def test_load_data_single_column():
"""Test that the featurizer saves attributes correctly after loading data"""
f = ImageFeaturizer()
f.load_data(**LOAD_DATA_ARGS)
compare_featurizer_class(f, (227, 227), np.zeros((1)), **COMPARE_ARGS)
# Remove path to the generated csv at end of test
remove_generated_paths()
def test_load_data_single_column():
"""Test that the featurizer saves attributes correctly after loading data"""
f = ImageFeaturizer()
f.load_data(**LOAD_DATA_ARGS)
compare_featurizer_class(f, (227, 227), np.zeros((1)), **COMPARE_ARGS)
# Remove path to the generated csv at end of test
if os.path.isdir('tests/ImageFeaturizer_testing/csv_tests'):
shutil.rmtree('tests/ImageFeaturizer_testing/csv_tests')
def test_load_then_featurize_data_single_column():
"""Test featurizations and attributes for each model are correct with multiple image columns"""
feat = ImageFeaturizer()
feat.load_data(**LOAD_DATA_ARGS)
feat.featurize_preloaded_data(save_features=True)
check_array = np.load(CHECK_ARRAY.format('squeezenet'))
try:
compare_featurizer_class(feat, (227, 227), check_array, featurized=True,
check_csv=CHECK_CSV.format('squeezenet'), **COMPARE_ARGS)
finally:
# Remove path to the generated csv at the end of the test
remove_generated_paths()
del feat
def test_load_data_multiple_columns():
"""Test featurizer loads data correctly with multiple image columns"""
f = ImageFeaturizer(auto_sample=True)
f.load_data(**LOAD_DATA_ARGS_MULT)
compare_featurizer_class(f, (227, 227), np.zeros((1)), **COMPARE_ARGS_MULT)
def test_load_data_multiple_columns_no_csv():
"""Test featurizer raises error if multiple columns passed with only a directory"""
f = ImageFeaturizer()
with pytest.raises(ValueError):
f.load_data(**LOAD_DATA_ARGS_MULT_ERROR)
def main():
parser = argparse.ArgumentParser()
parser.add_argument('--infolder',
default='../../original/Suomi/Kunta/',
help='folder containing the source images')
parser.add_argument('--coatfolder',
default=None,
help='folder containing the output images')
parser.add_argument('--outimage',
default='embedding.png',
help='Name of the output image')
parser.add_argument('--outcsv',
default='vectors.csv',
help='Name of the csv output')
parser.add_argument('--dpi',
default=300, type=int,
help='Resolution of the output image')
parser.add_argument('--zoom',
default=0.1, type=float,
help='size of a coat in output image')
parser.add_argument('--depth',
default=1, type=int,
help='Network depth')
parser.add_argument('--model',
default='squeezenet',
help='Network type')
args = parser.parse_args()
image_path = args.infolder
outimage = args.outimage
if args.coatfolder is None:
coatfolder = image_path
else:
coatfolder = args.coatfolder
# Extract vectors
featurizer = ImageFeaturizer(depth=args.depth, autosample = False, model=args.model)
featurizer.load_data('images', image_path=image_path)
featurize_preloaded_df = featurizer.featurize_preloaded_data(save_features=True)
# Output to csv file
featurize_preloaded_df.to_csv(path_or_buf = args.outcsv, sep = '\t')
print('Vector data saved to {}'.format(args.outcsv))
images = featurize_preloaded_df.values[:,0]
paths = [coatfolder+x for x in images]
# extract vectors:
X = featurize_preloaded_df.values[:,2:]
# First dimensionality reduction to 32 dimensions using truncated singular value decomposition
Y = TruncatedSVD(32).fit_transform(X)
# For plotting dimensionality reduction to 2D with TSNE
Y = TSNE(n_components=2, perplexity=30.0).fit_transform(Y)
# Plot the output image
plt.tight_layout()
fig, ax = plt.subplots()
ax.set_axis_off()
ax.scatter(Y[:,0], Y[:,1])
arr = []
for x0, y0, path in zip(Y[:,0], Y[:,1], paths):
try:
ab = AnnotationBbox(getImage(path, zoom=args.zoom), (x0, y0), frameon=False)
arr.append(ax.add_artist(ab))
except FileNotFoundError:
pass
fig.savefig(outimage, dpi=args.dpi, bbox_inches='tight')
print("{} saved.".format(outimage))
