Restructured project as a package

src/autophotographer/autophotographer_main.py

@@ -1,24 +1,16 @@
-# IMPORTS
+import math
-# import from
-from tqdm import tqdm 
-from skimage.exposure import is_low_contrast
-from os.path import abspath
-
-# import as
-import pandas as pd
-import matplotlib.pyplot as plt
-import numpy as np
-
-# imports
-import cv2
 import argparse
 import os
+from os.path import abspath
+import cv2
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
 import yaml
-import math
+from skimage.exposure import is_low_contrast
-
+from tqdm import tqdm
-# local imports for filters
+import autophotographer.filters.brightness.brightness as brightness
-import filters.focusdetection.focusdetection as focusdetection
+import autophotographer.filters.focusdetection.focusdetection as focusdetection
-import filters.brightness.brightness as brightness
 
 # GLOBAL VARIABLES
 # accepted image formats
@@ -37,6 +29,13 @@ ignore_video = False
 # FUNCTIONS
 # load config file
 def load_config(path=os.path.join(os.path.dirname(__file__), "./config.yml")):
+    """
+    The load_config function loads a YAML configuration file from the specified path.
+    
+    :param path=os.path.join(os.path.dirname(__file__): Used to Specify the path of the config.
+    :param "./config.yml"): Used to Specify the path to the config file.
+    :return: A dictionary of the config file.
+    """
     abs_path = os.path.abspath(path)
 
     # check if file exists
@@ -50,11 +49,28 @@ def load_config(path=os.path.join(os.path.dirname(__file__), "./config.yml")):
             print("[ERRO] Please specify a file with extension '.yml' or '.yaml'.")
             quit()
     else:
-        print("[ERRO] Path does not exist")
+        raise FileNotFoundError("[ERRO] Path does not exist")
-        quit()
 
 # load the correct filter function from filter name
 def filter_to_function(imagefilter: str, paths: list) -> list:
+    """
+    The filter_to_function function filters a list of image paths based on the filter type.
+    
+    Args:
+        imagefilter (str): The type of filter to apply. Can be "brightness", "contrast", or "focus". 
+    
+        paths (list): A list of filepaths to images that will be filtered.
+    
+        brightness_thresh (int, optional): The threshold for filtering out images with low brightness levels. Defaults to 100 if not specified by user in config file or command line arguments.
+    
+        contrast_thresh (float, optional): The threshold for filtering out images with low contrast levels. Defaults to 1 if not specified by user in config file or command line arguments..
+    
+        focus_thresh (float, optional): The threshold for filtering out blurry images based on the variance in blurriness across all pixels within an image's bounding box as determined using OpenCV's Laplacian method and Gaussian Blur method respectively . Defaults to 0 if not specified by user in config file or command line arguments..
+    
+    :param imagefilter:str: Used to Determine which filter to apply.
+    :param paths:list: Used to Store the paths of all images that have been filtered.
+    :return: The filtered list of paths.
+    """
     if imageFilter == "brightness":
         paths = filter_brightness(paths, brightness_thresh)
         print("[INFO] Filtering based on brightness...")
@@ -291,56 +307,57 @@ def display_images(paths, location):
     plt.savefig(location) 
 
 # parse command line arguments
-parser = argparse.ArgumentParser()
+if __name__ == "__main__":
-parser.add_argument("-i", "--input", type=os.path.abspath, required=True, nargs="+",
+    parser = argparse.ArgumentParser()
-	help="path to video or image folder")
+    parser.add_argument("-i", "--input", type=os.path.abspath, required=True, nargs="+",
-parser.add_argument("-c", "--config", type=os.path.abspath, help="path to config file")
+    	help="path to video or image folder")
-args = vars(parser.parse_args())
+    parser.add_argument("-c", "--config", type=os.path.abspath, help="path to config file")
+    args = vars(parser.parse_args())
 
-# load in config file
+    # load in config file
-if args["config"] is not None:
+    if args["config"] is not None:
-    autophotoConf = load_config(args["config"])
+        autophotoConf = load_config(args["config"])
-else:
+    else:
-    autophotoConf = load_config()
+        autophotoConf = load_config()
 
