Merge branch 'main' of github.com:pytorch/torchcodec into allocation

Author: NicolasHug

.github/workflows/lint.yaml

@@ -36,8 +36,6 @@ jobs:
         run: |
           python -m pip install pre-commit
       - name: Run pre-commit checks
-        # Continue on error to display the formatting diff in case lint fails.
-        continue-on-error: true
         run: |
           pre-commit run --all-files
       - name: Check to see what files pre-commit modified

benchmarks/decoders/benchmark_decoders.py

@@ -14,9 +14,9 @@
     plot_data,
     run_benchmarks,
     TorchAudioDecoder,
-    TorchCodecCoreCompiled,
-    TorchCodecCoreBatch,
     TorchCodecCore,
+    TorchCodecCoreBatch,
+    TorchCodecCoreCompiled,
     TorchCodecPublic,
     TorchVision,
 )
@@ -120,8 +120,8 @@ def main() -> None:
                     continue
                 k, v = item.split("=")
                 kwargs_dict[k] = v
-            decoder_dict["TorchCodecCoreBatch" + options] = (
-                TorchCodecCoreBatch(**kwargs_dict)
+            decoder_dict["TorchCodecCoreBatch" + options] = TorchCodecCoreBatch(
+                **kwargs_dict
             )
         elif decoder.startswith("tcoptions:"):
             options = decoder[len("tcoptions:") :]
@@ -131,9 +131,7 @@ def main() -> None:
                     continue
                 k, v = item.split("=")
                 kwargs_dict[k] = v
-            decoder_dict["TorchCodecCore:" + options] = (
-                TorchCodecCore(**kwargs_dict)
-            )
+            decoder_dict["TorchCodecCore:" + options] = TorchCodecCore(**kwargs_dict)
     video_paths = args.bm_video_paths.split(",")
     if args.bm_video_dir:
         video_paths = []

benchmarks/decoders/benchmark_decoders_library.py

@@ -227,9 +227,12 @@ 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
+        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)
@@ -246,6 +249,7 @@ def get_consecutive_frames_from_video(self, video_file, numFramesToDecode):
                 break
         return frames
 
+
 @torch.compile(fullgraph=True, backend="eager")
 def compiled_seek_and_next(decoder, pts):
     seek_to_pts(decoder, pts)
@@ -468,9 +472,11 @@ 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: dict[str, AbstractDecoder],
     video_files_paths: list[str],
@@ -492,9 +498,7 @@ def run_benchmarks(
         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)
-        ]
+        uniform_pts_list = [i * duration / num_samples for i in range(num_samples)]
 
         # Note that we are using the same random pts values for all decoders for the same
         # video. However, because we use the duration as part of this calculation, we
@@ -504,7 +508,10 @@ def run_benchmarks(
         for decoder_name, decoder in decoder_dict.items():
             print(f"video={video_file_path}, decoder={decoder_name}")
 
-            for kind, pts_list in [("uniform", uniform_pts_list), ("random", random_pts_list)]:
+            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}"

benchmarks/decoders/benchmark_readme_data.json

@@ -150,4 +150,4 @@
         "python_version": "3.11.10",
         "system": "Linux"
     }
-]
+]

benchmarks/decoders/generate_readme_data.py

@@ -47,12 +47,8 @@ def main() -> None:
 
     decoder_dict = {}
     decoder_dict["TorchCodec"] = TorchCodecPublic()
-    decoder_dict["TorchCodec[num_threads=1]"] = TorchCodecPublic(
-        num_ffmpeg_threads=1
-    )
-    decoder_dict["TorchVision[backend=video_reader]"] = TorchVision(
-        "video_reader"
-    )
+    decoder_dict["TorchCodec[num_threads=1]"] = TorchCodecPublic(num_ffmpeg_threads=1)
+    decoder_dict["TorchVision[backend=video_reader]"] = TorchVision("video_reader")
     decoder_dict["TorchAudio"] = TorchAudioDecoder()
 
     # These are the number of uniform seeks we do in the seek+decode benchmark.