JS script to prepare json files for performing object detection on AWS Sage Maker. It needs a csv input containing: image_name with extensions (str), img-height (int) , img-width (int), depth (int), left (int), top (int), width (int), height (int), label (str), label_id (int). This csv can have duplicate image_path value to represent different o…

ODjson_from_csv.js

const fs = require("fs");
const path = require("path");
const csv = require("fast-csv");
let megaJSON = {}; //will contain a json of multiple jsons
let aws_s3_URL = "<s3-data-url>"; //s3 url

// csv header image_path,img-height,img-width,depth,left,top,width,height,label,label_id
// csv can have duplicate image_path for multiple ODs (left,top,width,height) in one image
// <"image-name-1"> | 200 | 300 | 3 | 45 | 100 | 56 | 200 | <"label-1"> | 0
// <"image-name-1"> | 200 | 300 | 3 | 50 | 200 | 70 | 300 | <"label-2"> | 1

fs.createReadStream(path.resolve(__dirname, "annotations.csv"))
  .pipe(
    csv.parse({
      headers: true,
    })
  )
  .on("error", (error) => console.error(error))
  .on("data", (row) => {
    let annotations_obj = {
      class_id: row.label_id,
      left: row.left,
      top: row.top,
      width: row.width,
      height: row.height,
    };

    let categoriesObj = {
      class_id: row.label_id,
      name: row.label,
    };

    let imagePath = String(row.image_path).substring(0, String(row.image_path).lastIndexOf(".")); // remove .jpg or other extensions
// the final.json created will have key as just the image-name (without extensions)
    if (megaJSON[imagePath]) {
      megaJSON[imagePath]["annotations"].push(annotations_obj);

      let class_ids_available = [];

      for (let i of megaJSON[imagePath]["categories"]) {
        class_ids_available.push(i["class_id"]);
      }

      let search_result = class_ids_available.indexOf(row.label_id);

      if (search_result < 0) {
        megaJSON[imagePath]["categories"].push(categoriesObj);
      }
    } else {
      megaJSON[imagePath] = {};
      megaJSON[imagePath]["file"] = String(row.image_path); //image file name with extensions
      megaJSON[imagePath]["annotations"] = [];
      megaJSON[imagePath]["categories"] = [];
      megaJSON[imagePath]["image_size"] = [];

      let imageSizeObject = {
        width: row["img_width"],
        height: row["img_height"],
        depth: row.channel,
      };

      // push the objects respectively
      megaJSON[imagePath]["image_size"].push(imageSizeObject);
      megaJSON[imagePath]["annotations"].push(annotations_obj);
      megaJSON[imagePath]["categories"].push(categoriesObj);
    }

  })
  .on("end", (rowCount) => {
    console.log("ALL DONE GG ");
    fs.writeFileSync(
      path.resolve(__dirname, "final.json"), //json containing image jsons
      JSON.stringify(megaJSON)
    );
    jsonWalk(megaJSON);
  });

// breaking final json into separate image.json and storing in JASONS_ALL/
function jsonWalk(obj) {
  for (var key in obj) {
    if (obj.hasOwnProperty(key)) {
      var val = obj[key];

      fs.writeFileSync(
        path.resolve(__dirname, "./JSONS_ALL/" + key + ".json"),
        JSON.stringify(val),
        { flag: "w" }
      );
    }
  }

  console.log("All JSON Files Ceated --");
}