Refactor and add benchmarks

Author: scotts

benchmarks/decoders/benchmark_decoders.py

@@ -14,10 +14,11 @@
     plot_data,
     run_benchmarks,
     TorchAudioDecoder,
-    TorchcodecCompiled,
-    TorchCodecNonCompiledBatch,
-    TorchcodecNonCompiledWithOptions,
-    TVNewAPIDecoderWithBackend,
+    TorchCodecCoreCompiled,
+    TorchCodecCoreBatch,
+    TorchCodecCore,
+    TorchCodecPublic,
+    TorchVision,
 )
 
 
@@ -70,7 +71,7 @@ def main() -> None:
             "For torchcodec, you can specify options with tcoptions:<plus-separated-options>. "
         ),
         type=str,
-        default="decord,tcoptions:,torchvision,torchaudio,torchcodec_compiled,tcoptions:num_threads=1",
+        default="decord,tcoptions:,torchvision,torchaudio,torchcodec_compiled,torchcodec_public,tcoptions:num_threads=1,tcbatchoptions:",
     )
     parser.add_argument(
         "--bm_video_dir",
@@ -98,14 +99,16 @@ def main() -> None:
                 DecordNonBatchDecoderAccurateSeek()
             )
         elif decoder == "torchcodec":
-            decoder_dict["TorchCodecNonCompiled"] = TorchcodecNonCompiledWithOptions()
+            decoder_dict["TorchCodecCore:"] = TorchCodecCore()
         elif decoder == "torchcodec_compiled":
-            decoder_dict["TorchcodecCompiled"] = TorchcodecCompiled()
+            decoder_dict["TorchCodecCoreCompiled"] = TorchCodecCoreCompiled()
+        elif decoder == "torchcodec_public":
+            decoder_dict["TorchCodecPublic"] = TorchCodecPublic()
         elif decoder == "torchvision":
-            decoder_dict["TVNewAPIDecoderWithBackendVideoReader"] = (
+            decoder_dict["TorchVision[backend=video_reader]"] = (
                 # We don't compare TorchVision's "pyav" backend because it doesn't support
                 # accurate seeks.
-                TVNewAPIDecoderWithBackend("video_reader")
+                TorchVision("video_reader")
             )
         elif decoder == "torchaudio":
             decoder_dict["TorchAudioDecoder"] = TorchAudioDecoder()
@@ -117,8 +120,8 @@ def main() -> None:
                     continue
                 k, v = item.split("=")
                 kwargs_dict[k] = v
-            decoder_dict["TorchCodecNonCompiledBatch:" + options] = (
-                TorchCodecNonCompiledBatch(**kwargs_dict)
+            decoder_dict["TorchCodecCoreBatch" + options] = (
+                TorchCodecCoreBatch(**kwargs_dict)
             )
         elif decoder.startswith("tcoptions:"):
             options = decoder[len("tcoptions:") :]
@@ -128,8 +131,8 @@ def main() -> None:
                     continue
                 k, v = item.split("=")
                 kwargs_dict[k] = v
-            decoder_dict["TorchcodecNonCompiled:" + options] = (
-                TorchcodecNonCompiledWithOptions(**kwargs_dict)
+            decoder_dict["TorchCodecCore:" + options] = (
+                TorchCodecCore(**kwargs_dict)
             )
     video_paths = args.bm_video_paths.split(",")
     if args.bm_video_dir:

benchmarks/decoders/benchmark_decoders_library.py

@@ -12,7 +12,7 @@
 
 import torch
 import torch.utils.benchmark as benchmark
-from torchcodec.decoders import VideoDecoder
+from torchcodec.decoders import VideoDecoder, VideoStreamMetadata
 
 from torchcodec.decoders._core import (
     _add_video_stream,
@@ -78,7 +78,7 @@ def get_consecutive_frames_from_video(self, video_file, numFramesToDecode):
         return frames
 
 
-class TVNewAPIDecoderWithBackend(AbstractDecoder):
+class TorchVision(AbstractDecoder):
     def __init__(self, backend):
         self._backend = backend
         self._print_each_iteration_time = False
@@ -125,7 +125,7 @@ def get_consecutive_frames_from_video(self, video_file, numFramesToDecode):
         return frames
 