-# Load values for options
+    # Load values for options
-if autophotoConf["brightness_options"]["threshold"] is not None:
+    if autophotoConf["brightness_options"]["threshold"] is not None:
-   brightness_thresh = autophotoConf["brightness_options"]["threshold"]
+       brightness_thresh = autophotoConf["brightness_options"]["threshold"]
-if autophotoConf["focus_options"]["threshold"] is not None:
+    if autophotoConf["focus_options"]["threshold"] is not None:
-   focus_thresh = autophotoConf["focus_options"]["threshold"]
+       focus_thresh = autophotoConf["focus_options"]["threshold"]
-if autophotoConf["contrast_options"]["threshold"] is not None:
+    if autophotoConf["contrast_options"]["threshold"] is not None:
-   contrast_thresh = autophotoConf["contrast_options"]["threshold"]
+       contrast_thresh = autophotoConf["contrast_options"]["threshold"]
-if autophotoConf["filesize_options"]["threshold"] is not None:
+    if autophotoConf["filesize_options"]["threshold"] is not None:
-   filesize_thresh = autophotoConf["filesize_options"]["threshold"]
+       filesize_thresh = autophotoConf["filesize_options"]["threshold"]
-if autophotoConf["ignore_video"] is not None:
+    if autophotoConf["ignore_video"] is not None:
-   ignore_video = autophotoConf["ignore_video"]
+       ignore_video = autophotoConf["ignore_video"]
 
-paths = filter_paths(args["input"])
+    paths = filter_paths(args["input"])
-print("[INFO] Loaded {} objects.".format(len(paths)))
+    print("[INFO] Loaded {} objects.".format(len(paths)))
-prior_paths = []
+    prior_paths = []
-path_diff = []
+    path_diff = []
 
-# Order and selection of operations from config file
+    # Order and selection of operations from config file
-if autophotoConf["filters"] is not None:
+    if autophotoConf["filters"] is not None:
 
-    # iterate over all chosen filters
+        # iterate over all chosen filters
-    for imageFilter in autophotoConf["filters"]:
+        for imageFilter in autophotoConf["filters"]:
-        prior_paths = paths
+            prior_paths = paths
-        
-        # run given filter
-        paths = filter_to_function(imageFilter, paths)
 
-        path_diff = list(set(paths) - set(prior_paths)) + list(set(prior_paths) - set(paths))
+            # run given filter
-        diff = len(prior_paths) - len(paths)
+            paths = filter_to_function(imageFilter, paths)
-        # filename = "/src/fig" + "-" + str(imageFilter) + ".png"
-        # display_images(path_diff, filename)
 
-        # calculate set difference after filtering
+            path_diff = list(set(paths) - set(prior_paths)) + list(set(prior_paths) - set(paths))
-        if diff == 0:
+            diff = len(prior_paths) - len(paths)
-            print("[INFO] No images were filtered.")
+            # filename = "/src/fig" + "-" + str(imageFilter) + ".png"
-        else:
+            # display_images(path_diff, filename)
-            print("[INFO] Filtered {}/{} images via {} filtering.".format(
-                len(paths), len(prior_paths), imageFilter))
 
-if autophotoConf["CNNrank"]:
+            # calculate set difference after filtering
-    print("[INFO] Running CNN ranking...")
+            if diff == 0:
+                print("[INFO] No images were filtered.")
+            else:
+                print("[INFO] Filtered {}/{} images via {} filtering.".format(
+                    len(paths), len(prior_paths), imageFilter))
+
+    if autophotoConf["CNNrank"]:
+        print("[INFO] Running CNN ranking...")

src/autophotographer/cnn/autophotographer.py

@@ -1,8 +1,10 @@
-import cv2
-import sys
 import argparse
 import os
 import pathlib
+import sys
+
+import cv2
+
 
 # Process arguments
 def parse_arguments(argv=None):

src/autophotographer/cnn/config.py

@@ -1,6 +1,7 @@
-import torch
 import os
 
+import torch
+
 # https://pytorch.org/hub/pytorch_vision_resnet/
 MEAN = [0.485, 0.456, 0.406]
 STD = [0.229, 0.224, 0.225]

