def test_davis_tensorpack_dataflow():
ds = Davis('/data/public/rw/datasets/videos/davis/trainval', num_frames=4)
ds = df.MapDataComponent(
ds,
lambda images: [cv2.resize(image, (256, 256)) for image in images],
index=1)
ds = df.MapDataComponent(
ds,
lambda images: [cv2.resize(image, (256, 256)) for image in images],
index=2)
ds = df.MapDataComponent(ds,
lambda images: np.stack(images, axis=0),
index=1)
ds = df.MapDataComponent(ds,
lambda images: np.stack(images, axis=0),
index=2)
ds = df.BatchData(ds, 6)
ds.reset_state()
generator = ds.get_data()
for _ in range(10):
_, images, annotations = next(generator)
assert images.shape == (6, 4, 256, 256, 3)
assert annotations.shape == (6, 4, 256, 256, 3)
def test_davis():
davis = Davis('/data/public/rw/datasets/videos/davis/trainval')
assert davis.size() == 6000
assert davis.names[:5] == [
'bear', 'bmx-bumps', 'boat', 'boxing-fisheye', 'breakdance-flare'
]
assert davis.names[-5:] == [
'train', 'tuk-tuk', 'upside-down', 'varanus-cage', 'walking'
]
def dataflow(name='davis', scale=1, split='val'):
if name == 'davis':
ds = Davis('/data/zubin/videos/davis', name=split, num_frames=1, shuffle=False)
elif name == 'kinetics':
ds = Kinetics('/data/public/rw/datasets/videos/kinetics', num_frames=1, skips=[0], shuffle=False)
else:
raise Exception('not support dataset %s' % name)
if name != 'davis':
ds = df.MapData(ds, lambda dp: [dp[0], dp[1], dp[1]])
ds = df.MapData(ds, lambda dp: [
dp[0], # index
dp[1], # original
dp[2], # mask
dp[3], # name
])
feature_size = int(256 * scale)
size = (feature_size, feature_size)
ds = df.MapDataComponent(ds, ImageProcess.resize(small_axis=feature_size), index=1)
ds = df.MapDataComponent(ds, lambda images: cv2.resize(images[0], size), index=2)
ds = df.MapData(ds, lambda dp: [
dp[0], # index
dp[1][0], # original small axis 256 x scale
cv2.cvtColor(cv2.resize(dp[1][0], size), cv2.COLOR_BGR2GRAY).reshape((size[0], size[1], 1)), # gray (256xscale)x(256xscale)x1
dp[2], # annotated mask 256xscale x 256xscale
dp[3], # name
])
ds = df.MultiProcessPrefetchData(ds, nr_prefetch=32, nr_proc=1)
return ds
def test_davis_generator_with_num_frames():
davis = Davis('/data/public/rw/datasets/videos/davis/trainval')
generator = davis.get_data(num_frames=4)
idx, images, annotations = next(generator)
assert idx == 0
assert len(images) == 4
assert [image.shape for image in images] == [(1080, 1920, 3)] * 4
assert [image.shape for image in annotations] == [(1080, 1920, 3)] * 4
for _ in range(81 // 4 - 2):
next(generator)
idx, images, annotations = next(generator)
assert idx == 19
assert len(images) == 4
assert [image.shape for image in images] == [(1080, 1920, 3)] * 4
assert [image.shape for image in annotations] == [(1080, 1920, 3)] * 4
idx, images, annotations = next(generator)
assert idx == 0
assert len(images) == 4
assert [image.shape for image in images] == [(1080, 1920, 3)] * 4
assert [image.shape for image in annotations] == [(1080, 1920, 3)] * 4
def test_davis_generator():
davis = Davis('/data/public/rw/datasets/videos/davis/trainval')
generator = davis.get_data()
idx, images, annotations = next(generator)
assert idx == 0
assert len(images) == 1
assert images[0].shape == (1080, 1920, 3)
assert annotations[0].shape == (1080, 1920, 3)
for _ in range(81 - 1):
next(generator)
idx, images, annotations = next(generator)
assert idx == 81
assert len(images) == 1
assert images[0].shape == (1080, 1920, 3)
assert annotations[0].shape == (1080, 1920, 3)
idx, images, annotations = next(generator)
assert idx == 0
assert len(images) == 1
assert images[0].shape == (1080, 1920, 3)
assert annotations[0].shape == (1080, 1920, 3)
def dataflow(name='davis', scale=1):
if name == 'davis':
ds = Davis('/data/public/rw/datasets/videos/davis/trainval',
num_frames=1,
shuffle=False)
elif name == 'kinetics':
ds = Kinetics('/data/public/rw/datasets/videos/kinetics',
num_frames=1,
skips=[0],
shuffle=False)
else:
raise Exception('not support dataset %s' % name)
if name != 'davis':
ds = df.MapData(ds, lambda dp: [dp[0], dp[1], dp[1]])
ds = df.MapData(
ds,
lambda dp: [
dp[0], # index
dp[1], # original
dp[2], # mask
])
size = (256 * scale, 256 * scale)
ds = df.MapDataComponent(ds,
ImageProcess.resize(small_axis=256 * scale),
index=1)
ds = df.MapDataComponent(ds,
lambda images: cv2.resize(images[0], size),
index=2)
ds = df.MapData(
ds,
lambda dp: [
dp[0], # index
dp[1][0], # original
cv2.cvtColor(cv2.resize(dp[1][0], size), cv2.COLOR_BGR2GRAY).
reshape((size[0], size[1], 1)), # gray
dp[2], # mask
])
ds = df.MultiProcessPrefetchData(ds, nr_prefetch=32, nr_proc=1)
return ds