033a3da16d1d18b2509ce5501d5d60242
Binary files /dev/null and b/screenshots/nautilusDeploymentGPUrequest.PNG differ
diff --git a/screenshots/nautilusDeploymentNamespaceName.PNG b/screenshots/nautilusDeploymentNamespaceName.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..e452e0844d01b615736281f89daa814461443aa3
Binary files /dev/null and b/screenshots/nautilusDeploymentNamespaceName.PNG differ
diff --git a/screenshots/nautilusDeploymentResources.PNG b/screenshots/nautilusDeploymentResources.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..17f4f08d15940c7da17d8e77ea5862fcec527809
Binary files /dev/null and b/screenshots/nautilusDeploymentResources.PNG differ
diff --git a/screenshots/nautilusDeploymentStorage.PNG b/screenshots/nautilusDeploymentStorage.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..c2202de033a3da16d1d18b2509ce5501d5d60242
Binary files /dev/null and b/screenshots/nautilusDeploymentStorage.PNG differ
diff --git a/screenshots/nvidiasmireg.PNG b/screenshots/nvidiasmireg.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..70c1ccd81dc7bd2666edd564586f94410b3da822
Binary files /dev/null and b/screenshots/nvidiasmireg.PNG differ
diff --git a/screenshots/pathfields.PNG b/screenshots/pathfields.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..1e1926774aa67fb142eebb34036e46b3ea2f2167
Binary files /dev/null and b/screenshots/pathfields.PNG differ
diff --git a/screenshots/portforward.PNG b/screenshots/portforward.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..7c07994d28d297ee2fe5c6a1a9d667f0ca00affc
Binary files /dev/null and b/screenshots/portforward.PNG differ
diff --git a/screenshots/rawaddress.PNG b/screenshots/rawaddress.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..aa4de1d6960594b4fc71c56218072d1c051263c5
Binary files /dev/null and b/screenshots/rawaddress.PNG differ
diff --git a/screenshots/rawfile.PNG b/screenshots/rawfile.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..9d807309d2418a1761fd1977f8a2c9fcde988352
Binary files /dev/null and b/screenshots/rawfile.PNG differ
diff --git a/screenshots/results.PNG b/screenshots/results.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..e27acad462efd7eedafc47701b5bbb0e39e29f01
Binary files /dev/null and b/screenshots/results.PNG differ
diff --git a/screenshots/secondBatch.png b/screenshots/secondBatch.png
new file mode 100644
index 0000000000000000000000000000000000000000..c8bdfb2e9f8a89d3594039eda67e3e17efdfe258
Binary files /dev/null and b/screenshots/secondBatch.png differ
diff --git a/screenshots/startTraining.PNG b/screenshots/startTraining.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..d28525996eb2c511a04a7750b372742c61481af2
Binary files /dev/null and b/screenshots/startTraining.PNG differ
diff --git a/screenshots/startjupyter.PNG b/screenshots/startjupyter.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..12454faf495bde332a87ee44ecbfd54e4ad7508d
Binary files /dev/null and b/screenshots/startjupyter.PNG differ
diff --git a/screenshots/toolate.PNG b/screenshots/toolate.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..3e07e60c447e7c4a5137279053c30fd2c57e2267
Binary files /dev/null and b/screenshots/toolate.PNG differ
diff --git a/screenshots/usingotherports.PNG b/screenshots/usingotherports.PNG
new file mode 100644
index 0000000000000000000000000000000000000000..9d162f4f7e2b8b8fd5c09d312d65494aa3de3182
Binary files /dev/null and b/screenshots/usingotherports.PNG differ