ImgToMap finished

frontend/js/script.js

@@ -26,7 +26,7 @@ $('document').ready(function(){
                 }
                 reader.readAsDataURL($('#input_handle')[0].files[0]);
 
-                $('#output_image').attr("src", 'http://127.0.0.1:5000/static/uploads/' + data);
+                $('#output_image').attr("src", 'http://127.0.0.1:5000/static/outputs/' + data);
             }
         });
     });

server/codes/blurtohd.py

@@ -0,0 +1,108 @@
+# example of loading a pix2pix model and using it for image to image translation
+from keras.models import load_model
+from numpy import load
+from numpy import vstack
+from matplotlib import pyplot
+from numpy.random import randint
+
+# load and prepare training images
+def load_real_samples(filename):
+	# load compressed arrays
+	data = load(filename)
+	# unpack arrays
+	X1, X2 = data['arr_0'], data['arr_1']
+	# scale from [0,255] to [-1,1]
+	X1 = (X1 - 127.5) / 127.5
+	X2 = (X2 - 127.5) / 127.5
+	return [X1, X2]
+
+# plot source, generated and target images
+def plot_images(src_img, gen_img, tar_img):
+	images = vstack((src_img, gen_img, tar_img))
+	# scale from [-1,1] to [0,1]
+	images = (images + 1) / 2.0
+	titles = ['Source', 'Generated', 'Expected']
+	# plot images row by row
+	for i in range(len(images)):
+		# define subplot
+		pyplot.subplot(1, 3, 1 + i)
+		# turn off axis
+		pyplot.axis('off')
+		# plot raw pixel data
+		pyplot.imshow(images[i])
+		# show title
+		pyplot.title(titles[i])
+	pyplot.show()
+
+# load dataset
+[X1, X2] = load_real_samples('maps_256.npz')
+print('Loaded', X1.shape, X2.shape)
+# load model
+model = load_model('g_model.h5')
+# select random example
+ix = randint(0, len(X1), 1)
+print(ix)
+src_image, tar_image = X1[ix], X2[ix]
+# generate image from source
+gen_image = model.predict(src_image)
+# plot all three images
+plot_images(src_image, gen_image, tar_image)
+print(type(src_image), gen_image.shape, tar_image.shape)
+
+
+##########################################################
+
+import os
+from keras.preprocessing.image import img_to_array
+from keras.preprocessing.image import load_img
+from keras.models import load_model
+from matplotlib import pyplot as plt
+import numpy as np
+from numpy import vstack
+import time
+
+
+model = load_model('g_model.h5')
+
+##############################################################
+
+filename="./Capture1.PNG"
+size=(256,256)
+pixels = load_img(filename, target_size=size)
+
+# convert to numpy array
+pixels = img_to_array(pixels)
+# split into satellite and map
+sat_img = pixels[:, :256]
+sat_img = (sat_img - 127.5) / 127.5
+
+
+input_image=[]
+input_image.append(sat_img)
+input_image=np.array(input_image)
+
+t1=time.time()
+gen_image=model.predict(input_image)
+t2=time.time()
+
+###########################################################
+
+from matplotlib import pyplot
+def show_images(src_img, gen_img):
+	images = vstack((src_img, gen_img))
+	# scale from [-1,1] to [0,1]
+	images = (images + 1) / 2.0
+	titles = ['Source', 'Generated']
+	# plot images row by row
+	for i in range(len(images)):
+		# define subplot
+		pyplot.subplot(1, 2, 1 + i)
+		# turn off axis
+		pyplot.axis('off')
+		# plot raw pixel data
+		pyplot.imshow(images[i])
+		# show title
+		pyplot.title(titles[i])
+	pyplot.show()
+
+show_images(input_image,gen_image)

server/server.py

@@ -6,13 +6,20 @@
 import os
 import random
 import numpy as np
+import time
 
+#image_to_map
+from keras.preprocessing.image import img_to_array
+from keras.preprocessing.image import load_img
+from matplotlib import pyplot as plt
+from numpy import vstack
+
+image_to_map = load_model('models/image_to_map_g_model.h5')
+image_to_map._make_predict_function()
 
 global graph
 graph = tf.get_default_graph()
 
-image_to_map = load_model('models/image_to_map.h5')
-
 app = Flask(__name__)
 CORS(app)
 app.config['UPLOAD_FOLDER'] = 'static/uploads'
@@ -27,25 +34,24 @@ def predict(filename, process_type):
     if process_type == 'fogg_removal':
         pass
     if process_type == 'image_to_map':
-        # size=(256,256)
-        # sat_img = load_img(input_path, target_size=size)
-        # sat_img = img_to_array(sat_img)
-        # # split into satellite and map
-        # sat_img = (sat_img - 127.5) / 127.5
-
-        # input_image=[]
-        # input_image.append(sat_img)
-        # input_image=np.array(input_image)
-        # gen_image=image_to_map.predict(input_image)
-        # gen_image=(gen_image+1)/2.0
-        # save_img(output_path, gen_image)
-        pass
+        size=(256,256)
+        #image_to_map = load_model('models/image_to_map_g_model.h5')
+        sat_img = load_img(input_path, target_size=size)
+        sat_img = img_to_array(sat_img)
+        # split into satellite and map
+        sat_img = (sat_img - 127.5) / 127.5
+        input_image=[]
+        input_image.append(sat_img)
+        input_image=np.array(input_image)
+        print(input_image.shape)
+        gen_image=image_to_map.predict(input_image)
+        gen_image=(gen_image+1)/2.0
+        save_img(output_path, gen_image[0])
     if process_type == 'blur_to_hd':
         pass
     if process_type == 'face_aging':
         pass
 
-
 @app.route("/")
 def index():
     return "helllo"