Fmaps Loss Preprc

1508.06576/feature_maps.py

@@ -32,6 +32,22 @@ class FeatureMaps:
                 LOGGER.error("Could not fetch layer "+str(layer))
         return weights
 
+    def get_fmaps(self,img,layer=[0,5,10,19,28]):
+        '''
+        Function which will pass the image through the model and get the respective fmaps
+        @params
+        img: numpy image f64
+        layer: list
+        '''
+        fmaps = []
+        layer_num = 0
+        for layer_i in self.model.features:
+            img = layer_i(img)
+            if layer_num in layer:
+                fmaps.append(img)
+            layer_num+=1
+        return fmaps
+
 if __name__ == "__main__":
     fmap = FeatureMaps()
     model = fmap.get_model()

1508.06576/loss.py

@@ -10,11 +10,12 @@ class Loss:
         @params
         F: 2D numpy array
         P: 2D numpy array
+        Author: @meetdoshi
         '''
         l2_norm_sq = None
         try:
             diff = F-P
-            l2_norm_sq = np.sum(diff*diff)
+            l2_norm_sq = np.sum(diff**2)
         except Exception as e:
             LOGGER.error("Error computing loss",e)
         return l2_norm_sq/2.0

1508.06576/preprocess.py

 from distutils.log import Log
 from logger import Logger
+import numpy as np
 LOGGER = Logger().logger()
 
 class Preprocessor:
+    @staticmethod
+    def subtract_mean(img):
+        '''
+        Function to subtract mean values of RGB channels computed over whole ImageNet dataset
+        @params
+        img: 3d numpy array
+        '''
+        mean = np.reshape([103.939, 116.779, 123.68],(1,1,3))#b,g,r
+        return img-mean
+
+    @staticmethod
+    def reshape_img(img):
+        '''
+        Function to reshpae image in 224x224xnum_of_channels shape
+        @params
+        img: 3d numpy array
+        '''
+        
+
     @staticmethod
     def process(img):
         '''
         Function to preprocess the image
         @params
-        '''
\ No newline at end of file
+        img: 2d numpy a[103.939, 116.779, 123.68]rray
+        '''
+
+if __name__=="__main__":
+    prec = Preprocessor()
+    img = np.zeros(shape=(4,4,3))
+    print(img.shape)
+    for i in range(img.shape[2]):
+        print(img[:,:,i])
+    img = prec.subtract_mean(img)
+    for i in range(img.shape[2]):
+        print(img[:,:,i])