def cluster_images(self):
image.LOAD_TRUNCATED_IMAGES = True
model = NNModel(weights='imagenet', include_top=False)
filelist = glob.glob(os.path.join(self.org_images, '*.jpg'))
filelist.sort()
featurelist = []
for i, imagepath in enumerate(filelist):
info = "Progress {curr}/{total}".format(curr=i,
total=len(filelist))
print("\r" + info, end="")
# noinspection PyBroadException
try:
img = image.load_img(imagepath, target_size=(224, 224))
img_data = image.img_to_array(img)
img_data = np.expand_dims(img_data, axis=0)
img_data = preprocess_input(img_data)
features = np.array(model.predict(img_data, batch_size=1000))
featurelist.append(features.flatten())
except:
continue
# Clustering
to_fit = np.array(featurelist)
kmeans = KMeans(n_clusters=self.k, random_state=0,
verbose=1).fit(to_fit)
# This is a computation heavy task so I'm copying the images renamed according to cluster for the next time.
try:
os.makedirs(self.cluster_home)
except OSError:
pass
for i, m in enumerate(kmeans.labels_):
shutil.copy(
filelist[i], self.cluster_home + str(m) + "_" +
os.path.basename(filelist[i]))
return kmeans
framedur = time.time()
for batchframeNum in range(0, 1000):
s = proc.stdout.read(nbytes)
if len(s) == nbytes:
result = np.frombuffer(s, dtype='uint8')
result.shape = MODLE_INPUT_DIMS + (-1, )
frameBatch.append(result)
if cv2.waitKey(1) == ord('q'):
run = False
framedur = time.time() - framedur
if len(frameBatch) > 0:
x = np.array(frameBatch)
x = preprocess_input(x)
preddur = time.time()
pred_features_batch = model.predict(x)
pred_features_batch.shape = (pred_features_batch.shape[0], -1)
preddur = time.time() - preddur
lastAccepted = False
for result, pred_features in zip(frameBatch, pred_features_batch):
frameNum += 1
timeStamp = frameNum * (1 / RATE)
total += 1
if lastAccepted:
lastAccepted = False
skipsize += 1
continue
