File size: 3,777 Bytes
3133fdb |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 |
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
import contextlib
import json
import tempfile
import unittest
from pytorchvideo.data import json_dataset
from pytorchvideo.data.clip_sampling import make_clip_sampler
from pytorchvideo.data.labeled_video_dataset import LabeledVideoDataset
from utils import temp_frame_video_dataset
class TestJsonDatasets(unittest.TestCase):
def setUp(self):
LabeledVideoDataset._MAX_CONSECUTIVE_FAILURES = 1
def test_recognition_random_clip_sampler(self):
total_duration = 0.05
with mock_json_annotations() as (annotation_json, labels, duration):
clip_sampler = make_clip_sampler("random", total_duration)
dataset = json_dataset.clip_recognition_dataset(
data_path=annotation_json,
clip_sampler=clip_sampler,
decode_audio=False,
)
self.assertEqual(dataset.num_videos, 4)
self.assertEqual(len(list(iter(dataset))), 4)
def test_recognition_uniform_clip_sampler(self):
total_duration = 0.05
with mock_json_annotations() as (annotation_json, labels, duration):
clip_sampler = make_clip_sampler("uniform", total_duration)
dataset = json_dataset.clip_recognition_dataset(
data_path=annotation_json,
clip_sampler=clip_sampler,
decode_audio=False,
)
self.assertEqual(dataset.num_videos, 4)
self.assertEqual(len(list(iter(dataset))), 4)
def test_video_only_frame_video_dataset(self):
total_duration = 2.0
with mock_json_annotations() as (annotation_json, labels, duration):
clip_sampler = make_clip_sampler("random", total_duration)
dataset = json_dataset.video_only_dataset(
data_path=annotation_json,
clip_sampler=clip_sampler,
decode_audio=False,
)
self.assertEqual(dataset.num_videos, 2)
self.assertEqual(len(list(iter(dataset))), 2)
@contextlib.contextmanager
def mock_json_annotations():
with temp_frame_video_dataset() as (_, videos):
label_videos = []
json_dict = {}
for video in videos:
label_videos.append((video[-3], video[-2]))
name = str(video[0])
json_dict[name] = {
"benchmarks": {
"forecasting_hands_objects": [
{
"critical_frame_selection_parent_start_sec": 0.001,
"critical_frame_selection_parent_end_sec": 0.012,
"taxonomy": {
"noun": video[-3],
"verb": video[-3],
"noun_unsure": False,
"verb_unsure": False,
},
},
{
"critical_frame_selection_parent_start_sec": 0.01,
"critical_frame_selection_parent_end_sec": 0.05,
"taxonomy": {
"noun": video[-3],
"verb": video[-3],
"noun_unsure": False,
"verb_unsure": False,
},
},
]
}
}
with tempfile.NamedTemporaryFile(delete=False, suffix=".json", mode="wt") as f:
json.dump(json_dict, f)
f.close()
min_duration = min(videos[0][-1], videos[1][-1])
yield f.name, label_videos, min_duration
|