def extract_and_predict(self, image, featureSet=None):
# Use the classifier's configured feature set
if not featureSet:
featureSet = self.featureSet
extractedFeatures = FeatureExtractor.extract(image, featureSet)
return self.model.predict([extractedFeatures])
def main():
webpages_dir = os.path.join(util.ROOT, 'data/weps2007_data_1.1/traininig/web_pages')
fe = FeatureExtractor()
ff = FeatureFilter()
for name in os.listdir(webpages_dir):
print 'begin clustering %s' % name
reader = FileReader(webpages_dir, name)
description = reader.read_description()
pc = PersonCorpus(name)
fm = FeatureMapper()
for rank in description:
doc_meta = {}
html_path = os.path.join(webpages_dir, name, 'raw', rank, 'index.html')
content = text_extract(html_path)
features, wordcount = fe.extract(content)
doc_meta['word_num'] = wordcount
good_features = ff.filter(features)
vec = FeatureVector(good_features, fm)
pc.add_vector(vec)
pc.compute_matrix()
pc.dump_matrix()
class RealWorldTester(object):
def __init__(self, fileloc, clf, ss=None):
self.clf = clf
self.standardizer = ss
self.file_loc = fileloc
self.file_handler = FileHandler(self.file_loc)
self.file_handler.set_file_extensions((".wav"))
self.file_handler.create_all_file_list()
self.file_handler.split_train_test()
self.extractor = FeatureExtractor()
def classify_clip(self):
y = []
for tf in self.file_handler.train_files:
cur_clips = self.file_handler.file_to_clips(tf, short=False)
for clip in cur_clips:
self.extractor.set_clip(clip)
features = np.reshape(self.extractor.extract(), (1, -1))
features = self.standardizer.transform(features)
pred = self.clf.predict(features)
y.append(pred[0])
return y
def reorder_clip(self, classification):
fs, raw = wavfile.read(self.file_handler.train_files[0])
raw = raw / (2**15 - 1)
sil = []
noise = []
music = []
impure = []
pure = []
count = 0
sr = fs
for c in classification:
if c == 's':
sil.extend(raw[count * sr:(count + 1) * sr])
elif c == 'n':
noise.extend(raw[count * sr:(count + 1) * sr])
elif c == 'm':
music.extend(raw[count * sr:(count + 1) * sr])
elif c == 'i':
impure.extend(raw[count * sr:(count + 1) * sr])
elif c == 'p':
pure.extend(raw[count * sr:(count + 1) * sr])
count += 1
rearranged = sil + noise + music + impure + pure
rearranged = np.asarray(rearranged, dtype="float32")
wavfile.write("rearranged.wav", fs, rearranged)
def plot_classification(self):
classification = self.classify_clip()
class_colors = ["#4286f4", "#ff3855", "#92ff5b", "#f4c60e", "#111111"]
p_sp = []
im_sp = []
music = []
noise = []
sil = []
count = 0
for c in classification:
if c == 'p':
p_sp.append(count)
elif c == 'i':
im_sp.append(count)
elif c == 'm':
music.append(count)
elif c == 'n':
noise.append(count)
elif c == 's':
sil.append(count)
count += 1
print(sil)
print(noise)
print(music)
print(im_sp)
print(p_sp)
self.reorder_clip(classification)
plt.figure()
plt.plot(sil, [0] * len(sil), 'ko')
plt.plot(noise, [1] * len(noise), 'yo')
plt.plot(music, [2] * len(music), 'ro')
plt.plot(im_sp, [3] * len(im_sp), 'bo')
plt.plot(p_sp, [4] * len(p_sp), 'go')
plt.xlabel("Time (seconds)")
plt.title("God's Plan (30 Seconds)")
plt.yticks(
[0, 1, 2, 3, 4],
['silence', 'noise', 'music', 'impure speech', 'pure speech'])
plt.show()
args = parser.parse_args()
if not os.path.exists(args.extractor):
