def save_samples(data, bits, outfname):
print("bits", bits.shape)
nb_bits = bits.shape[1]
for i in range(len(data)):
s = 64 // nb_bits
for j in range(nb_bits):
data[i, :s, s * j:s * (j + 1)] = 2 * bits[i, j] - 1
image_save(outfname, np.clip(tile(data), -1, 1))
def save_samples(data, bits, outfname):
print("bits", bits.shape)
nb_bits = bits.shape[1]
for i in range(len(data)):
s = 64 // nb_bits
for j in range(nb_bits):
data[i, :s, s*j:s*(j+1)] = 2*bits[i, j] - 1
image_save(outfname, np.clip(tile(data), -1, 1))
def save_real_images(real_hdf5_fname, output_dir, nb_visualise=20**2):
real = next(train_data_generator(real_hdf5_fname, nb_visualise, 10))['data']
print(real.shape)
print(real.max())
print(real.min())
tiled = tile(real)
fname = join(output_dir, 'real_{}.png'.format(nb_visualise))
image_save(fname, tiled[0])
def save_real_images(real_hdf5_fname, output_dir, nb_visualise=20**2):
real = next(train_data_generator(real_hdf5_fname, nb_visualise,
10))['data']
print(real.shape)
print(real.max())
print(real.min())
tiled = tile(real)
fname = join(output_dir, 'real_{}.png'.format(nb_visualise))
image_save(fname, tiled[0])
def save_first_frame(video_fname, output_dir, force):
camIdx, start, _ = parse_video_fname(video_fname)
outname = os.path.join(output_dir, get_fname(camIdx, start) + ".png")
if os.path.exists(outname) and not force:
return
gen = raw_frames_generator(video_fname, format='guess_on_ext')
frame = next(gen)
assert frame.dtype == np.uint8
image_save(outname, frame)
def save_first_frame(video_fname, output_dir, force):
camIdx, start, _ = parse_video_fname(video_fname)
outname = os.path.join(output_dir, get_fname(camIdx, start) + ".png")
if os.path.exists(outname) and not force:
return
gen = raw_frames_generator(video_fname, format='guess_on_ext')
frame = next(gen)
assert frame.dtype == np.uint8
image_save(outname, frame)
def test_image_save(tmpdir):
x = np.random.random((1, 64, 64))
image_save(str(tmpdir.join("one_channel.png")), x)
x = np.random.random((3, 64, 64))
image_save(str(tmpdir.join("one_channel.png")), x)
x = np.random.random((64, 64))
image_save(str(tmpdir.join("one_channel.png")), x)
with pytest.raises(Exception):
x = np.random.random((100, 64, 64))
image_save(str(tmpdir.join("one_channel.png")), x)
# test scale
x = 0.5*np.linspace(0, 1, 64*64).reshape((64, 64)) + 0.1
image_save(str(tmpdir.join("scale.png")), x, low=0, high=1)
loaded_x = imread(str(tmpdir.join("scale.png")))
assert 0.1 <= x.min()
assert np.abs(0.1 - (loaded_x / 255.).min()) <= 1/256
assert (loaded_x / 255.).max() <= 0.6
def visualize_detection_tiles(dset, name, n=20**2):
crown_vis = ResultCrownVisualizer()
imgs_raw = []
imgs_overlayed = []
nb_tags = len(dset['tags'])
n = min(nb_tags, n)
indicies = np.arange(nb_tags)
np.random.shuffle(indicies)
for i in range(n):
p = indicies[i]
position = np.array([dset['tags'][0, 0].shape]) / 2
tag = dset['tags'][p, 0]
bits = (dset['bits'][p:p + 1] + 1) / 2.
overlay = crown_vis(tag, position, np.zeros((1, 3)), bits)[0]
overlayed = crown_vis.add_overlay((tag + 1) / 2, overlay)
imgs_raw.append(tag)
imgs_overlayed.append(2 * overlayed - 1)
tiled_raw = tile([img.swapaxes(0, -1) for img in imgs_raw])
tiled_overlayed = tile([img.swapaxes(0, -1) for img in imgs_overlayed])
image_save(name + '_raw.png', tiled_raw)
image_save(name + '_overlayed.png', tiled_overlayed)
def test_stack_augmentations(outdir, datadir):
fname = "/home/leon/uni/bachelor/deepdecoder/test/data/00350.hdf5"
myconfig = config.load(str(datadir.join('augmentation.yml')))
dset = DistributionHDF5Dataset(fname)
batch = next(dset.iter(15**2))
image_save(str(outdir.join('real.png')), tile(batch['real']))
image_save(str(outdir.join('fake.png')), np.clip(tile(batch['fake']), -1, 1))
# for i, name in enumerate(['tag3d']):
for i, name in enumerate(['tag3d', 'tag3d_lighten', 'fake_without_noise', 'fake']):
augment = stack_augmentations(name, myconfig)
xs = augment(batch)
image_save(str(outdir.join('{}_{}_aug_tiled.png'.format(i, name))), tile(xs))
