def _make_encoded_video_dataset(self, data) -> 'EncodedVideoDataset':
ds: EncodedVideoDataset = labeled_encoded_video_dataset(
pathlib.Path(data),
self.clip_sampler,
video_sampler=self.video_sampler,
decode_audio=self.decode_audio,
decoder=self.decoder,
)
return ds
def load_data(self, data: Any, dataset: IterableDataset) -> 'EncodedVideoDataset':
ds: EncodedVideoDataset = labeled_encoded_video_dataset(
data,
self.clip_sampler,
video_sampler=self.video_sampler,
decode_audio=self.decode_audio,
decoder=self.decoder,
)
if self.training:
label_to_class_mapping = {p[1]: p[0].split("/")[-2] for p in ds._labeled_videos._paths_and_labels}
self.set_state(ClassificationState(label_to_class_mapping))
dataset.num_classes = len(np.unique([s[1]['label'] for s in ds._labeled_videos]))
return ds
def test_random_video_sampler(self, decoder):
with mock_encoded_video_dataset_file() as (mock_csv, expected,
total_duration):
clip_sampler = make_clip_sampler("uniform", total_duration)
dataset = labeled_encoded_video_dataset(
data_path=mock_csv,
clip_sampler=clip_sampler,
video_sampler=RandomSampler,
decode_audio=False,
decoder=decoder,
)
for _ in range(2):
actual = [(sample["label"], sample["video"])
for sample in dataset]
assert_unordered_list_compare_true(self, expected, actual)
def load_data(self,
data: str,
dataset: Optional[Any] = None) -> 'EncodedVideoDataset':
ds: EncodedVideoDataset = labeled_encoded_video_dataset(
pathlib.Path(data),
self.clip_sampler,
video_sampler=self.video_sampler,
decode_audio=self.decode_audio,
decoder=self.decoder,
)
if self.training:
label_to_class_mapping = {
p[1]: p[0].split("/")[-2]
for p in ds._labeled_videos._paths_and_labels
}
self.set_state(LabelsState(label_to_class_mapping))
dataset.num_classes = len(
np.unique([s[1]['label'] for s in ds._labeled_videos]))
return ds
def test_single_clip_per_video_works(self, decoder):
with mock_encoded_video_dataset_file() as (mock_csv, expected,
total_duration):
clip_sampler = make_clip_sampler("uniform", total_duration)
dataset = labeled_encoded_video_dataset(
data_path=mock_csv,
clip_sampler=clip_sampler,
video_sampler=SequentialSampler,
decode_audio=False,
decoder=decoder,
)
test_dataloader = DataLoader(dataset,
batch_size=None,
num_workers=2)
for _ in range(2):
actual = [(sample["label"], sample["video"])
for sample in test_dataloader]
assert_unordered_list_compare_true(self, expected, actual)