print "Path to extractor '%s' not found" % args.extractor
sys.exit(-1)
if args.path_to_audio is None:
args.path_to_audio = "audio/"+args.collection_name
if args.path_to_audio.endswith("/"):
args.path_to_audio = args.path_to_audio[:-1]
if not os.path.exists(args.path_to_audio):
print "Path to audio '%s' not found" % args.path_to_audio
sys.exit(-1)
if args.path_to_features is None:
if not os.path.exists("features"):
os.mkdir("features")
args.path_to_features = "features/"+args.collection_name
if args.path_to_features.endswith("/"):
args.path_to_features = args.path_to_features[:-1]
if not os.path.exists(args.path_to_features[:args.path_to_features.rfind("/")]):
print "Path to features '%s' not found" % args.path_to_features
sys.exit(-1)
print args
extractor = FeatureExtractor(args.extractor)
extractor.extract(args.path_to_audio, args.path_to_features, args.audio_filetype, args.replace_features)
origins = [] cameras = [] D4prev = np.array([0, 0, 0, 0]).reshape(4, 1) col_prev = np.array([0, 0, 0]).reshape(1, 3) q = Queue() mapa = Map() p = Process(target=draw_process, args=(q,)) p.start() ### INIT FIRST FRAME im = cv2.imread(dir + im_list[0]) Fr = Frame(im) Fr.pose = np.eye(4) # im = undistort(im) Fr.add_feature(feate.extract(Fr.im)) mapa.append_frame(Fr) cameras.append(np.eye(4)) ##### Process another frame for it in range(1, len(im_list)): # for imname in im_list: im = cv2.imread(dir + im_list[it]) Fr = Frame(im) # im = undistort(im) Fr.add_feature(feate.extract(Fr.im)) mapa.append_frame(Fr) idx1, idx2, D4, pts2 = feate.estimate_pose(*(mapa.get_two_back_frame())) D4 = mapa.frames[-2].pose @ D4.T
if __name__ == "__main__":
dir = "/home/sviat/Documents/Datasets/kitti/2011_09_26/2011_09_26_drive_0009_sync/image_00/data/"
# dir = "/home/sviatoslavpovod/Downloads/mav0/cam0/data/"
im_list = sorted(os.listdir(dir))
feate = FeatureExtractor(K)
f1 = 0
RTprev = np.eye(4)
origins = []
D4prev = np.array([0, 0, 0]).reshape(3, 1)
im_prev = 0
while True:
for imname in im_list:
im = cv2.imread(dir + imname)
f2 = feate.extract(im)
if f1 != 0:
## 2D points on image
pts2, pts1 = feate.matches_frame(f1, f2)
## R, T between cameras
R, T = feate.getRT(pts1, pts2)
## 3D points
D4 = feate.get3D(R, T, pts1.T, pts2.T).T
D4 = D4[:, :3] / D4[:, 3:4]
mask = D4[:, 2] > 0.05
D4 = D4[mask]
if not os.path.exists(args.extractor):
print "Path to extractor '%s' not found" % args.extractor
sys.exit(-1)
if args.path_to_audio is None:
args.path_to_audio = "audio/" + args.collection_name
if args.path_to_audio.endswith("/"):
args.path_to_audio = args.path_to_audio[:-1]
if not os.path.exists(args.path_to_audio):
print "Path to audio '%s' not found" % args.path_to_audio
sys.exit(-1)
if args.path_to_features is None:
if not os.path.exists("features"):
os.mkdir("features")
args.path_to_features = "features/" + args.collection_name
if args.path_to_features.endswith("/"):
args.path_to_features = args.path_to_features[:-1]
if not os.path.exists(
args.path_to_features[:args.path_to_features.rfind("/")]):
print "Path to features '%s' not found" % args.path_to_features
sys.exit(-1)
print args
extractor = FeatureExtractor(args.extractor)
extractor.extract(args.path_to_audio, args.path_to_features,
args.audio_filetype, args.replace_features)
