Create paths in an OS-agnostic way.

Fixes #37 (closed) and fixes #35 (closed).

data/1_move_files.py

@@ -13,8 +13,8 @@ def get_train_test_lists(version='01'):
     breakdowns we'll later use to move everything.
     """
     # Get our files based on version.
-    test_file = './ucfTrainTestlist/testlist' + version + '.txt'
-    train_file = './ucfTrainTestlist/trainlist' + version + '.txt'
+    test_file = os.path.join('ucfTrainTestlist', 'testlist' + version + '.txt')
+    train_file = os.path.join('ucfTrainTestlist', 'trainlist' + version + '.txt')
 
     # Build the test list.
     with open(test_file) as fin:
@@ -44,14 +44,14 @@ def move_files(file_groups):
         for video in videos:
 
             # Get the parts.
-            parts = video.split('/')
+            parts = video.split(os.path.sep)
             classname = parts[0]
             filename = parts[1]
 
             # Check if this class exists.
-            if not os.path.exists(group + '/' + classname):
+            if not os.path.exists(os.path.join(group, classname)):
                 print("Creating folder for %s/%s" % (group, classname))
-                os.makedirs(group + '/' + classname)
+                os.makedirs(os.path.join(group, classname))
 
             # Check if we have already moved this file, or at least that it
             # exists to move.
@@ -60,7 +60,7 @@ def move_files(file_groups):
                 continue
 
             # Move it.
-            dest = group + '/' + classname + '/' + filename
+            dest = os.path.join(group, classname, filename)
             print("Moving %s to %s" % (filename, dest))
             os.rename(filename, dest)
 

data/2_extract_files.py

@@ -25,13 +25,13 @@ def extract_files():
     `ffmpeg -i video.mpg image-%04d.jpg`
     """
     data_file = []
-    folders = ['./train/', './test/']
+    folders = ['train', 'test']
 
     for folder in folders:
-        class_folders = glob.glob(folder + '*')
+        class_folders = glob.glob(os.path.join(folder, '*'))
 
         for vid_class in class_folders:
-            class_files = glob.glob(vid_class + '/*.avi')
+            class_files = glob.glob(os.path.join(vid_class, '*.avi'))
 
             for video_path in class_files:
                 # Get the parts of the file.
@@ -43,10 +43,9 @@ def extract_files():
                 # the info.
                 if not check_already_extracted(video_parts):
                     # Now extract it.
-                    src = train_or_test + '/' + classname + '/' + \
-                        filename
-                    dest = train_or_test + '/' + classname + '/' + \
-                        filename_no_ext + '-%04d.jpg'
+                    src = os.path.join(train_or_test, classname, filename)
+                    dest = os.path.join(train_or_test, classname,
+                        filename_no_ext + '-%04d.jpg')
                     call(["ffmpeg", "-i", src, dest])
 
                 # Now get how many frames it is.
@@ -66,25 +65,25 @@ def get_nb_frames_for_video(video_parts):
     """Given video parts of an (assumed) already extracted video, return
     the number of frames that were extracted."""
     train_or_test, classname, filename_no_ext, _ = video_parts
-    generated_files = glob.glob(train_or_test + '/' + classname + '/' +
-                                filename_no_ext + '*.jpg')
+    generated_files = glob.glob(os.path.join(train_or_test, classname,
+                                filename_no_ext + '*.jpg'))
     return len(generated_files)
 
 def get_video_parts(video_path):
     """Given a full path to a video, return its parts."""
-    parts = video_path.split('/')
-    filename = parts[3]
+    parts = video_path.split(os.path.sep)
+    filename = parts[2]
     filename_no_ext = filename.split('.')[0]
-    classname = parts[2]
-    train_or_test = parts[1]
+    classname = parts[1]
+    train_or_test = parts[0]
 
     return train_or_test, classname, filename_no_ext, filename
 
 def check_already_extracted(video_parts):
     """Check to see if we created the -0001 frame of this file."""
     train_or_test, classname, filename_no_ext, _ = video_parts
-    return bool(os.path.exists(train_or_test + '/' + classname +
-                               '/' + filename_no_ext + '-0001.jpg'))
+    return bool(os.path.exists(os.path.join(train_or_test, classname,
+                               filename_no_ext + '-0001.jpg')))
 
 def main():
     """

data.py

@@ -22,7 +22,7 @@ class DataSet():
         """
         self.seq_length = seq_length
         self.class_limit = class_limit
-        self.sequence_path = './data/sequences/'
+        self.sequence_path = os.path.join('data', 'sequences')
         self.max_frames = 300  # max number of frames a video can have for us to use it
 
         # Get the data.
@@ -39,7 +39,7 @@ class DataSet():
     @staticmethod
     def get_data():
         """Load our data from file."""
-        with open('./data/data_file.csv', 'r') as fin:
+        with open(os.path.join('data', 'data_file.csv'), 'r') as fin:
             reader = csv.reader(fin)
             data = list(reader)
 
@@ -203,14 +203,14 @@ class DataSet():
     def get_frames_for_sample(sample):
         """Given a sample row from the data file, get all the corresponding frame
         filenames."""
-        path = './data/' + sample[0] + '/' + sample[1] + '/'
+        path = os.path.join('data', sample[0], sample[1])
         filename = sample[2]
-        images = sorted(glob.glob(path + filename + '*jpg'))
+        images = sorted(glob.glob(os.path.join(path, filename + '*jpg')))
         return images
 
     @staticmethod
     def get_filename_from_image(filename):
-        parts = filename.split('/')
+        parts = filename.split(os.path.sep)
         return parts[-1].replace('.jpg', '')
 
     @staticmethod

extract_features.py

@@ -32,8 +32,8 @@ pbar = tqdm(total=len(data.data))
 for video in data.data:
 
     # Get the path to the sequence for this video.
-    path = './data/sequences/' + video[2] + '-' + str(seq_length) + \
-        '-features.txt'
+    path = os.path.join('data', 'sequences', video[2] + '-' + str(seq_length) + \
+        '-features.txt')
 
     # Check if we already have it.
     if os.path.isfile(path):

models.py

@@ -47,7 +47,7 @@ class ResearchModels():
             self.model = self.lstm()
         elif model == 'lrcn':
             print("Loading CNN-LSTM model.")
-            self.input_shape = (seq_length, 150, 150, 3)
+            self.input_shape = (seq_length, 80, 80, 3)
             self.model = self.lrcn()
         elif model == 'mlp':
             print("Loading simple MLP.")
@@ -66,7 +66,7 @@ class ResearchModels():
             sys.exit()
 
         # Now compile the network.
-        optimizer = Adam(lr=1e-4, decay=1e-6)
+        optimizer = Adam(lr=1e-5, decay=1e-6)
         self.model.compile(loss='categorical_crossentropy', optimizer=optimizer,
                            metrics=metrics)