.

Predictor/PredictorNeuralNetwork/Predictor.py

@@ -8,15 +8,38 @@ import matplotlib.pyplot as plt
 import matplotlib.image as mpimg
 import cv2
 import numpy as np
+import os
+import shutil
+import random
 
 img_width, img_height = 150, 150
-train_data_dir = './UserflowPredictorSystem/predictor/datas/train'
-validation_data_dir = './UserflowPredictorSystem/predictor/datas/test'
+train_data_dir = './Predictor/PredictorNeuralNetwork/datas/userflows/train/'
+validation_data_dir = './Predictor/PredictorNeuralNetwork/datas/userflows/test/'
 nb_train_samples = 2000
 nb_validation_samples = 800
-epochs = 100
+epochs = 20
 batch_size = 16
 
+def copytree(src, dst, symlinks=False, ignore=None):
+    for item in os.listdir(src):
+        s = os.path.join(src, item)
+        d = os.path.join(dst, item)
+        if os.path.isdir(s):
+            shutil.copytree(s, d, symlinks, ignore)
+        else:
+            shutil.copy2(s, d)
+
+def populateDatas():
+    copytree('./Predictor/PredictorWebService/trainingImages/virtual', './Predictor/PredictorNeuralNetwork/datas/userflows/train')
+    offset = 0
+    for folder in os.listdir('./Predictor/PredictorNeuralNetwork/datas/userflows/train'):
+        numberOfFiles = len([name for name in os.listdir('./Predictor/PredictorNeuralNetwork/datas/userflows/train/' + folder)])
+        numberOfTestFiles = int(numberOfFiles / 10)
+        for idx in range(0,numberOfTestFiles):
+            file =  os.listdir('./Predictor/PredictorNeuralNetwork/datas/userflows/train/' + folder)[random.randint(0,numberOfTestFiles)]
+            shutil.copy2("./Predictor/PredictorNeuralNetwork/datas/userflows/train/" + folder + "/" + file, './Predictor/PredictorNeuralNetwork/datas/userflows/test/' + str(idx + offset) + '.png')
+        shutil.copy2("./Predictor/PredictorNeuralNetwork/datas/userflows/train/" + folder + "/" + file, './Predictor/PredictorNeuralNetwork/datas/userflows/test/' + str(idx + offset) + '_SEPARATOR.png')
+        offset = numberOfTestFiles
 
 if K.image_data_format() == 'channels_first':
     input_shape = (3, img_width, img_height)
@@ -45,7 +68,7 @@ def create_model():
     model.add(Activation('sigmoid'))
 
 
-    model.compile(loss='binary_crossentropy',
+    model.compile(loss='categorical_crossentropy',
                   optimizer='rmsprop',
                   metrics=['accuracy'])
     return model
@@ -66,13 +89,13 @@ def train_model(model):
         train_data_dir,
         target_size=(img_width, img_height),
         batch_size=batch_size,
-        class_mode='binary')
+        class_mode='categorical')
 
     validation_generator = test_datagen.flow_from_directory(
         validation_data_dir,
         target_size=(img_width, img_height),
         batch_size=batch_size,
-        class_mode='binary')
+        class_mode='categorical')
 
     model.fit_generator(
         train_generator,
@@ -81,7 +104,7 @@ def train_model(model):
         validation_data=validation_generator,
         validation_steps=nb_validation_samples // batch_size)
 
-    model.save_weights('./UserflowPredictorSystem/first_try2.h5')
+    model.save_weights('./Predictor/PredictorNeuralNetwork/weights/userflows.h5')
     return model
 
 
@@ -93,29 +116,26 @@ def load_trained_model(weights_path):
 
 
 def predict(number, model):
-    img = cv2.imread("./UserflowPredictorSystem/predictor/datas/test/" + str(number) + ".jpg")
-    im = mpimg.imread("./UserflowPredictorSystem/predictor/datas/test/" + str(number) + ".jpg")
+    img = cv2.imread("./Predictor/PredictorNeuralNetwork/datas/userflows/test/" + str(number) + ".png")
+    im = mpimg.imread("./Predictor/PredictorNeuralNetwork/datas/userflows/test/" + str(number) + ".png")
     plt.imshow(im)
     img = cv2.resize(img, (img_width,img_height))
     img = img.reshape(1, img_width, img_height, 3)
     res = model.predict(img)
-    if res == 1:
-        print('DOG')
-    else:
-        print('CAT')
+    print(res)
 
 model = create_model()
+populateDatas()
+
 model = train_model(model)
 
