Commit @2ec958df0351f8ea302c1646c925bb0d5d733039

f617e0a

2ec958d

action.py

--- action.py

+++ action.py


             }, 200
 
 
-
-
 @Action.route('/image_anal')
 class fileUpload(Resource):
     @Action.doc(responses={200: 'Success'})

             crop_size = (512, 512)
             start_point = (750, 450)
             tf_toTensor = ToTensor()
-            clasifier = Classifier()
-            clasifier.load_state_dict(torch.load("weights/Classifier_512.pt"))
-            clasifier.to(device=device)
+            classifier = Classifier()
+            classifier.load_state_dict(torch.load("weights/Classifier_512.pt"))
+            classifier.to(device=device)
             dir = os.getcwd()
             lat = float(request.json['gps_x'])
             lon = float(request.json['gps_y'])

             if not image:
                 return {
                     'node': (lat, lon),
-                    'rain': 'rain',
+                    'rain': None,
                 }, 500
             image_tensor = tf_toTensor(image)
-            image_tensor.to(device)
-            image_arnn = AttentiveRNN(image_tensor)
-            result = Classifier(image_arnn)
+            image_tensor = image_tensor.unsqueeze(0)
+            image_tensor = image_tensor.to(device)
+            image_arnn = arnn(image_tensor)
+            result = classifier(image_arnn['x'])
             result = result.to("cpu")
-            if result == 0:
+            _, predicted = torch.max(result.data, 1)
+            if predicted == 0:
                 rain = False
-            else: # elif result == 1
+            else:  # elif result == 1
                 rain = True
             user_id = 'test'
             action_success = True

f617e0a

2ec958d

auth.py

--- auth.py

+++ auth.py


 import jwt
 
 
-
-
-
 users = {}
 
 Auth = Namespace(

     'password': fields.String(description='Password', required=True),'email': fields.String(description='email', required=True),'user_sex': fields.String(description='sex', required=True),'phone': fields.String(description='phone', required=True)
 
 })
-
 
 
 @Auth.route('/id')

f617e0a

2ec958d

model/Classifier.py

--- model/Classifier.py

+++ model/Classifier.py


         )
 
         self.global_pool = nn.AdaptiveAvgPool2d((1, 1))
-        self.fc = nn.Linear(256, classes)  # assuming 10 classes for the classification
+        self.fc = nn.Linear(256, classes)
 
     def forward(self, x):
         x = self.firstconv(x)

2ec958d

requirements.txt (added)

+++ requirements.txt

...	...	@@ -0,0 +1,11 @@
	1	+torch~=2.0.1+cu118
	2	+flask~=2.3.3
	3	+jwt~=1.3.1
	4	+werkzeug~=2.3.7
	5	+torchvision~=0.15.2+cu118
	6	+networkx~=3.0
	7	+geojson~=3.0.1
	8	+haversine~=2.8.0
	9	+opencv-python~=4.8.0.76
	10	+joblib~=1.3.2
	11	+pandas~=2.0.3(파일 끝에 줄바꿈 문자 없음)

f617e0a

2ec958d

subfuction/image_crop.py

--- subfuction/image_crop.py

+++ subfuction/image_crop.py


     # run the cropping function in parallel
     Parallel(n_jobs=-1)(delayed(crop_image)(image_path, output_directory, crop_size, start_point) for image_path in image_paths)
 
+if __name__ == "__main__":
+    output_directory = "/home/takensoft/Pictures/test512_512/rainy/"
 
-output_directory = "/home/takensoft/Pictures/test512_512/rainy/"
+    # get all image paths in the directory
+    # image_paths = glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/화창한날 프레임 추출/하드디스크 화창한날(17개)/**/*.png")
+    # image_paths += glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/화창한날 프레임 추출/7월19일 화창한날(8개)/**/*.png")
+    image_paths = glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/비오는날 프레임 추출/7월11일 폭우(3개)/**/*.png")
+    image_paths += glob.glob("/home/takensoft/Pictures/폭우 빗방울 (475개)/*.png")
 
-# get all image paths in the directory
-# image_paths = glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/화창한날 프레임 추출/하드디스크 화창한날(17개)/**/*.png")
-# image_paths += glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/화창한날 프레임 추출/7월19일 화창한날(8개)/**/*.png")
-image_paths = glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/비오는날 프레임 추출/7월11일 폭우(3개)/**/*.png")
-image_paths += glob.glob("/home/takensoft/Pictures/폭우 빗방울 (475개)/*.png")
+    crop_size = (512, 512) # width and height you want for your cropped images
+    start_point = (750, 450) # upper left point where the crop should start
 
-crop_size = (512, 512) # width and height you want for your cropped images
-start_point = (750, 450) # upper left point where the crop should start
-
-crop_images_parallel(image_paths, output_directory, crop_size, start_point)
+    crop_images_parallel(image_paths, output_directory, crop_size, start_point)

