NanoNets Object Detection Node.js Sample

Golang Sample	Python Sample	Node.js Sample

---

Tracking the Millenium Falcon

Images and annotations taken from - https://github.com/bourdakos1/Custom-Object-Detection

Images consists of frames taken from a clip from Star Wars: The Force Awakens.

Annotations are present for each frame and have the same name as the image name. You can find the example to train a model in python and node, by updating the api-key and model id in corresponding file. There is also a pre-processed json annotations folder that are ready payload for nanonets api, the script used is code/xml-to-json.js .

---

Build an Object Detector for the Millenium Falcon

Note: Make sure you have node.js and npm installed on your system

Step 1: Clone the Repo

git clone https://github.com/NanoNets/object-detection-sample-nodejs.git
cd object-detection-sample-nodejs
npm install ./code/

Step 2: Get your free API Key

Get your free API Key from http://app.nanonets.com/user/api_key

Step 3: Set the API key as an Environment Variable

export NANONETS_API_KEY=YOUR_API_KEY_GOES_HERE

Step 4: Create a New Model

node ./code/create-model.js

_Note: This generates a MODEL_ID that you need for the next step

Step 5: Add Model Id as Environment Variable

export NANONETS_MODEL_ID=YOUR_MODEL_ID

_Note: you will get YOUR_MODEL_ID from the previous step

Step 6: Upload the Training Data

The training data is found in images (image files) and annotations (annotations for the image files)

node ./code/upload-training.js

Step 7: Train Model

Once the Images have been uploaded, begin training the Model

node ./code/train-model.js

Step 8: Get Model State

The model takes ~2 hours to train. You will get an email once the model is trained. In the meanwhile you check the state of the model

node ./code/model-state.js

Step 9: Make Prediction

Once the model is trained. You can make predictions using the model

node ./code/prediction.js PATH_TO_YOUR_IMAGE.jpg

Sample Usage:

node ./code/prediction.js ./images/videoplayback0051.jpg