ahmed-deftoner
diff --git a/‎.gitattributes
+2 b/‎.gitattributes
+2
diff --git a/‎.gitignore
+1 b/‎.gitignore
+1
diff --git a/‎app.js
+24 b/‎app.js
+24
diff --git a/‎controllers/predict.controllers.js
+47 b/‎controllers/predict.controllers.js
+47
diff --git a/‎index.html
+28 b/‎index.html
+28
@@ -0,0 +1,2 @@
+# Auto detect text files and perform LF normalization
+* text=auto
@@ -0,0 +1 @@
+node_modules
@@ -0,0 +1,24 @@
+const express = require('express');
+const logger = require('morgan');
+const cors = require('cors');
+const app = express();
+
+const corsOptions = {
+  origin: '*',
+};
+
+app.use(logger('dev'));
+app.use(express.json());
+app.use(cors(corsOptions));
+app.use(express.urlencoded({ extended: false }));
+
+app.get('/', (req, res) => {
+  res.send('Image Classifier API')
+});
+
+const predictRouter = require('./routes/predict.route')
+app.use('/predict', predictRouter);
+PORT = process.env.PORT || 3000;
+app.listen(PORT);
+
+console.log(`Running server at http://localhost:${PORT}`);
@@ -0,0 +1,47 @@
+const tf = require('@tensorflow/tfjs');
+const mobilenet = require('@tensorflow-models/mobilenet');
+const image = require('get-image-data');
+const fs = require('fs');
+//loading
+exports.loadmodel = async function MobilenetLoad(){
+   console.log('Loading.......')
+   const model = await mobilenet.load();
+};
+
+exports.makePredictions = async (req, res, next) => {
+  const imagePath = './images/test-image.jpg';
+  try {
+    const loadModel = async (img) => {
+      const output = {};
+      // classify
+      console.log("Predicting...");
+      output.predictions = await model.classify(img);
+      console.log(output);
+      res.statusCode = 200;
+      res.json(output);
+    };
+    await image(imagePath, async (err, imageData) => {
+      // pre-process image
+      const numChannels = 3;
+      const numPixels = imageData.width * imageData.height;
+      const values = new Int32Array(numPixels * numChannels);
+      const pixels = imageData.data;
+      for (let i = 0; i < numPixels; i++) {
+        for (let channel = 0; channel < numChannels; ++channel) {
+          values[i * numChannels + channel] = pixels[i * 4 + channel];
+        }
+      }
+      const outShape = [imageData.height, imageData.width, numChannels];
+      const input = tf.tensor3d(values, outShape, 'int32');
+      await loadModel(input);
+// delete image file
+      fs.unlinkSync(imagePath, (error) => {
+        if (error) {
+          console.error(error);
+        }
+      });
+    });
+  } catch (error) {
+    console.log(error)
+  }
+};
@@ -0,0 +1,28 @@
+<!DOCTYPE html>
+<html lang="en">
+<body>
+  <form name="myForm" method="post" enctype="multipart/form-data">
+    Select Image: <input type='file' name='file' id='image-upload'>
+    <button type='submit' id="submit-btn">Submit</button>
+  </form>
+  <div id="result"></div>
+  <script>
+    const button = document.querySelector('#submit-btn')
+    button.addEventListener('click', async (e) => {
+      e.preventDefault();
+      const URL = 'https://image-clf-api.herokuapp.com/predict'
+      const image = document.querySelector('#image-upload');
+      const resultDiv = document.querySelector('#result')
+      const formData = new FormData();
+      formData.append("file", image.files[0]);
+      const response = await fetch(URL, {
+        method: 'POST',
+        body: formData
+      });
+      const result = await response.json();
+      resultDiv.innerHTML = JSON.stringify(result.predictions);
+      console.log(result);
+    });
+  </script>
+</body>
+</html>
Original file line number	Diff line number	Diff line change
`@@ -0,0 +1,2 @@`
	`1`	`+# Auto detect text files and perform LF normalization`
	`2`	`+* text=auto`