def get_x_y(self, tag_set, reduction_factor=0):
x = None
y = None
for t in tqdm(tag_set):
use_sample = True
if reduction_factor > 1:
if not np.random.randint(0, reduction_factor):
use_sample = False
if use_sample:
x_img = t.load_x()
segments = generate_segments(x_img, self.opt)
x_img, _ = self.get_features(x_img)
h_img, w_img = x_img.shape[:2]
x_img = get_features_for_segments(
x_img, segments, self.opt["feature_aggregation"])
y_img = t.load_y([h_img, w_img])
y_img = get_y_for_segments(y_img, segments)
assert x_img.shape[0] == y_img.shape[
0], "Not equal dimensions. [{} - {}]".format(
x_img.shape, y_img.shape)
if x is None:
x = x_img
y = y_img
else:
x = np.append(x, x_img, axis=0)
y = np.append(y, y_img, axis=0)
return x, y
def inference(self, x_input, interpolation="nearest"):
segments = generate_segments(x_input, self.opt)
x_img, x_pass = self.get_features(x_input)
o_height, o_width = x_pass.shape[:2]
x_height, x_width = x_img.shape[:2]
x_img = get_features_for_segments(x_img, segments,
self.opt["feature_aggregation"])
y_pred = self.clf.predict_proba(x_img)
segments = resize(segments,
width=x_width,
height=x_height,
interpolation="nearest")
y_img = map_segments(segments, y_pred)
x_img_pass = resize(x_pass,
width=o_width,
height=o_height,
interpolation="nearest")
y_img = resize(y_img,
width=o_width,
height=o_height,
interpolation=interpolation)
if len(x_img_pass.shape) < 3:
x_img_pass = np.expand_dims(x_img_pass, axis=2)
if len(y_img.shape) < 3:
y_img = np.expand_dims(y_img, axis=2)
y_img = np.concatenate([x_img_pass, y_img], axis=2)
return y_img
def predict(self, tag):
x_input = tag.load_x()
segments = generate_segments(x_input, self.opt)
x_img, x_pass = self.get_features(tag)
o_height, o_width = x_pass.shape[:2]
x_height, x_width = x_img.shape[:2]
x_img = get_features_for_segments(x_img, segments, self.opt["feature_aggregation"])
y_img = self.clf.predict(x_img)
segments = resize(segments, width=x_width, height=x_height, interpolation="nearest")
y_img = map_segments(segments, y_img)
y_img = resize(y_img, width=o_width, height=o_height, interpolation="nearest")
return y_img