basic iterations working, need to do duration mapping

main.py

@@ -7,12 +7,15 @@ import hashlib
 import random
 import multiprocessing
 import concurrent.futures
+import time
 
 import numpy as np
 
 from src.mediautils.audio import extract_audio_from_video
+from src.mediautils.video import render_moments
 from src.editors.amplitude.editor import AmplitudeEditor
 from src.editors.sentiment.editor import SentimentEditor
+from src.math.cost import quadratic_loss
 from src.math.distribution import create_distribution
 
 log = structlog.get_logger()
@@ -22,6 +25,10 @@ EDITORS = {
     'sentiment': SentimentEditor
 }
 
+ERROR_FUNCS = {
+    'quadratic': quadratic_loss
+}
+
 def main(args):
     # Check video existance
     input_file = args.file
@@ -56,6 +63,8 @@ def main(args):
     log.info("initializing editor", editor=args.editor)
     editor = EDITORS[args.editor](str(in_vid_path.resolve()), audio_path, vars(args))
     log.info("initialized editor", editor=args.editor)
+    costfunc = ERROR_FUNCS[args.cost]
+    desired = args.duration
 
     # Generate center of large window and small window size
     large_window_center = random.uniform(30, 50)
@@ -67,14 +76,27 @@ def main(args):
     # The decay rate, or how quickly our spread multiplier decreases as we approach the center of the gradient
     spread_decay = random.uniform(0.0001, 0.001)
 
-    log.info("creating distributions", large_start=large_window_center, small_start=small_window_center, spread=spread_multiplier, decay=spread_decay)
-    # Create distribution of large and small
     parallelism = args.parallelism
+
+    # The main loop of the program starts here
+    #   we first create distributions
+    #   use workers to simultanously create many possible edits
+    #   find the best edit of the lot -> this is determined by lowest "cost"
+    #   if the best fits within our desitred time range, output, otherwise
+    #       reset the distributions using the best as the new center, then repeat
+    # Create distribution of large and small
+
+    complete = False
+    iterations = 0
+    while not complete:
+        log.info("creating distributions", large_start=large_window_center, small_start=small_window_center, spread=spread_multiplier, decay=spread_decay)
         large_distribution = create_distribution(large_window_center, spread_multiplier, parallelism)
         np.random.shuffle(large_distribution)
         small_distribution = create_distribution(small_window_center, spread_multiplier, parallelism)
         np.random.shuffle(small_distribution)
 
+        # Fire off workers to generate edits
+        moment_results = []
         with concurrent.futures.ThreadPoolExecutor() as executor:
             futures = []
             pairs = list(zip(large_distribution, small_distribution))
@@ -88,11 +110,49 @@ def main(args):
                     )
                 )
             for future in concurrent.futures.as_completed(futures):
-            value = future.result()
-            log.info("got val", val=value)
+                try:
+                    moment_results.append(future.result())
+                except Exception:
+                    log.exception("error during editing")
+                    sys.exit(-2)
+        moment_results
+        costs = []
+        durations = []
+        for result in moment_results:
+            total_duration = 0
+            for moment in result[0]:
+               total_duration = total_duration + moment.get_duration()
+            costs.append(costfunc(desired, total_duration))
+            durations.append(total_duration)
+        index_min = min(range(len(costs)), key=costs.__getitem__)
+        large_window_center = moment_results[index_min][1]
+        small_window_center = moment_results[index_min][2]
+        log.info("batch complete", best_large=large_window_center, best_small=small_window_center, duration=durations[index_min])
+        if durations[index_min] > desired * 0.95 and desired * 1.05 > durations[index_min]:
+            log.info("found edit within target duration", target=desired, duration=durations[index_min])
+            out_path = Path(args.destination)
+            log.info("rendering...")
+            start = time.time()
+            render_moments(moment_results[index_min][0], str(in_vid_path.resolve()), str(out_path.resolve()))
+            log.info("render complete", duration=time.time() - start, output=str(out_path.resolve()))
+            sys.exit(0)
+        iterations = iterations + parallelism
+        if iterations > 50000:
+            log.error("could not find a viable edit in the target duration, try other params", target=desired)
+            sys.exit(-4)
+        spread_multiplier = spread_multiplier - spread_decay
+        if spread_multiplier < 0:
+            log.warn("spread reached 0, resetting")
+            large_window_center = random.uniform(30, 50)
+            small_window_center = random.uniform(5, 15)
+            spread_multiplier = random.uniform(0.15, 0.18)
+            spread_decay = random.uniform(0.0001, 0.001)
+            
+
+
+            
 
     
-    desired = args.duration
 
 
 if __name__ == "__main__":
@@ -115,13 +175,12 @@ if __name__ == "__main__":
         type=int,
     )
 
-    parser_audio_amp = subparsers.add_parser('sentiment', help='The sentiment editor transcribes the speech in a video and runs sentiment analysis on the resulting text. Using moving averages, large swings in sentiment can be correlated to controversial or exciting moments.')
+    parser_audio_amp = subparsers.add_parser('sentiment', help='The sentiment editor transcribes the speech in a video and runs sentiment analysis on the resulting text. Using moving averages, large swings in sentiment can be correlated to controversial or exciting moments. A GPU with CUDA is recommended for fast results.')
 
-    parser.add_argument("-d", "--dryrun", dest="drun", action="store_true")
     parser.add_argument("-p", "--parallelism", dest="parallelism", type=int, default=multiprocessing.cpu_count() - 2, help="The number of cores to use, defaults to N - 2 cores.")
+    parser.add_argument("--cost-function", dest="cost", choices=ERROR_FUNCS.keys(), default='quadratic')
 
     parser.add_argument(
-        "-i",
         "--minduration",
         default=8,
         help="Minimum clip duration",
@@ -129,7 +188,6 @@ if __name__ == "__main__":
         type=int,
     )
     parser.add_argument(
-        "-m",
         "--maxduration",
         default=15,
         help="Maximum clip duration",

src/editors/amplitude/editor.py

@@ -25,5 +25,5 @@ class AmplitudeEditor:
         long_ma = np_moving_average(self.squared_subsample, large_window * window_factor)
         short_ma = np_moving_average(self.squared_subsample, small_window * window_factor)
         highlights = find_moving_average_highlights(short_ma, long_ma, self.factor / self.bitrate)
-        return highlights
+        return highlights, large_window, small_window