 
-class TorchcodecNonCompiledWithOptions(AbstractDecoder):
+class TorchCodecCore(AbstractDecoder):
     def __init__(self, num_threads=None, color_conversion_library=None, device="cpu"):
         self._print_each_iteration_time = False
         self._num_threads = int(num_threads) if num_threads else None
@@ -186,7 +186,7 @@ def get_consecutive_frames_from_video(self, video_file, numFramesToDecode):
         return frames
 
 
-class TorchCodecNonCompiledBatch(AbstractDecoder):
+class TorchCodecCoreBatch(AbstractDecoder):
     def __init__(self, num_threads=None, color_conversion_library=None):
         self._print_each_iteration_time = False
         self._num_threads = int(num_threads) if num_threads else None
@@ -227,6 +227,24 @@ def get_consecutive_frames_from_video(self, video_file, numFramesToDecode):
         )
         return frames
 
+class TorchCodecPublic(AbstractDecoder):
+    def __init__(self, num_ffmpeg_threads=None):
+        self._num_ffmpeg_threads = int(num_ffmpeg_threads) if num_ffmpeg_threads else None
+
+    def get_frames_from_video(self, video_file, pts_list):
+        decoder = VideoDecoder(video_file, num_ffmpeg_threads=self._num_ffmpeg_threads)
+        return decoder.get_frames_played_at(pts_list)
+
+    def get_consecutive_frames_from_video(self, video_file, numFramesToDecode):
+        decoder = VideoDecoder(video_file, num_ffmpeg_threads=self._num_ffmpeg_threads)
+        frames = []
+        count = 0
+        for frame in decoder:
+            frames.append(frame)
+            count += 1
+            if count == numFramesToDecode:
+                break
+        return frames
 
 @torch.compile(fullgraph=True, backend="eager")
 def compiled_seek_and_next(decoder, pts):
@@ -239,7 +257,7 @@ def compiled_next(decoder):
     return get_next_frame(decoder)
 
 
-class TorchcodecCompiled(AbstractDecoder):
+class TorchCodecCoreCompiled(AbstractDecoder):
     def __init__(self):
         pass
 
@@ -444,11 +462,13 @@ def plot_data(df_data, plot_path):
         plot_path,
     )
 
+def get_metadata(video_file_path: str) -> VideoStreamMetadata:
+    return VideoDecoder(video_file_path).metadata
 
