uncached label removal
This commit is contained in:
Glenn Jocher
parent
b1d385a8de
commit
15f1343dfc
|
|
@ -257,7 +257,7 @@ class LoadStreams: # multiple IP or RTSP cameras
|
|||
|
||||
class LoadImagesAndLabels(Dataset): # for training/testing
|
||||
def __init__(self, path, img_size=416, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
|
||||
cache_labels=True, cache_images=False, single_cls=False):
|
||||
cache_images=False, single_cls=False):
|
||||
path = str(Path(path)) # os-agnostic
|
||||
assert os.path.isfile(path), 'File not found %s. See %s' % (path, help_url)
|
||||
with open(path, 'r') as f:
|
||||
|
|
@ -315,71 +315,69 @@ class LoadImagesAndLabels(Dataset): # for training/testing
|
|||
|
||||
self.batch_shapes = np.ceil(np.array(shapes) * img_size / 64.).astype(np.int) * 64
|
||||
|
||||
# Preload labels (required for weighted CE training)
|
||||
# Cache labels
|
||||
self.imgs = [None] * n
|
||||
self.labels = [None] * n
|
||||
if cache_labels or image_weights: # cache labels for faster training
|
||||
self.labels = [np.zeros((0, 5))] * n
|
||||
extract_bounding_boxes = False
|
||||
create_datasubset = False
|
||||
pbar = tqdm(self.label_files, desc='Caching labels')
|
||||
nm, nf, ne, ns, nd = 0, 0, 0, 0, 0 # number missing, found, empty, datasubset, duplicate
|
||||
for i, file in enumerate(pbar):
|
||||
try:
|
||||
with open(file, 'r') as f:
|
||||
l = np.array([x.split() for x in f.read().splitlines()], dtype=np.float32)
|
||||
except:
|
||||
nm += 1 # print('missing labels for image %s' % self.img_files[i]) # file missing
|
||||
continue
|
||||
self.labels = [np.zeros((0, 5), dtype=np.float32)] * n
|
||||
extract_bounding_boxes = False
|
||||
create_datasubset = False
|
||||
pbar = tqdm(self.label_files, desc='Caching labels')
|
||||
nm, nf, ne, ns, nd = 0, 0, 0, 0, 0 # number missing, found, empty, datasubset, duplicate
|
||||
for i, file in enumerate(pbar):
|
||||
try:
|
||||
with open(file, 'r') as f:
|
||||
l = np.array([x.split() for x in f.read().splitlines()], dtype=np.float32)
|
||||
except:
|
||||
nm += 1 # print('missing labels for image %s' % self.img_files[i]) # file missing
|
||||
continue
|
||||
|
||||
if l.shape[0]:
|
||||
assert l.shape[1] == 5, '> 5 label columns: %s' % file
|
||||
assert (l >= 0).all(), 'negative labels: %s' % file
|
||||
assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels: %s' % file
|
||||
if np.unique(l, axis=0).shape[0] < l.shape[0]: # duplicate rows
|
||||
nd += 1 # print('WARNING: duplicate rows in %s' % self.label_files[i]) # duplicate rows
|
||||
if single_cls:
|
||||
l[:, 0] = 0 # force dataset into single-class mode
|
||||
self.labels[i] = l
|
||||
nf += 1 # file found
|
||||
if l.shape[0]:
|
||||
assert l.shape[1] == 5, '> 5 label columns: %s' % file
|
||||
assert (l >= 0).all(), 'negative labels: %s' % file
|
||||
assert (l[:, 1:] <= 1).all(), 'non-normalized or out of bounds coordinate labels: %s' % file
|
||||
if np.unique(l, axis=0).shape[0] < l.shape[0]: # duplicate rows
|
||||
nd += 1 # print('WARNING: duplicate rows in %s' % self.label_files[i]) # duplicate rows
|
||||
if single_cls:
|
||||
l[:, 0] = 0 # force dataset into single-class mode
|
||||
self.labels[i] = l
|
||||
nf += 1 # file found
|
||||
|
||||
# Create subdataset (a smaller dataset)
|
||||
if create_datasubset and ns < 1E4:
|
||||
if ns == 0:
|
||||
create_folder(path='./datasubset')
|
||||
os.makedirs('./datasubset/images')
|
||||
exclude_classes = 43