-import os
 os.getcwd()
 
-trained_model = load_trained_model("./UserflowPredictorSystem/first_try2.h5")
+trained_model = load_trained_model("./Predictor/PredictorNeuralNetwork/weights/userflows.h5")
 trained_model.summary()
-import random
-predict(random.randint(1,12500), trained_model)
-predict('lolly', model)
+num = random.randint(1,10)
+print(num)
+predict(num, trained_model)
 
 
-
-print(np.argmax(loaded_model.predict(img)))
+print(np.argmax(trained_model.predict(img)))

Predictor/PredictorNeuralNetwork/PredictorDEMO_CatVsDog.py

@@ -0,0 +1,119 @@
+from keras.models import Sequential
+from keras.layers import Activation, Dropout, Flatten, Dense
+from keras import backend as K
+from keras.preprocessing.sequence import pad_sequences
+from keras.preprocessing.image import ImageDataGenerator
+from keras.layers import Conv2D, MaxPooling2D
+import matplotlib.pyplot as plt
+import matplotlib.image as mpimg
+import cv2
+import numpy as np
+
+img_width, img_height = 150, 150
+train_data_dir = './Predictor/PredictorNeuralNetwork/datas/catVsDog/train/'
+validation_data_dir = './Predictor/PredictorNeuralNetwork/datas/catVsDog/test/'
+nb_train_samples = 2000
+nb_validation_samples = 800
+epochs = 100
+batch_size = 16
+
+
+if K.image_data_format() == 'channels_first':
+    input_shape = (3, img_width, img_height)
+else:
+    input_shape = (img_width, img_height, 3)
+
+def create_model():
+    model = Sequential()
+    model.add(Conv2D(32, (3, 3), input_shape=input_shape))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+
+    model.add(Conv2D(32, (3, 3)))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+
+    model.add(Conv2D(64, (3, 3)))
+    model.add(Activation('relu'))
+    model.add(MaxPooling2D(pool_size=(2, 2)))
+
+    model.add(Flatten())
+    model.add(Dense(64))
+    model.add(Activation('relu'))
+    model.add(Dropout(0.5))
+    model.add(Dense(1))
+    model.add(Activation('sigmoid'))
+
+
+    model.compile(loss='binary_crossentropy',
+                  optimizer='rmsprop',
+                  metrics=['accuracy'])
+    return model
+
+def train_model(model):
+    # this is the augmentation configuration we will use for training
+    train_datagen = ImageDataGenerator(
+        rescale=1. / 255,
+        shear_range=0.2,
+        zoom_range=0.2,
+        horizontal_flip=True)
+
+    # this is the augmentation configuration we will use for testing:
+    # only rescaling
+    test_datagen = ImageDataGenerator(rescale=1. / 255)
+
+    train_generator = train_datagen.flow_from_directory(
+        train_data_dir,
+        target_size=(img_width, img_height),
+        batch_size=batch_size,
+        class_mode='binary')
+
+    validation_generator = test_datagen.flow_from_directory(
+        validation_data_dir,
+        target_size=(img_width, img_height),
+        batch_size=batch_size,
+        class_mode='binary')
+
+    model.fit_generator(
+        train_generator,
+        steps_per_epoch=nb_train_samples // batch_size,
+        epochs=epochs,
+        validation_data=validation_generator,
+        validation_steps=nb_validation_samples // batch_size)
+
+    model.save_weights('./Predictor/PredictorNeuralNetwork/weights/catVsDog2.h5')
+    return model
+
+
+
+def load_trained_model(weights_path):
+   model = create_model()
+   model.load_weights(weights_path)
+   return model
+
+
+def predict(number, model):
+    img = cv2.imread("./Predictor/PredictorNeuralNetwork/datas/catVsDog/test/" + str(number) + ".jpg")
+    im = mpimg.imread("./Predictor/PredictorNeuralNetwork/datas/catVsDog/test/" + str(number) + ".jpg")
+    plt.imshow(im)
+    img = cv2.resize(img, (img_width,img_height))
+    img = img.reshape(1, img_width, img_height, 3)
+    res = model.predict(img)
+    if res == 1:
+        print('DOG')
+    else:
+        print('CAT')
+
+model = create_model()
+model = train_model(model)
+
+import os
+os.getcwd()
+
+trained_model = load_trained_model("./Predictor/PredictorNeuralNetwork/weights/catVsDog.h5")
+trained_model.summary()
+import random
+predict(random.randint(1,12500), trained_model)
+
+
+print(np.argmax(trained_model.predict(img)))

