[video reader] inception commit (#1303)

* [video reader] inception commit

* add method save_metadata to class VideoClips in video_utils.py

* add load_metadata() method to VideoClips class

* add Exception to not catch unexpected events such as memory erros, interrupt

* fix bugs in video_plus.py

* [video reader]remove logging. update setup.py

* remove time measurement in test_video_reader.py

* Remove glog and try making ffmpeg finding more robust

* Add ffmpeg to conda build

* Add ffmpeg to conda build [again]

* Make library path finding more robust

* Missing import

* One more missing fix for import

* Py2 compatibility and change package to av to avoid version conflict with ffmpeg

* Fix for python2

* [video reader] support to decode one stream only (e.g. video/audio stream)

* remove argument _precomputed_metadata_filepath

* remove save_metadata method

* add get_metadata method

* expose _precomputed_metadata and frame_rate arguments in video dataset __init__ method

* remove ssize_t

* remove size_t to pass CI check on Windows

* add PyInit__video_reader function to pass CI check on Windows

* minor fix to define PyInit_video_reader symbol

* Make c++ video reader optional

* Temporarily revert changes to test_io

* Revert changes to python files

* Rename files to make it private

* Fix python lint

* Fix C++ lint

* add a functor object EnumClassHash to make Enum class instances usable as key type of std::unordered_map

* fix cpp format check

Author: stephenyan1231

packaging/torchvision/meta.yaml

@@ -12,6 +12,7 @@ requirements:
   host:
     - python
     - setuptools
+    - av
     {{ environ.get('CONDA_PYTORCH_BUILD_CONSTRAINT') }}
     {{ environ.get('CONDA_CUDATOOLKIT_CONSTRAINT') }}
     {{ environ.get('CONDA_CPUONLY_FEATURE') }}
@@ -21,6 +22,7 @@ requirements:
     - pillow >=4.1.1
     - numpy >=1.11
     - six
+    - av
     {{ environ.get('CONDA_PYTORCH_CONSTRAINT') }}
     {{ environ.get('CONDA_CUDATOOLKIT_CONSTRAINT') }}
 

setup.py

@@ -7,11 +7,12 @@
 from pkg_resources import get_distribution, DistributionNotFound
 import subprocess
 import distutils.command.clean
+import distutils.spawn
 import glob
 import shutil
 
 import torch
-from torch.utils.cpp_extension import CppExtension, CUDAExtension, CUDA_HOME
+from torch.utils.cpp_extension import BuildExtension, CppExtension, CUDAExtension, CUDA_HOME
 
 
 def read(*names, **kwargs):
@@ -124,6 +125,17 @@ def get_extensions():
     include_dirs = [extensions_dir]
     tests_include_dirs = [test_dir, models_dir]
 
+    ffmpeg_exe = distutils.spawn.find_executable('ffmpeg')
+    has_ffmpeg = ffmpeg_exe is not None
+    if has_ffmpeg:
+        ffmpeg_bin = os.path.dirname(ffmpeg_exe)
+        ffmpeg_root = os.path.dirname(ffmpeg_bin)
+        ffmpeg_include_dir = os.path.join(ffmpeg_root, 'include')
+
+        # TorchVision video reader
+        video_reader_src_dir = os.path.join(this_dir, 'torchvision', 'csrc', 'cpu', 'video_reader')
+        video_reader_src = glob.glob(os.path.join(video_reader_src_dir, "*.cpp"))
+
     ext_modules = [
         extension(
             'torchvision._C',
@@ -140,6 +152,27 @@ def get_extensions():
             extra_compile_args=extra_compile_args,
         ),
     ]
+    if has_ffmpeg:
+        ext_modules.append(
+            CppExtension(
+                'torchvision.video_reader',
+                video_reader_src,
+                include_dirs=[
+                    video_reader_src_dir,
+                    ffmpeg_include_dir,
+                    extensions_dir,
+                ],
+                libraries=[
+                    'avcodec',
+                    'avformat',
+                    'avutil',
+                    'swresample',
+                    'swscale',
+                ],
+                extra_compile_args=["-std=c++14"],
+                extra_link_args=["-std=c++14"],
+            )
+        )
 
     return ext_modules
 
@@ -179,6 +212,8 @@ def run(self):
         "scipy": ["scipy"],
     },
     ext_modules=get_extensions(),
-    cmdclass={'build_ext': torch.utils.cpp_extension.BuildExtension,
-              'clean': clean}
+    cmdclass={
+        'build_ext': BuildExtension.with_options(no_python_abi_suffix=True),
+        'clean': clean,
+    }
 )

test/assets/videos/R6llTwEh07w.mp4

@@ -0,0 +1,59 @@
+Video meta-information Notation
+
+Video File Name
+  video: codec, fps
+  audio: codec, bits per sample, sample rate
+
+Test videos are listed below.
+--------------------------------
+
+- RATRACE_wave_f_nm_np1_fr_goo_37.avi
+  - source: hmdb51
+  - video: DivX MPEG-4
+    - fps: 30
+  - audio: N/A
+
+- SchoolRulesHowTheyHelpUs_wave_f_nm_np1_ba_med_0.avi
+  - source: hmdb51
+  - video: DivX MPEG-4
+    - fps: 30
+  - audio: N/A
+
+- TrumanShow_wave_f_nm_np1_fr_med_26.avi
+  - source: hmdb51
+  - video: DivX MPEG-4
+    - fps: 30
+  - audio: N/A
+
+- v_SoccerJuggling_g23_c01.avi
+  - source: ucf101
+  - video: Xvid MPEG-4
+    - fps: 29.97
+  - audio: N/A
+
+- v_SoccerJuggling_g24_c01.avi
+  - source: ucf101
+  - video: Xvid MPEG-4
+    - fps: 29.97
+  - audio: N/A
+
+- R6llTwEh07w.mp4
+  - source: kinetics-400
+  - video: H-264 - MPEG-4 AVC (part 10) (avc1)
+    - fps: 30
+  - audio: MPEG AAC audio (mp4a)
+    - sample rate: 44.1K Hz
+
+- SOX5yA1l24A.mp4
+  - source: kinetics-400
+  - video: H-264 - MPEG-4 AVC (part 10) (avc1)
+    - fps: 29.97
+  - audio: MPEG AAC audio (mp4a)
+    - sample rate: 48K Hz
+
+- WUzgd7C1pWA.mp4
+  - source: kinetics-400
+  - video: H-264 - MPEG-4 AVC (part 10) (avc1)
+    - fps: 29.97
+  - audio: MPEG AAC audio (mp4a)
+    - sample rate: 48K Hz