def test_img_one(self):
bp = os.path.join(os.path.dirname(__file__), 'test-images')
imgs = [os.path.join(bp, x) for x in ["eiffel1.png"]]
ie = ImageEmbedder()
ie.load_model(model_name="mobilenet", depth=-2)
embed = ie.process_images(imgs, pooling="flat")
embed_one = ie.process_images(imgs[0], pooling="flat")
sim = np.mean(np.abs(embed[0, :] - embed_one[0, :]))
self.assertLess(sim, 0.000001)
def test_depth_positive(self):
bp = os.path.join(os.path.dirname(__file__), 'test-images')
imgs = [os.path.join(bp, x) for x in ["eiffel1.png"]]
ie = ImageEmbedder()
ie.load_model(model_name="mobilenet", depth=10)
embed_pos = ie.process_images(imgs)
ie.load_model(model_name="mobilenet", depth=-45)
embed_neg = ie.process_images(imgs)
sim = np.sum(np.abs(embed_pos[0, :] - embed_neg[0, :]))
self.assertLess(sim, 0.000001)
def test_pooling(self):
bp = os.path.join(os.path.dirname(__file__), 'test-images')
imgs = [os.path.join(bp, x) for x in ["eiffel1.png"]]
ie = ImageEmbedder()
ie.load_model(model_name="mobilenet", depth=2)
embed_none = ie.process_images(imgs, pooling="none")
embed_max = ie.process_images(imgs, pooling="max")
embed_avg = ie.process_images(imgs, pooling="avg")
embed_flat = ie.process_images(imgs, pooling="flat")
self.assertEqual(embed_none.shape, (1, 112, 112, 32))
self.assertEqual(embed_max.shape, (1, 112 * 112))
self.assertEqual(embed_avg.shape, (1, 112 * 112))
self.assertEqual(embed_flat.shape, (1, 112 * 112 * 32))
self.assertGreater(np.mean(embed_max), np.mean(embed_avg))
def test_img_small(self):
bp = os.path.join(os.path.dirname(__file__), 'test-images')
imgs = [
os.path.join(bp, x)
for x in ["eiffel1.png", "eiffel1-small.jpg", "eiffel1-small.png"]
]
ie = ImageEmbedder()
ie.load_model(model_name="mobilenet", depth=-2)
embed = ie.process_images(imgs, pooling="flat")
sim1 = np.mean(np.abs(embed[0, :] - embed[1, :]))
sim2 = np.mean(np.abs(embed[0, :] - embed[2, :]))
sim = (sim1 + sim2) / 2
self.assertLess(sim, 2)
def main(model_name, depth, output):
from image_embed import ImageEmbedder
if os.path.exists(output):
msg = "Output location '{0:s}' already exists.".format(output)
raise ValueError(msg)
input_dir = "~/local/cv_tutorial/images/wikiart"
input_dir = os.path.expanduser(input_dir)
input_dir = os.path.abspath(input_dir)
fs = [
y for x in os.walk(input_dir)
for y in glob(os.path.join(x[0], '*.jpg'))
]
ie = ImageEmbedder()
ie.load_model(model_name=model_name, depth=depth)
ld = len([x.name for x in ie.nn.layers if x.count_params() > 0])
sz = np.prod(ie.nn.layers[-1].output_shape[1:])
click.echo("")
click.echo("Loaded model. : {0:s}".format(model_name))
click.echo("Depth parameters : {0:d}".format(depth))
click.echo("Total depth : {0:d}".format(ld))
click.echo("Output size : {0:d}".format(sz))
click.echo("")
click.echo("Input location : {0:s}".format(input_dir))
click.echo("Num. input images : {0:d}".format(len(fs)))
click.echo("")
embed = ie.process_images(fs)
ue = umap.UMAP(n_neighbors=10, min_dist=0.1).fit_transform(embed)
df = pd.DataFrame(ue)
df.columns = ['umap{0:d}'.format(x) for x in range(df.shape[1])]
df = pd.concat([pd.DataFrame({"file": fs}), df], axis=1)
df.to_csv(output, index=False)
click.echo("\n\n")