Predictor/PredictorWebService/build/config.gypi

@@ -0,0 +1,78 @@
+# Do not edit. File was generated by node-gyp's "configure" step
+{
+  "target_defaults": {
+    "cflags": [],
+    "default_configuration": "Release",
+    "defines": [],
+    "include_dirs": [],
+    "libraries": [],
+    "msbuild_toolset": "v141",
+    "msvs_windows_target_platform_version": "10.0.17763.0"
+  },
+  "variables": {
+    "asan": 0,
+    "build_v8_with_gn": "false",
+    "coverage": "false",
+    "debug_nghttp2": "false",
+    "enable_lto": "false",
+    "enable_pgo_generate": "false",
+    "enable_pgo_use": "false",
+    "force_dynamic_crt": 0,
+    "host_arch": "x64",
+    "icu_data_in": "..\\..\\deps/icu-small\\source/data/in\\icudt64l.dat",
+    "icu_endianness": "l",
+    "icu_gyp_path": "tools/icu/icu-generic.gyp",
+    "icu_locales": "en,root",
+    "icu_path": "deps/icu-small",
+    "icu_small": "true",
+    "icu_ver_major": "64",
+    "nasm_version": "2.14",
+    "node_byteorder": "little",
+    "node_code_cache_path": "yes",
+    "node_debug_lib": "false",
+    "node_enable_d8": "false",
+    "node_enable_v8_vtunejit": "false",
+    "node_install_npm": "true",
+    "node_module_version": 72,
+    "node_no_browser_globals": "false",
+    "node_prefix": "/usr/local",
+    "node_release_urlbase": "https://nodejs.org/download/release/",
+    "node_report": "true",
+    "node_shared": "false",
+    "node_shared_cares": "false",
+    "node_shared_http_parser": "false",
+    "node_shared_libuv": "false",
+    "node_shared_nghttp2": "false",
+    "node_shared_openssl": "false",
+    "node_shared_zlib": "false",
+    "node_tag": "",
+    "node_target_type": "executable",
+    "node_use_bundled_v8": "true",
+    "node_use_dtrace": "false",
+    "node_use_etw": "true",
+    "node_use_large_pages": "false",
+    "node_use_node_snapshot": "false",
+    "node_use_openssl": "true",
+    "node_use_v8_platform": "true",
+    "node_with_ltcg": "true",
+    "node_without_node_options": "false",
+    "openssl_fips": "",
+    "openssl_is_fips": "false",
+    "shlib_suffix": "so.72",
+    "target_arch": "x64",
+    "v8_enable_gdbjit": 0,
+    "v8_enable_i18n_support": 1,
+    "v8_enable_inspector": 1,
+    "v8_no_strict_aliasing": 1,
+    "v8_optimized_debug": 1,
+    "v8_promise_internal_field_count": 1,
+    "v8_random_seed": 0,
+    "v8_trace_maps": 0,
+    "v8_use_siphash": 1,
+    "v8_use_snapshot": 1,
+    "want_separate_host_toolset": 0,
+    "nodedir": "C:\\Users\\Lorenzo\\AppData\\Local\\node-gyp\\Cache\\12.4.0",
+    "standalone_static_library": 1,
+    "msbuild_path": "C:\\Program Files (x86)\\Microsoft Visual Studio\\2017\\BuildTools\\MSBuild\\15.0\\Bin\\MSBuild.exe"
+  }
+}

Predictor/PredictorWebService/src/image-creator/ImageCreatorService.ts

@@ -39,7 +39,7 @@ export class ImageCreatorService {
             });
 
             //todo da cambiare le dimensioni e renderle dinamiche
-            const canvas = createCanvas(1000, 800);
+            const canvas = createCanvas(150, 150);
             const ctx = canvas.getContext('2d');
             this.printHTMLElements(htmlElements, ctx);
             this.printMouseClick(mouseClicks, ctx);