...	...	@@ -68,7 +68,7 @@
68	68	)
69	69
70	70	self.global_pool = nn.AdaptiveAvgPool2d((1, 1))
71		- self.fc = nn.Linear(256, classes) # assuming 10 classes for the classification
	71	+ self.fc = nn.Linear(256, classes)
72	72
73	73	def forward(self, x):
74	74	x = self.firstconv(x)

...	...	@@ -33,8 +33,6 @@
33	33	}, 200
34	34
35	35
36		-
37		-
38	36	@Action.route('/image_anal')
39	37	class fileUpload(Resource):
40	38	@Action.doc(responses={200: 'Success'})
...	...	@@ -48,9 +46,9 @@
48	46	crop_size = (512, 512)
49	47	start_point = (750, 450)
50	48	tf_toTensor = ToTensor()
51		- clasifier = Classifier()
52		- clasifier.load_state_dict(torch.load("weights/Classifier_512.pt"))
53		- clasifier.to(device=device)
	49	+ classifier = Classifier()
	50	+ classifier.load_state_dict(torch.load("weights/Classifier_512.pt"))
	51	+ classifier.to(device=device)
54	52	dir = os.getcwd()
55	53	lat = float(request.json['gps_x'])
56	54	lon = float(request.json['gps_y'])
...	...	@@ -61,16 +59,18 @@
61	59	if not image:
62	60	return {
63	61	'node': (lat, lon),
64		- 'rain': 'rain',
	62	+ 'rain': None,
65	63	}, 500
66	64	image_tensor = tf_toTensor(image)
67		- image_tensor.to(device)
68		- image_arnn = AttentiveRNN(image_tensor)
69		- result = Classifier(image_arnn)
	65	+ image_tensor = image_tensor.unsqueeze(0)
	66	+ image_tensor = image_tensor.to(device)
	67	+ image_arnn = arnn(image_tensor)
	68	+ result = classifier(image_arnn['x'])
70	69	result = result.to("cpu")
71		- if result == 0:
	70	+ _, predicted = torch.max(result.data, 1)
	71	+ if predicted == 0:
72	72	rain = False
73		- else: # elif result == 1
	73	+ else: # elif result == 1
74	74	rain = True
75	75	user_id = 'test'
76	76	action_success = True

...	...	@@ -6,9 +6,6 @@
6	6	import jwt
7	7
8	8
9		-
10		-
11		-
12	9	users = {}
13	10
14	11	Auth = Namespace(
...	...	@@ -31,7 +28,6 @@
31	28	'password': fields.String(description='Password', required=True),'email': fields.String(description='email', required=True),'user_sex': fields.String(description='sex', required=True),'phone': fields.String(description='phone', required=True)
32	29
33	30	})
34		-
35	31
36	32
37	33	@Auth.route('/id')

...	...	@@ -22,16 +22,16 @@
22	22	# run the cropping function in parallel
23	23	Parallel(n_jobs=-1)(delayed(crop_image)(image_path, output_directory, crop_size, start_point) for image_path in image_paths)
24	24
	25	+if __name__ == "__main__":
	26	+ output_directory = "/home/takensoft/Pictures/test512_512/rainy/"
25	27
26		-output_directory = "/home/takensoft/Pictures/test512_512/rainy/"
	28	+ # get all image paths in the directory
	29	+ # image_paths = glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/화창한날 프레임 추출/하드디스크 화창한날(17개)/*/.png")
	30	+ # image_paths += glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/화창한날 프레임 추출/7월19일 화창한날(8개)/*/.png")
	31	+ image_paths = glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/비오는날 프레임 추출/7월11일 폭우(3개)/*/.png")
	32	+ image_paths += glob.glob("/home/takensoft/Pictures/폭우 빗방울 (475개)/*.png")
27	33
28		-# get all image paths in the directory
29		-# image_paths = glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/화창한날 프레임 추출/하드디스크 화창한날(17개)/*/.png")
30		-# image_paths += glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/화창한날 프레임 추출/7월19일 화창한날(8개)/*/.png")
31		-image_paths = glob.glob("/home/takensoft/Pictures/화창한날, 비오는날 프레임2000장/비오는날 프레임 추출/7월11일 폭우(3개)/*/.png")
32		-image_paths += glob.glob("/home/takensoft/Pictures/폭우 빗방울 (475개)/*.png")
	34	+ crop_size = (512, 512) # width and height you want for your cropped images
	35	+ start_point = (750, 450) # upper left point where the crop should start
33	36
34		-crop_size = (512, 512) # width and height you want for your cropped images
35		-start_point = (750, 450) # upper left point where the crop should start
36		-
37		-crop_images_parallel(image_paths, output_directory, crop_size, start_point)
	37	+ crop_images_parallel(image_paths, output_directory, crop_size, start_point)

Delete comment