Myosotis-Researches 0.1.33__tar.gz → 0.1.35__tar.gz

{myosotis_researches-0.1.33 → myosotis_researches-0.1.35/Myosotis_Researches.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: Myosotis-Researches
-Version: 0.1.33
+Version: 0.1.35
 Summary: A repository for storing my progress of researches.
 Home-page: https://github.com/Zeyu-Xie/Myosotis-Researches
 Author: Zeyu Xie

{myosotis_researches-0.1.33/Myosotis_Researches.egg-info → myosotis_researches-0.1.35}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: Myosotis-Researches
-Version: 0.1.33
+Version: 0.1.35
 Summary: A repository for storing my progress of researches.
 Home-page: https://github.com/Zeyu-Xie/Myosotis-Researches
 Author: Zeyu Xie

myosotis_researches-0.1.35/myosotis_researches/CcGAN/utils/similarity.py

@@ -0,0 +1,92 @@
+import cv2
+import math
+import numpy as np
+from PIL import Image
+from skimage.metrics import structural_similarity as ssim
+
+
+# MSE
+def _MSE(image_1, image_2):
+    array_1 = np.array(image_1) / 255
+    array_2 = np.array(image_2) / 255
+    n, m, _ = array_1.shape
+    return np.sum((array_1 - array_2) ** 2) / (n * m * 3)
+
+
+def MSE(images):
+    MSE_sum = 0
+    n = len(images)
+    for i in range(n):
+        for j in range(i + 1, n):
+            MSE_sum += _MSE(images[i], images[j])
+    return MSE_sum / (n * (n - 1) / 2)
+
+
+# SSIM
+
+
+def _SSIM(image_1, image_2):
+
+    array_1 = np.array(image_1)
+    array_2 = np.array(image_2)
+    score, _ = ssim(array_1, array_2, channel_axis=-1, full=True)
+    return score
+
+
+def SSIM(images):
+    SSIM_sum = 0
+    n = len(images)
+    for i in range(n):
+        for j in range(i + 1, n):
+            SSIM_sum += _SSIM(images[i], images[j])
+    return SSIM_sum / (n * (n - 1) / 2)
+
+
+# PSNR
+def _PSNR(image_1, image_2):
+    mse = _MSE(image_1, image_2)
+    if mse == 0:
+        return float("inf")
+    else:
+        return 20 * math.log10(1.0 / math.sqrt(mse))
+
+
+def PSNR(images):
+    PSNR_sum = 0
+    n = len(images)
+    for i in range(n):
+        for j in range(i + 1, n):
+            PSNR_sum += _PSNR(images[i], images[j])
+    return PSNR_sum / (n * (n - 1) / 2)
+
+# Cross-correlation
+
+def _cross_correlation(image_1, image_2):
+    array_1 = np.array(image_1)
+    array_2 = np.array(image_2)
+    channels_1 = cv2.split(array_1)
+    channels_2 = cv2.split(array_2)
+    scores = []
+    for c1, c2 in zip(channels_1, channels_2):
+        result = cv2.matchTemplate(c1, c2, method=cv2.TM_CCOEFF_NORMED)
+        _, max_val, _, _ = cv2.minMaxLoc(result)
+        scores.append(max_val)
+    return sum(scores) / len(scores)
+
+def cross_correlation(images):
+    cross_correlation_sum = 0
+    n = len(images)
+    for i in range(n):
+        for j in range(i + 1, n):
+            cross_correlation_sum += _cross_correlation(images[i], images[j])
+    return cross_correlation_sum / (n * (n - 1) / 2)
+
+# Similarity
+_method_dict = {"MSE": MSE, "SSIM": SSIM, "PSNR": PSNR, "cross-correlation": cross_correlation}
+
+
+def similarity(images, method):
+    return _method_dict[method](images)
+
+
+__all__ = ["similarity"]

{myosotis_researches-0.1.33 → myosotis_researches-0.1.35}/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup, find_packages
 
 setup(
     name="Myosotis-Researches",
-    version="0.1.33",
+    version="0.1.35",
     description="A repository for storing my progress of researches.",
     long_description=open("README.md").read(),
     long_description_content_type="text/markdown",

myosotis_researches-0.1.33/myosotis_researches/CcGAN/utils/similarity.py

@@ -1,52 +0,0 @@
-import cv2
-import numpy as np
-from PIL import Image
-from skimage.metrics import structural_similarity as ssim
-
-
-# MSE
-def _MSE(image_1, image_2):
-    array_1 = np.array(image_1) / 255
-    array_2 = np.array(image_2) / 255
-    n, m, _ = array_1.shape
-    return np.sum((array_1 - array_2) ** 2) / (n * m * 3)
-
-
-def MSE(images):
-    MSE_sum = 0
-    n = len(images)
-    for i in range(n):
-        for j in range(i + 1, n):
-            MSE_sum += _MSE(images[i], images[j])
-    return MSE_sum / (n * (n - 1) / 2)
-
-
-# SSIM
-
-
-def _SSIM(image_1, image_2):
-
-    array_1 = np.array(image_1)
-    array_2 = np.array(image_2)
-    score, _ = ssim(array_1, array_2, channel_axis=-1, full=True)
-    return score
-
-
-def SSIM(images):
-    SSIM_sum = 0
-    n = len(images)
-    for i in range(n):
-        for j in range(i + 1, n):
-            SSIM_sum += _SSIM(images[i], images[j])
-    return SSIM_sum / (n * (n - 1) / 2)
-
-
-# Similarity
-_method_dict = {"MSE": MSE, "SSIM": SSIM}
-
-
-def similarity(images, method):
-    return _method_dict[method](images)
-
-
-__all__ = ["similarity"]