Machine Learning project with supervise.ly

Task description :-

Create a project designed to solve the real use case, using either transfer learning example existing Mask-RCNN, VGG16, etc. or creating new model of Mask-RCNN, GANs, RNN, etc. to solve any real case problems or new problems.

Necessary requirements:

1. Make your own custom dataset using supervisely

2. Either create a new model or using existing model as transfer learning

3. Launch the training on aws cloud

What is Supervisely :

Supervisely is a web platform where you can find everything you need to build Deep Learning solutions within a single environment.

Supervisely platform covers entire R&D lifecycle for computer vision. It allows to interate from image annotation to neural networks training 10x faster:

1. Organize image annotation / data management / manipulation within a single platform at scale.
2. Integrate custom NNs or user pretrained models from Model Zoo, perform / track / reproduce tons of experiments.
3. Use data science workflows out of the box: upload new data and continuously improve the accuracy of your neural networks.
4. Combine different neural networks together into single pipeline with post processing stages and deploy these pipelines as API.
5. Utilize NNs to speed up image annotation process: platform has trainable SmartTool, supports Active Learning and Human in the Loop.

Here we go...

Step 1: Register in supervisely and create your own workspace

Step 2 : Import data

Step 3: Using supervisely tool annotate the images

Step 4 : Data preparation for training takes most of data scientists's time. In addition, there is a high probability of mistakes while performing such process.

Supervisely solved this issue by designing a special language named DTL that allows to fully automate data manipulation: merge projects and datasets, make classes mapping, various augmentations of images and annotations, save to different formats and more.

This process is defined with a JSON based config file.

Code for DTL

[
  {
    "dst": "$data",
    "src": [
      "Console Dataset/*"
    ],
    "action": "data",
    "settings": {
      "classes_mapping": "default"
    }
  },
  {
    "dst": "$flip_vert",
    "src": [
      "$data"
    ],
    "action": "flip",
    "settings": {
      "axis": "vertical"
    }
  },
  {
    "dst": "Console Dataset_Aug",
    "src": [
      "$data",
      "$resized_result",
      "$resized_result2",
      "$noise_result",
      "$flip_vert"
    ],
    "action": "supervisely",
    "settings": {}
  },
  {
    "action": "resize",
    "src": [
      "$data"
    ],
    "dst": "$resized_result",
    "settings": {
      "width": 800,
      "height": -1,
      "aspect_ratio": {
        "keep": true
      }
    }
  },
  {
    "action": "noise",
    "src": [
      "$data"
    ],
    "dst": "$noise_result",
    "settings": {
      "mean": 10,
      "std": 60
    }
  },
  {
    "action": "resize",
    "src": [
      "$data"
    ],
    "dst": "$resized_result2",
    "settings": {
      "width": 300,
      "height": -1,
      "aspect_ratio": {
        "keep": true
      }
    }
  }

]

Step 5 : Add model

Now run the model for training

when you click train it will show the error

Now bring your own agent

Step 6 : Use AWS instance for agent

Now run the code provide by supervisely

Input image

Output image

THANK YOU !!