Update transformations.

main.py

@@ -42,7 +42,9 @@ classes = ["person", "bicycle", "car", "motorbike", "aeroplane", "bus",
            "keyboard", "cell phone", "microwave", "oven", "toaster", "sink", "refrigerator",
            "book", "clock", "vase", "scissors", "teddy bear", "hair drier", "toothbrush"]
 
+PATH = "saved_patches/realcat.jpg"
 PATH = "saved_patches/fatcat.jpg"
+PATH = "saved_patches/smallcat.jpg"
 PATCH_SIZE = 300
 
 total_variation = TotalVariation()
@@ -194,7 +196,7 @@ if __name__ == "__main__":
     move = False
     rotate = False
     taper = False
-    resize = False
+    resize = True
     squeeze = False
     gauss = False
     obfuscate = False
@@ -256,6 +258,7 @@ if __name__ == "__main__":
                     pass
 
                 iou, pred = get_best_prediction(bounding_box, raw_results, 15)  # get cat
+                # iou, pred = get_best_prediction(bounding_box, raw_results, 0)  # get personal
                 # iou, pred = get_best_prediction(bounding_box, raw_results, 12)  # get parking meter
                 # iou, pred = get_best_prediction(bounding_box, raw_results, 11)  # get stop sign
                 # iou, pred = get_best_prediction(bounding_box, raw_results, 8)  # get boat
@@ -293,7 +296,7 @@ if __name__ == "__main__":
             # sgn_grads = torch.sign(optimizer.param_groups[0]['params'][0].grad)
             # optimizer.param_groups[0]['params'][0].grad = sgn_grads
             # optimizer.step()
-            patch.data -= torch.sign(gradient_sum) * 0.001
+            patch.data -= torch.sign(gradient_sum) * 0.001 # * 0 # TODO reactivate
             patch.data = patch.detach().clone().clamp(MIN_THRESHOLD, 0.99999).data
             gradient_sum = 0
 
@@ -333,12 +336,18 @@ if __name__ == "__main__":
                 stretch = not stretch
                 print(f"Obfuscate: {obfuscate}")
             if key == ord("+"):
-                transform_interval += 1
-                print("Transform Interval: {}".format(transform_interval))
+                # transform_interval += 1
+                patch_transformer.maxsize += 0.01
+                patch_transformer.minsize += 0.01
+                # print("Transform Interval: {}".format(transform_interval))
+                print(f"Size {patch_transformer.minsize}")
             if key == ord("-"):
-                transform_interval -= 1
-                transform_interval = max(transform_interval, 1)
-                print("Transform Interval: {}".format(transform_interval))
+                # transform_interval -= 1
+                patch_transformer.maxsize -= 0.01
+                patch_transformer.minsize -= 0.01
+                print(f"Size {patch_transformer.minsize}")
+                # transform_interval = max(transform_interval, 1)
+                # print("Transform Interval: {}".format(transform_interval))
             if key == ord("9"):
                 patch_transformer.maxangle = min(patch_transformer.maxangle + (math.pi * angle_step / 180), math.pi)
                 patch_transformer.minangle = max(patch_transformer.minangle - (math.pi * angle_step / 180), -math.pi)

patch_transformer.py

@@ -95,7 +95,7 @@ class PatchTransformer(nn.Module):
         self.minangle = -20 / 180 * math.pi
         self.maxangle = 20 / 180 * math.pi
         self.minsize = 0.5
-        self.maxsize = 1.5
+        self.maxsize = 0.51
         self.medianpooler = MedianPool2d(7, same=True)
         '''
         kernel = torch.cuda.FloatTensor([[0.003765, 0.015019, 0.023792, 0.015019, 0.003765],