|
||||
if exclude_classes not in l[:, 0]:
|
||||
ns += 1
|
||||
# shutil.copy(src=self.img_files[i], dst='./datasubset/images/') # copy image
|
||||
with open('./datasubset/images.txt', 'a') as f:
|
||||
f.write(self.img_files[i] + '\n')
|
||||
# Create subdataset (a smaller dataset)
|
||||
if create_datasubset and ns < 1E4:
|
||||
if ns == 0:
|
||||
create_folder(path='./datasubset')
|
||||
os.makedirs('./datasubset/images')
|
||||
exclude_classes = 43
|
||||
if exclude_classes not in l[:, 0]:
|
||||
ns += 1
|
||||
# shutil.copy(src=self.img_files[i], dst='./datasubset/images/') # copy image
|
||||
with open('./datasubset/images.txt', 'a') as f:
|
||||
f.write(self.img_files[i] + '\n')
|
||||
|
||||
# Extract object detection boxes for a second stage classifier
|
||||
if extract_bounding_boxes:
|
||||
p = Path(self.img_files[i])
|
||||
img = cv2.imread(str(p))
|
||||
h, w = img.shape[:2]
|
||||
for j, x in enumerate(l):
|
||||
f = '%s%sclassifier%s%g_%g_%s' % (p.parent.parent, os.sep, os.sep, x[0], j, p.name)
|
||||
if not os.path.exists(Path(f).parent):
|
||||
os.makedirs(Path(f).parent) # make new output folder
|
||||
# Extract object detection boxes for a second stage classifier
|
||||
if extract_bounding_boxes:
|
||||
p = Path(self.img_files[i])
|
||||
img = cv2.imread(str(p))
|
||||
h, w = img.shape[:2]
|
||||
for j, x in enumerate(l):
|
||||
f = '%s%sclassifier%s%g_%g_%s' % (p.parent.parent, os.sep, os.sep, x[0], j, p.name)
|
||||
if not os.path.exists(Path(f).parent):
|
||||
os.makedirs(Path(f).parent) # make new output folder
|
||||
|
||||
b = x[1:] * [w, h, w, h] # box
|
||||
b[2:] = b[2:].max() # rectangle to square
|
||||
b[2:] = b[2:] * 1.3 + 30 # pad
|
||||
b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)
|
||||
b = x[1:] * [w, h, w, h] # box
|
||||
b[2:] = b[2:].max() # rectangle to square
|
||||
b[2:] = b[2:] * 1.3 + 30 # pad
|
||||
b = xywh2xyxy(b.reshape(-1, 4)).ravel().astype(np.int)
|
||||
|
||||
b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image
|
||||
b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
|
||||
assert cv2.imwrite(f, img[b[1]:b[3], b[0]:b[2]]), 'Failure extracting classifier boxes'
|
||||
else:
|
||||
ne += 1 # print('empty labels for image %s' % self.img_files[i]) # file empty
|
||||
# os.system("rm '%s' '%s'" % (self.img_files[i], self.label_files[i])) # remove
|
||||
b[[0, 2]] = np.clip(b[[0, 2]], 0, w) # clip boxes outside of image
|
||||
b[[1, 3]] = np.clip(b[[1, 3]], 0, h)
|
||||
assert cv2.imwrite(f, img[b[1]:b[3], b[0]:b[2]]), 'Failure extracting classifier boxes'
|
||||
else:
|
||||
ne += 1 # print('empty labels for image %s' % self.img_files[i]) # file empty
|
||||
# os.system("rm '%s' '%s'" % (self.img_files[i], self.label_files[i])) # remove
|
||||
|
||||
pbar.desc = 'Caching labels (%g found, %g missing, %g empty, %g duplicate, for %g images)' % (
|
||||
nf, nm, ne, nd, n)
|
||||
assert nf > 0, 'No labels found in %s. See %s' % (os.path.dirname(file) + os.sep, help_url)
|
||||
pbar.desc = 'Caching labels (%g found, %g missing, %g empty, %g duplicate, for %g images)' % (
|
||||
nf, nm, ne, nd, n)
|
||||
assert nf > 0, 'No labels found in %s. See %s' % (os.path.dirname(file) + os.sep, help_url)
|
||||
|
||||
# Cache images into memory for faster training (WARNING: large datasets may exceed system RAM)
|
||||
if cache_images: # if training
|
||||
|
|
@ -432,7 +430,7 @@ class LoadImagesAndLabels(Dataset): # for training/testing
|