 def run_benchmarks(
     decoder_dict,
     video_files_paths,
-    num_uniform_samples,
+    num_samples,
     min_runtime_seconds,
     benchmark_video_creation,
 ) -> list[dict[str, str | float | int]]:
@@ -459,55 +479,57 @@ def run_benchmarks(
     for decoder_name, decoder in decoder_dict.items():
         for video_file_path in video_files_paths:
             print(f"video={video_file_path}, decoder={decoder_name}")
-            # We only use the VideoDecoder to get the metadata and get
-            # the list of PTS values to seek to.
-            simple_decoder = VideoDecoder(video_file_path)
-            duration = simple_decoder.metadata.duration_seconds
-            pts_list = [
-                i * duration / num_uniform_samples for i in range(num_uniform_samples)
+            metadata = get_metadata(video_file_path)
+            metadata_label = f"{metadata.codec} {metadata.width}x{metadata.height}, {metadata.duration_seconds}s {metadata.average_fps}fps"
+
+            duration = metadata.duration_seconds
+            uniform_pts_list = [
+                i * duration / num_samples for i in range(num_samples)
             ]
-            metadata = simple_decoder.metadata
-            metadata_string = f"{metadata.codec} {metadata.width}x{metadata.height}, {metadata.duration_seconds}s {metadata.average_fps}fps"
-            if verbose:
-                print(
-                    f"video={video_file_path}, decoder={decoder_name}, pts_list={pts_list}"
+
+            random_pts_list = (torch.rand(num_samples) * duration).tolist()
+
+            for kind, pts_list in [("uniform", uniform_pts_list), ("random", random_pts_list)]:
+                if verbose:
+                    print(
+                        f"video={video_file_path}, decoder={decoder_name}, pts_list={pts_list}"
+                    )
+                seeked_result = benchmark.Timer(
+                    stmt="decoder.get_frames_from_video(video_file, pts_list)",
+                    globals={
+                        "video_file": video_file_path,
+                        "pts_list": pts_list,
+                        "decoder": decoder,
+                    },
+                    label=f"video={video_file_path} {metadata_label}",
+                    sub_label=decoder_name,
+                    description=f"{kind} {num_samples} seek()+next()",
                 )
-            seeked_result = benchmark.Timer(
-                stmt="decoder.get_frames_from_video(video_file, pts_list)",
-                globals={
-                    "video_file": video_file_path,
-                    "pts_list": pts_list,
-                    "decoder": decoder,
-                },
-                label=f"video={video_file_path} {metadata_string}",
-                sub_label=decoder_name,
-                description=f"{num_uniform_samples} seek()+next()",
-            )
-            results.append(
-                seeked_result.blocked_autorange(min_run_time=min_runtime_seconds)
-            )
-            df_item = {}
-            df_item["decoder"] = decoder_name
-            df_item["video"] = video_file_path
-            df_item["description"] = results[-1].description
-            df_item["frame_count"] = num_uniform_samples
-            df_item["median"] = results[-1].median
-            df_item["iqr"] = results[-1].iqr
-            df_item["type"] = "seek()+next()"
-            df_item["fps"] = 1.0 * num_uniform_samples / results[-1].median
-            df_item["fps_p75"] = 1.0 * num_uniform_samples / results[-1]._p75
-            df_item["fps_p25"] = 1.0 * num_uniform_samples / results[-1]._p25
-            df_data.append(df_item)
-
-            for num_consecutive_nexts in [1, 10]:
+                results.append(
+                    seeked_result.blocked_autorange(min_run_time=min_runtime_seconds)
+                )
+                df_item = {}
+                df_item["decoder"] = decoder_name
+                df_item["video"] = video_file_path
+                df_item["description"] = results[-1].description
+                df_item["frame_count"] = num_samples
+                df_item["median"] = results[-1].median
+                df_item["iqr"] = results[-1].iqr
+                df_item["type"] = f"{kind}:seek()+next()"
+                df_item["fps"] = 1.0 * num_samples / results[-1].median
+                df_item["fps_p75"] = 1.0 * num_samples / results[-1]._p75
+                df_item["fps_p25"] = 1.0 * num_samples / results[-1]._p25
+                df_data.append(df_item)
+
+            for num_consecutive_nexts in [100]:
                 consecutive_frames_result = benchmark.Timer(
                     stmt="decoder.get_consecutive_frames_from_video(video_file, consecutive_frames_to_extract)",
                     globals={
                         "video_file": video_file_path,
                         "consecutive_frames_to_extract": num_consecutive_nexts,
                         "decoder": decoder,
                     },
-                    label=f"video={video_file_path} {metadata_string}",
+                    label=f"video={video_file_path} {metadata_label}",
                     sub_label=decoder_name,
                     description=f"{num_consecutive_nexts} next()",
                 )
@@ -531,17 +553,16 @@ def run_benchmarks(
 
         first_video_file_path = video_files_paths[0]
         if benchmark_video_creation:
-            simple_decoder = VideoDecoder(first_video_file_path)
-            metadata = simple_decoder.metadata
-            metadata_string = f"{metadata.codec} {metadata.width}x{metadata.height}, {metadata.duration_seconds}s {metadata.average_fps}fps"
+            metadata = get_metadata(video_file_path)
+            metadata_label = f"{metadata.codec} {metadata.width}x{metadata.height}, {metadata.duration_seconds}s {metadata.average_fps}fps"
             creation_result = benchmark.Timer(
                 stmt="create_torchcodec_decoder_from_file(video_file)",
                 globals={
                     "video_file": first_video_file_path,
                     "create_torchcodec_decoder_from_file": create_torchcodec_decoder_from_file,
                 },
-                label=f"video={first_video_file_path} {metadata_string}",
-                sub_label="TorchcodecNonCompiled",
+                label=f"video={first_video_file_path} {metadata_label}",
+                sub_label="TorchCodecCore:",
                 description="create()+next()",
             )
             results.append(