freshness analysis

freshness/flask_server/app.py

+from flask import Flask, render_template, redirect, url_for
+import os
+import cv2
+from matplotlib import image
+import numpy as np
+from numpy.lib.type_check import imag
+import pandas as pd
+import matplotlib.pyplot as plt
+from tqdm import tqdm
+from random import shuffle
+import pickle
+from tensorflow.keras.utils import to_categorical
+import keras
+from keras.layers import Dense, Dropout, Conv2D, MaxPooling2D, Activation, Flatten, BatchNormalization, SeparableConv2D
+from keras.models import Sequential
+from keras.models import Model, load_model
+from PIL import Image
+from urllib import request
+from io import BytesIO
+from keras_preprocessing import image
+import urllib.request
+import tensorflow as tf
+
+from tensorflow.keras import datasets, layers, models
+
+model = models.Sequential()
+
+new_model = load_model(
+    'F:/EDUCATION/SLIIT/4thYear 1st semester/Research Project/python/python cnn/python cnn/Working/types.h5')
+
+img = cv2.imread(
+    "F:/EDUCATION/SLIIT/4thYear 1st semester/Research Project/python/python cnn/quality analysis/dataset/Banana/test/freshbanana/(102).png", 1)
+img = cv2.resize(img, (50, 50))
+img = np.reshape(img, [1, 50, 50, 3])
+predicted_value = np.argmax(model.predict(img))
+print(model.predict(img))
+type = ""
+if predicted_value == 0:
+    type = "BANANA"
+elif predicted_value == 1:
+    type = "TOMATO"
+else:
+    type = "cant predict"
+
+
+model = Sequential()
+model.add(Conv2D(32, (3, 3), kernel_initializer='he_uniform',
+          padding='same', activation='relu', input_shape=(100, 100, 3)))
+model.add(BatchNormalization())
+model.add(SeparableConv2D(32, (3, 3), kernel_initializer='he_uniform',
+          padding='same', activation='relu'))
+model.add(MaxPooling2D((2, 2)))
+model.add(BatchNormalization())
+model.add(Dropout(0.3))
+
+model.add(SeparableConv2D(64, (3, 3), kernel_initializer='he_uniform',
+          padding='same', activation='relu'))
+model.add(SeparableConv2D(64, (3, 3), kernel_initializer='he_uniform',
+          padding='same', activation='relu'))
+model.add(BatchNormalization())
+model.add(MaxPooling2D((2, 2)))
+model.add(Dropout(0.4))
+
+model.add(Conv2D(128, (3, 3), kernel_initializer='he_uniform',
+          padding='same', activation='relu'))
+
+
+model.add(Conv2D(128, (3, 3), kernel_initializer='he_uniform',
+          padding='same', activation='relu'))
+model.add(BatchNormalization())
+model.add(MaxPooling2D((2, 2)))
+model.add(Dropout(0.5))
+
+model.add(Flatten())
+
+
+model.add(Dense(128, activation='relu', kernel_initializer='he_uniform'))
+model.add(Dropout(0.3))
+
+model.add(Dense(1, activation='sigmoid'))
+new_model = load_model(
+    'F:/EDUCATION/SLIIT/4thYear 1st semester/Research Project/python/python cnn/quality analysis/dataset/Banana/working/rottenvsfresh.h5')
+
+imge = cv2.imread(
+    "F:/EDUCATION/SLIIT/4thYear 1st semester/Research Project/python/python cnn/quality analysis/dataset/Banana/test/freshbanana/(102).png", 1)
+imge = cv2.cvtColor(imge, cv2.COLOR_BGR2RGB)
+imge = cv2.resize(imge, (100, 100))
+imge = np.reshape(imge, [1, 100, 100, 3])
+imge = np.array(imge).astype('float32')/255
+predicted_value = model.predict_classes(imge)
+print(predicted_value)
+print(model.predict(imge))
+
+if predicted_value == 0:
+    print("fresh_banana")
+elif predicted_value == 1:
+    print("rotten_banana")
+else:
+    print("cant predict")
+
+outputs = ""
+
+if predicted_value == 0:
+    outputs = "Fresh Banana"
+elif predicted_value == 1:
+    outputs = "Rotten Banana"
+else:
+    outputs = "Cant predict"
+
+
+app = Flask(__name__)
+
+
+@app.route('/')
+def Home():
+
+    return render_template("index.html")
+
+
+@app.route('/predict/<weight>/<paths>')
+def predict(weight,paths):
+
+    gram = 0.0 
+    quality = ""
+    size = ""
+    weight1 = float(weight)
+
+    gram = weight1 * 1000
+    
+    if gram < 114:
+        size = "Small"
+        quality = "Grade A"
+    elif gram < 151:
+        size = "Medium"
+        quality = "Grade B"
+    elif gram > 151:
+        size = "Large"
+        quality = "Grade C"
+    else:
+        size = "Cant predict"    
+     
+
+    return render_template("predict.html", Predicted=outputs, type=type, weight=gram, sizee=size, qualityy=quality, paths=paths)
+
+
+if __name__ == "__main__":
+    app.run(debug=True)

freshness/freshnessanalysis.html

+<html>
+
+<head>
+    <title>Cupertino Streaming</title>
+    <script src="https://ajax.googleapis.com/ajax/libs/jquery/3.5.1/jquery.min.js"></script>
+</head>
+
+<body>
+    <h1>Welcome to Orgi Check</h1>
+    <img src="http://192.168.1.6/" alt="http://192.168.1.6/" class="shrinkToFit" width="404" height="303">
+    <span id="loadvalue">0.0</span>
+</body>
+
+</html>
+
+<script>
+    var xmlHttp;
+    if (window.XMLHttpRequest) {
+        xmlHttp = new XMLHttpRequest();
+    } else if (window.ActiveXObject) {
+        xmlHttp = new ActiveXObject("Microsoft.XMLHTTP");
+    } else {
+        alert("Browser Doesnt Support Ajax!");
+    }
+    if (xmlHttp !== null) {
+
+        xmlHttp.onreadystatechange = async function () {
+
+            if (xmlHttp.readyState === 4) {
+                var res = xmlHttp.responseText;
+                document.getElementById("loadvalue").innerHTML = res;
+
+
+
+            }
+
+        };
+        xmlHttp.open("GET", "http://192.168.1.5/GetValue/", true);
+        xmlHttp.send();
+
+    }
+
+
+
+
+</script>
\ No newline at end of file