|||
# Load labels
|
||||
labels = []
|
||||
x = self.labels[index]
|
||||
if x is not None and x.size > 0:
|
||||
if x.size > 0:
|
||||
# Normalized xywh to pixel xyxy format
|
||||
labels = x.copy()
|
||||
labels[:, 1] = ratio[0] * w * (x[:, 1] - x[:, 3] / 2) + pad[0] # pad width
|
||||
|
|
@ -502,9 +500,9 @@ def load_image(self, index):
|
|||
# loads 1 image from dataset, returns img, original hw, resized hw
|
||||
img = self.imgs[index]
|
||||
if img is None: # not cached
|
||||
img_path = self.img_files[index]
|
||||
img = cv2.imread(img_path) # BGR
|
||||
assert img is not None, 'Image Not Found ' + img_path
|
||||
path = self.img_files[index]
|
||||
img = cv2.imread(path) # BGR
|
||||
assert img is not None, 'Image Not Found ' + path
|
||||
h0, w0 = img.shape[:2] # orig hw
|
||||
r = self.img_size / max(h0, w0) # resize image to img_size
|
||||
if r < 1 or (self.augment and r != 1): # always resize down, only resize up if training with augmentation
|
||||
|
|
@ -557,24 +555,15 @@ def load_mosaic(self, index):
|
|||
padw = x1a - x1b
|
||||
padh = y1a - y1b
|
||||
|
||||
# Load labels
|
||||
label_path = self.label_files[index]
|
||||
if os.path.isfile(label_path):
|
||||
x = self.labels[index]
|
||||
if x is None: # labels not preloaded
|
||||
with open(label_path, 'r') as f:
|
||||
x = np.array([x.split() for x in f.read().splitlines()], dtype=np.float32)
|
||||
|
||||
if x.size > 0:
|
||||
# Normalized xywh to pixel xyxy format
|
||||
labels = x.copy()
|
||||
labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padw
|
||||
labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + padh
|
||||
labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padw
|
||||
labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + padh
|
||||
else:
|
||||
labels = np.zeros((0, 5), dtype=np.float32)
|
||||
labels4.append(labels)
|
||||
# Labels
|
||||
x = self.labels[index]
|
||||
labels = x.copy()
|
||||
if x.size > 0: # Normalized xywh to pixel xyxy format
|
||||
labels[:, 1] = w * (x[:, 1] - x[:, 3] / 2) + padw
|
||||
labels[:, 2] = h * (x[:, 2] - x[:, 4] / 2) + padh
|
||||
labels[:, 3] = w * (x[:, 1] + x[:, 3] / 2) + padw
|
||||
labels[:, 4] = h * (x[:, 2] + x[:, 4] / 2) + padh
|
||||
labels4.append(labels)
|
||||
|
||||
# Concat/clip labels
|
||||
if len(labels4):
|
||||
|
|
@ -585,10 +574,10 @@ def load_mosaic(self, index):
|
|||
# Augment
|
||||
# img4 = img4[s // 2: int(s * 1.5), s // 2:int(s * 1.5)] # center crop (WARNING, requires box pruning)
|
||||
img4, labels4 = random_affine(img4, labels4,
|
||||
degrees=self.hyp['degrees'] * 1,
|
||||
translate=self.hyp['translate'] * 1,
|
||||
scale=self.hyp['scale'] * 1,
|
||||
shear=self.hyp['shear'] * 1,
|
||||
degrees=self.hyp['degrees'],
|
||||
translate=self.hyp['translate'],
|
||||
scale=self.hyp['scale'],
|
||||
shear=self.hyp['shear'],
|
||||
border=-s // 2) # border to remove
|
||||
|
||||
return img4, labels4
|
||||
|
|
@ -688,7 +677,7 @@ def random_affine(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10,
|
|||
area = w * h
|
||||
area0 = (targets[:, 3] - targets[:, 1]) * (targets[:, 4] - targets[:, 2])
|
||||
ar = np.maximum(w / (h + 1e-16), h / (w + 1e-16)) # aspect ratio
|
||||
i = (w > 4) & (h > 4) & (area / (area0 + 1e-16) > 0.2) & (ar < 10)
|
||||
i = (w > 4) & (h > 4) & (area / (area0 * s + 1e-16) > 0.2) & (ar < 10)
|
||||
|
||||
targets = targets[i]
|
||||
targets[:, 1:5] = xy[i]
|
||||
|
|
|
|||
Loading…
Reference in New Issue