edumapri
diff --git a/‎computer_vision/haralick_descriptors.py‎
Lines changed: 1 addition & 1 deletion b/‎computer_vision/haralick_descriptors.py‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎graphs/strongly_connected_components.py‎
Lines changed: 1 addition & 1 deletion b/‎graphs/strongly_connected_components.py‎
Lines changed: 1 addition & 1 deletion
diff --git a/‎maths/points_are_collinear_3d.py‎
Lines changed: 5 additions & 5 deletions b/‎maths/points_are_collinear_3d.py‎
Lines changed: 5 additions & 5 deletions
diff --git a/‎neural_network/convolution_neural_network.py‎
Lines changed: 4 additions & 4 deletions b/‎neural_network/convolution_neural_network.py‎
Lines changed: 4 additions & 4 deletions
@@ -141,7 +141,7 @@ def transform(
 
     center_x, center_y = (x // 2 for x in kernel.shape)
 
-    # Use padded image when applying convolotion
+    # Use padded image when applying convolution
     # to not go out of bounds of the original the image
     transformed = np.zeros(image.shape, dtype=np.uint8)
     padded = np.pad(image, 1, "constant", constant_values=constant)
 
@@ -38,7 +38,7 @@ def find_components(
     reversed_graph: dict[int, list[int]], vert: int, visited: list[bool]
 ) -> list[int]:
     """
-    Use depth first search to find strongliy connected
+    Use depth first search to find strongly connected
     vertices. Now graph is reversed
     >>> find_components({0: [1], 1: [2], 2: [0]}, 0, 5 * [False])
     [0, 1, 2]
 
@@ -76,9 +76,9 @@ def get_3d_vectors_cross(ab: Vector3d, ac: Vector3d) -> Vector3d:
 
 def is_zero_vector(vector: Vector3d, accuracy: int) -> bool:
     """
-    Check if vector is equal to (0, 0, 0) of not.
+    Check if vector is equal to (0, 0, 0) or not.
 
-    Sine the algorithm is very accurate, we will never get a zero vector,
+    Since the algorithm is very accurate, we will never get a zero vector,
     so we need to round the vector axis,
     because we want a result that is either True or False.
     In other applications, we can return a float that represents the collinearity ratio.
@@ -97,9 +97,9 @@ def are_collinear(a: Point3d, b: Point3d, c: Point3d, accuracy: int = 10) -> boo
     """
     Check if three points are collinear or not.
 
-    1- Create tow vectors AB and AC.
-    2- Get the cross vector of the tow vectors.
-    3- Calcolate the length of the cross vector.
+    1- Create two vectors AB and AC.
+    2- Get the cross vector of the two vectors.
+    3- Calculate the length of the cross vector.
     4- If the length is zero then the points are collinear, else they are not.
 
     The use of the accuracy parameter is explained in is_zero_vector docstring.
 
@@ -1,7 +1,7 @@
 """
  - - - - - -- - - - - - - - - - - - - - - - - - - - - - -
 Name - - CNN - Convolution Neural Network For Photo Recognizing
-Goal - - Recognize Handing Writing Word Photo
+Goal - - Recognize Handwriting Word Photo
 Detail: Total 5 layers neural network
         * Convolution layer
         * Pooling layer
@@ -135,7 +135,7 @@ def convolute(self, data, convs, w_convs, thre_convs, conv_step):
             )
             data_featuremap.append(featuremap)
 
-        # expanding the data slice to One dimenssion
+        # expanding the data slice to one dimension
         focus1_list = []
         for each_focus in data_focus:
             focus1_list.extend(self.Expand_Mat(each_focus))
@@ -304,7 +304,7 @@ def draw_error():
             plt.grid(True, alpha=0.5)
             plt.show()
 
-        print("------------------Training Complished---------------------")
+        print("------------------Training Complete---------------------")
         print((" - - Training epoch: ", rp, f"     - - Mse: {mse:.6f}"))
         if draw_e:
             draw_error()
@@ -353,5 +353,5 @@ def convolution(self, data):
 
 if __name__ == "__main__":
     """
-    I will put the example on other file
+    I will put the example in another file
     """