Merge branch 'IT18124354_SALUKB.M.M' into 'master'

create cnn model with more diseases

See merge request !23

skin_disease/API.py

+import os
+import predict_image_class
+from flask import Flask, request
+from flask_cors import CORS, cross_origin
+from flask import send_file
+
+app = Flask(__name__)
+cors = CORS(app)
+uploadPath = "uploads"
+
+@app.route('/predict', methods=['POST'])
+@cross_origin()
+def uploadImage():
+    print(os.getcwd())
+    f = request.files['file']
+    splits = f.filename.split("/")
+    print(splits[len(splits)-1])
+    # os.remove(os.path.join(uploadPath, "upload.jpg"))
+    f.save(os.path.join(uploadPath, "upload.jpg"))
+    return predict_image_class.predictImageClass("uploads/upload.jpg")
+
+@app.route('/getImage', methods=['POST', 'GET'])
+@cross_origin()
+def getImage():
+    return send_file("uploads/upload.jpg", mimetype='image/gif')
+
+if __name__ == '__main__':
+    app.run(debug=True, port=5000, host="0.0.0.0")

skin_disease/convolutional_neural_network.py

@@ -9,11 +9,11 @@ import matplotlib.pyplot as plt
 
 img_width, img_height = 350, 350
 
-train_data_dir = 'data/train'
-validation_data_dir = 'data/test'
-nb_train_samples = 168
-nb_validation_samples = 20
-epochs = 20
+train_data_dir = 'v2_data/train'
+validation_data_dir = 'v2_data/test'
+nb_train_samples = 150
+nb_validation_samples = 30
+epochs = 15
 batch_size = 20
 
 if K.image_data_format() == 'channels_first':
@@ -26,20 +26,20 @@ model.add(Conv2D(32, (2, 2), input_shape = input_shape))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(pool_size =(2, 2)))
 
-model.add(Conv2D(32, (2, 2)))
+model.add(Conv2D(64, (2, 2)))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(pool_size =(2, 2)))
 
-model.add(Conv2D(64, (2, 2)))
+model.add(Conv2D(32, (2, 2)))
 model.add(Activation('relu'))
 model.add(MaxPooling2D(pool_size =(2, 2)))
 
 model.add(Flatten())
-model.add(Dense(64))
+model.add(Dense(32))
 model.add(Activation('relu'))
 
 model.add(Dropout(0.5))
-model.add(Dense(2))
+model.add(Dense(3))
 model.add(Activation('softmax'))
 
 model.compile(loss ='sparse_categorical_crossentropy',

skin_disease/predict_image_class.py

+import random
+
 from keras.layers import Activation
 import keras
 import numpy as np
@@ -14,10 +16,6 @@ def predictImageClass(image):
     K.clear_session()
     # tensorflow.reset_default_graph()
 
-    nb_train_samples = 112
-    nb_validation_samples = 20
-    epochs = 10
-    batch_size = 2
     img_width, img_height = 350, 350
 
     if K.image_data_format() == 'channels_first':
@@ -25,31 +23,32 @@ def predictImageClass(image):
     else:
         input_shape = (img_width, img_height, 3)
 
-    modelI = Sequential()
-    modelI.add(Conv2D(32, (2, 2), input_shape=input_shape))
-    modelI.add(Activation('relu'))
-    modelI.add(MaxPooling2D(pool_size=(2, 2)))
+    model = Sequential()
+    model.add(Conv2D(32, (2, 2), input_shape = input_shape))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size =(2, 2)))
+
+    model.add(Conv2D(64, (2, 2)))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size =(2, 2)))
 
-    modelI.add(Conv2D(32, (2, 2)))
-    modelI.add(Activation('relu'))
-    modelI.add(MaxPooling2D(pool_size=(2, 2)))
+    model.add(Conv2D(32, (2, 2)))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size =(2, 2)))
 
-    modelI.add(Conv2D(64, (2, 2)))
-    modelI.add(Activation('relu'))
-    modelI.add(MaxPooling2D(pool_size=(2, 2)))
+    model.add(Flatten())
+    model.add(Dense(32))
+    model.add(Activation('relu'))
 
-    modelI.add(Flatten())
-    modelI.add(Dense(64))
-    modelI.add(Activation('relu'))
-    modelI.add(Dropout(0.5))
-    modelI.add(Dense(2))
-    modelI.add(Activation('softmax'))
+    model.add(Dropout(0.5))
+    model.add(Dense(3))
+    model.add(Activation('softmax'))
 
-    modelI.compile(loss='sparse_categorical_crossentropy',
+    model.compile(loss='sparse_categorical_crossentropy',
                    optimizer='adam',
                    metrics=['accuracy'])
 
-    modelI.load_weights('model_saved.h5')
+    model.load_weights('model_saved.h5')
 
     sess = keras.backend.get_session()
     # image = request.args.get('image', default = 1, type = str)
@@ -63,12 +62,13 @@ def predictImageClass(image):
     img = img.eval(session=sess)  # convert to numpy array
     img = np.expand_dims(img, 0)  # make 'batch' of 1
 
-    pred = modelI.predict(img)
+    pred = model.predict(img)
     # pred = labels["label_names"][np.argmax(pred)]
     print(pred)
-    y = ["Sarcoptic & demodectic mange", "Ring worms"]
+    y = ["Demodatic", "Dermatites", "ringworms"]
     print(np.argmax(pred))
     print(y[np.argmax(pred)])
+    i = random.randint(0, 1)
     return {
         "pred": y[np.argmax(pred)],
         "accuracy": str(pred[0][np.argmax(pred)])