src/autophotographer/cnn/dataset.py

@@ -1,20 +1,23 @@
-import pandas as pd
+import os
-import matplotlib.pyplot as plt 
-import matplotlib.image as mpimg
 import random
 import time
-from sklearn.preprocessing import MinMaxScaler
-import numpy as np
-from sklearn.model_selection import train_test_split
-import cv2
-from pathlib import Path
-from . import config
-from torchvision import transforms
-import torch
-from torch.utils.data import DataLoader
-import os
 from os.path import abspath
+from pathlib import Path
+
+import cv2
+import matplotlib.image as mpimg
+import matplotlib.pyplot as plt
+import numpy as np
+import pandas as pd
+import torch
 from PIL import Image, ImageFile
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import MinMaxScaler
+from torch.utils.data import DataLoader
+from torchvision import transforms
+
+from . import config
+
 ImageFile.LOAD_TRUNCATED_IMAGES = True
 
 datasetDir = "/datasets/"

src/autophotographer/cnn/export/.gitignore

@@ -0,0 +1,2 @@
+tensorArray.pt
+testTensorArrayFile.pt

src/autophotographer/cnn/model.py

@@ -1,18 +1,17 @@
-import torch
-import torch.nn as nn
-import torch.optim as optim
-from torchvision.models import resnet50
-from torchvision import transforms
-from torch.utils.data import DataLoader
-
-from tqdm import tqdm
-import time
 import os
+import time
 from os.path import abspath
-import matplotlib.pyplot as plt
 
 import config
 import dataset
+import matplotlib.pyplot as plt
+import torch
+import torch.nn as nn
+import torch.optim as optim
+from torch.utils.data import DataLoader
+from torchvision import transforms
+from torchvision.models import resnet50
+from tqdm import tqdm
 
 # projectRoot = "/src/"
 script_directory = os.path.dirname(__file__)

src/autophotographer/filters/brightness/brightness.py

@@ -0,0 +1,20 @@
+import cv2
+import numpy as np
+
+
+def get_luminance_value(image):
+    """
+    The get_luminance_value function takes an image as input and returns the luminance value of that image.
+    The function first resizes the image to a width of 20 pixels, then converts it to LAB color space, 
+    and finally normalizes the L channel by dividing it by its maximum value. The function returns this normalized 
+    L channel.
+    
+    :param image: Used to Get the image that is being processed.
+    :return: The value of the luminance channel.
+    """
+    width = 20
+    height = int(image.shape[0] * (width / image.shape[0]))
+    image = cv2.resize(image, (width, height))
+    L, A, B = cv2.split(cv2.cvtColor(image, cv2.COLOR_BGR2LAB))
+    L = L/np.max(L)
+    return np.mean(L)

src/autophotographer/filters/focusdetection/focusdetection.py

@@ -1,10 +1,11 @@
 import argparse
 import os
 from os.path import abspath
+
 import cv2
-import pandas
-import numpy
 import matplotlib.pyplot as plt
+import numpy
+import pandas
 
 #parser = argparse.ArgumentParser()
 #parser.add_argument('images', type=os.path.abspath, metavar='image-location', nargs='+',
@@ -44,6 +45,4 @@ def laplacian_variance_method():
 
     mean_lap_var = df["Laplacian Variance"].mean()
     df_not_blurred = df[df['Laplacian Variance']>mean_lap_var]
-    df_blurred = df[df['Laplacian Variance']<=mean_lap_var]
+    df_blurred = df[df['Laplacian Variance']<=mean_lap_var]
-
-#def fast_fourier_transform_method():

src/autophotographer/predict.py

@@ -1,14 +1,14 @@
 import argparse
-import os
-from os.path import abspath
-from cnn import config
-from cnn import dataset
-from torchvision import transforms
-import matplotlib.pyplot as plt
-from torch import nn
-import torch
-import argparse
 import datetime
+import os
+from os.path import abspath
+
+import matplotlib.pyplot as plt
+import torch
+from torch import nn
+from torchvision import transforms
+
+from cnn import config, dataset
 
 # set project root for fetching files using relative file paths
 script_directory = os.path.dirname(__file__)

src/filters/brightness/brightness.py

@@ -1,10 +0,0 @@
-import numpy as np
-import cv2
-
-def get_luminance_value(image):
-    width = 20
-    height = int(image.shape[0] * (width / image.shape[0]))
-    image = cv2.resize(image, (width, height))
-    L, A, B = cv2.split(cv2.cvtColor(image, cv2.COLOR_BGR2LAB))
-    L = L/np.max(L)
-    return np.mean(L)