ValueError: need at least one array to concatenate
I am having issues with
ValueError: need at least one array to concatenate
Below is the whole error message.
Training mode
Traceback (most recent call last):
File "bcf.py", line 342, in <module>
bcf.train()
File "bcf.py", line 321, in train
self._learn_codebook()
File "bcf.py", line 142, in _learn_codebook
feats_sc = np.concatenate(feats_sc, axis=1).transpose()
ValueError: need at least one array to concatenate
Below is the area of the problem.
def _learn_codebook(self):
MAX_CFS = 800 # max number of contour fragments per image; if above, sample randomly
CLUSTERING_CENTERS = 1500
feats_sc = []
for image in self.data.values():
feats = image['cfs']
feat_sc = feats[1]
if feat_sc.shape[1] > MAX_CFS:
# Sample MAX_CFS from contour fragments
rand_indices = np.random.permutation(feat_sc.shape[1])
feat_sc = feat_sc[:, rand_indices[:MAX_CFS]]
feats_sc.append(feat_sc)
feats_sc = np.concatenate(feats_sc, axis=1).transpose()
print("Running KMeans...")
self.kmeans = sklearn.cluster.KMeans(min(CLUSTERING_CENTERS, feats_sc.shape[0]), n_jobs=-1, algorithm='elkan').fit(feats_sc)
print("Saving codebook...")
self._save_kmeans(self.kmeans)
return self.kmeans
Below is the complete CLASS
class BCF():
def __init__(self):
self.DATA_DIR = "/Users/minniemouse/TRAIN/bcf-master5/data/cuauv/"
self.PERC_TRAINING_PER_CLASS = 0.5
self.CODEBOOK_FILE = "codebook.data"
self.CLASSIFIER_FILE = "classifier"
self.LABEL_TO_CLASS_MAPPING_FILE = "labels_to_classes.data"
self.classes = defaultdict(list)
self.data = defaultdict(dict)
self.counter = defaultdict(int)
self.kmeans = None
self.clf = None
self.label_to_class_mapping = None
def _load_classes(self):
for dir_name, subdir_list, file_list in os.walk(self.DATA_DIR):
if subdir_list:
continue
for f in sorted(file_list, key=hash):
self.classes[dir_name.split('/')[-1]].append(os.path.join(dir_name, f))
def _load_training(self):
for cls in self.classes:
images = self.classes[cls]
for image in images[:int(len(images) * self.PERC_TRAINING_PER_CLASS)]:
image_id = self._get_image_identifier(cls)
self.data[image_id]['image'] = cv2.imread(image, cv2.IMREAD_GRAYSCALE)
if self.data[image_id]['image'] is None:
print("Failed to load " + image)
def _load_testing(self):
for cls in self.classes:
images = self.classes[cls]
for image in images[int(len(images) * self.PERC_TRAINING_PER_CLASS):]:
image_id = self._get_image_identifier(cls)
self.data[image_id]['image'] = cv2.imread(image, cv2.IMREAD_GRAYSCALE)
if self.data[image_id]['image'] is None:
print("Failed to load " + image)
def _load_single(self, image):
# Load single image data
self.data.clear()
image_id = self._get_image_identifier(None)
self.data[image_id]['image'] = image
def _save_label_to_class_mapping(self):
self.label_to_class_mapping = {hash(cls): cls for cls in self.classes}
with open(self.LABEL_TO_CLASS_MAPPING_FILE, 'wb') as out_file:
pickle.dump(self.label_to_class_mapping, out_file, -1)
def _load_label_to_class_mapping(self):
if self.label_to_class_mapping is None:
with open(self.LABEL_TO_CLASS_MAPPING_FILE, 'rb') as in_file:
self.label_to_class_mapping = pickle.load(in_file)
return self.label_to_class_mapping
def _normalize_shapes(self):
for (cls, idx) in self.data.keys():
image = self.data[(cls, idx)]['image']
# Remove void space
y, x = np.where(image > 50)
max_y = y.max()
min_y = y.min()
max_x = x.max()
min_x = x.min()
trimmed = image[min_y:max_y, min_x:max_x] > 50
trimmed = trimmed.astype('uint8')
trimmed[trimmed > 0] = 255
self.data[(cls, idx)]['normalized_image'] = trimmed
def _extract_cf(self):
for (cls, idx) in self.data.keys():
image = self.data[(cls, idx)]['normalized_image']
images,contours, _ = cv2.findContours(image, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
contour = sorted(contours, key=len)[-1]
mat = np.zeros(image.shape, np.int8)
cv2.drawContours(mat, [contour], -1, (255, 255, 255))
#self.show(mat)
MAX_CURVATURE = 1.5
N_CONTSAMP = 50
N_PNTSAMP = 10
C = None
for pnt in contour:
if C is None:
C = np.array([[pnt[0][0], pnt[0][1]]])
else:
C = np.append(C, [[pnt[0][0], pnt[0][1]]], axis=0)
cfs = self._extr_raw_points(C, MAX_CURVATURE, N_CONTSAMP, N_PNTSAMP)
tmp = mat.copy()
for cf in cfs:
for pnt in cf:
cv2.circle(tmp, (pnt[0], pnt[1]), 2, (255, 0, 0))
#self.show(tmp)
num_cfs = len(cfs)
print("Extracted %s points" % (num_cfs))
feat_sc = np.zeros((300, num_cfs))
xy = np.zeros((num_cfs, 2))
for i in range(num_cfs):
cf = cfs[i]
sc, _, _, _ = shape_context(cf)
# shape context is 60x5 (60 bins at 5 reference points)
sc = sc.flatten(order='F')
sc /= np.sum(sc) # normalize
feat_sc[:, i] = sc
# shape context descriptor sc for each cf is 300x1
# save a point at the midpoint of the contour fragment
xy[i, 0:2] = cf[np.round(len(cf) / 2. - 1).astype('int32'), :]
sz = image.shape
self.data[(cls, idx)]['cfs'] = (cfs, feat_sc, xy, sz)
def _learn_codebook(self):
MAX_CFS = 800 # max number of contour fragments per image; if above, sample randomly
CLUSTERING_CENTERS = 1500
feats_sc = []
for image in self.data.values():
feats = image['cfs']
feat_sc = feats[1]
if feat_sc.shape[1] > MAX_CFS:
# Sample MAX_CFS from contour fragments
rand_indices = np.random.permutation(feat_sc.shape[1])
feat_sc = feat_sc[:, rand_indices[:MAX_CFS]]
feats_sc.append(feat_sc)
feats_sc = np.concatenate(feats_sc, axis=1).transpose()
print("Running KMeans...")
self.kmeans = sklearn.cluster.KMeans(min(CLUSTERING_CENTERS, feats_sc.shape[0]), n_jobs=-1, algorithm='elkan').fit(feats_sc)
print("Saving codebook...")
self._save_kmeans(self.kmeans)
return self.kmeans
I have read through the various posts on ValueError already described, but I am not having much luck on figuring it out. I have now attached the CLASS and full error message information.
Please, can someone point out what I am missing?
Thank you
Answer
the problem comes from the lenght of your array. Check if your array/list is longer than to 0 print(len(feats_sc)).
Don't forget to checkout the documentation numpy.concatenate — NumPy v1.16 Manual