def map(self, key, value):
"""
Args:
key: Image name
value: Image as jpeg byte data
Yields:
A tuple in the form of (key, value)
key: (Image name, (x, y, w, h))
value: face image (.png)
"""
try:
image = imfeat.image_fromstring(value, {
'type': 'numpy',
'dtype': 'uint8',
'mode': 'gray'
})
image_color = imfeat.image_fromstring(value, {
'type': 'numpy',
'dtype': 'uint8',
'mode': 'bgr'
})
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
return
faces = _detect_faces(image, self._cascade)
for x, y, w, h in faces:
yield (key, (x, y, w, h)), imfeat.image_tostring(
image_color[y:y + h, x:x + w, :], '.png')
def _verify_image(image_binary):
import imfeat
try:
imfeat.image_fromstring(image_binary)
except IOError:
return False
return True
def test_tostring(self):
for fn in ['lena.jpg', 'lena.pgm', 'lena.ppm']:
for i in load_images(fn):
for ext in ['jpeg', 'png']:
o = imfeat.image_tostring(i, ext)
o2 = imfeat.image_tostring(imfeat.image_fromstring(imfeat.image_tostring(i, ext)), ext)
if ext == 'png':
np.testing.assert_equal(o, o2)
s = imfeat.image_fromstring(o)
s2 = imfeat.image_fromstring(o2)
# No more than 9% of the pixels differ by more than 3
self.assertLess(np.mean(np.abs(s - s2) > 3), .09)
def test_tostring(self):
for fn in ['lena.jpg', 'lena.pgm', 'lena.ppm']:
for i in load_images(fn):
for ext in ['jpeg', 'png']:
o = imfeat.image_tostring(i, ext)
o2 = imfeat.image_tostring(imfeat.image_fromstring(imfeat.image_tostring(i, ext)), ext)
if ext == 'png':
np.testing.assert_equal(o, o2)
s = imfeat.image_fromstring(o)
s2 = imfeat.image_fromstring(o2)
# No more than 9% of the pixels differ by more than 3
self.assertLess(np.mean(np.abs(s - s2) > 3), .09)
def map(self, key, value):
"""
Args:
key: Image name
value: Image as jpeg byte data
Yields:
A tuple in the form of (key, value)
key: Constant dummy value
value: (l2sqr_dist, key, value)
"""
try:
image = imfeat.resize_image(
imfeat.image_fromstring(value, {
'type': 'numpy',
'mode': 'bgr',
'dtype': 'uint8'
}), 100, 100)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
return
# Distance metric
diff = image - self.target_image
dist = np.sum(diff * diff)
yield '', (dist, key, value)
def map(self, key, value):
"""
Args:
key: Image name
value: Image as jpeg byte data
Yields:
A tuple in the form of (key, value)
key: Constant dummy value
value: (l2sqr_dist, value)
"""
try:
image = imfeat.resize_image(imfeat.image_fromstring(value, {'type': 'numpy', 'mode': 'bgr', 'dtype': 'uint8'}),
100, 100)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
return
# Distance metric
diff = image - self.target_image
dist = np.sum(diff * diff)
# Output
if dist < self.min_dist:
self.min_dist = dist
self.min_key = key
self.min_value = value
def main():
exemplars = sorted(pickle.load(open('exemplars.pkl')), key=lambda x: x[0][2], reverse=True)[:100]
with open('exemplars_best.pkl', 'w') as fp:
pickle.dump(exemplars, fp, -1)
hdfs_output = 'exemplarbank/output/%s/' % '1341790878.92'
#hadoopy.launch_frozen('/user/brandyn/aladdin_results/keyframe/9/keyframe', hdfs_output + 'frame_pred', 'predict_video_frame.py', cmdenvs=['EXEMPLARS=exemplars_best.pkl', 'CELL_SKIP=1'], remove_output=True, files=['exemplars_best.pkl'])
local_out = 'frame_preds/'
try:
shutil.rmtree(local_out)
except OSError:
pass
os.makedirs(local_out)
for num, (data, (pyramid, num_boxes)) in enumerate(hadoopy.readtb(hdfs_output + 'frame_pred')):
if np.sum(pyramid):
pyramid_norm = pyramid / float(num_boxes)
pyramid_prob = np.sqrt(pyramid / float(np.max(pyramid)))
p = np.sum(pyramid_norm)
f = imfeat.image_fromstring(data['frame'])
pyramid_prob_frame = cv2.resize(pyramid_prob, (f.shape[1], f.shape[0]))
pyramid_prob_frame_color = COLORS[(pyramid_prob_frame * 255).astype(np.int), :]
alpha = .5
beta = alpha * pyramid_prob_frame
beta = beta.reshape((beta.shape[0], beta.shape[1], 1))
else:
beta = 0.
f = ((1 - beta) * f + beta * pyramid_prob_frame_color).astype(np.uint8)
print(p)
open(local_out + '%f-%d.jpg' % (p, num), 'w').write(imfeat.image_tostring(f, 'jpg'))
def annotation_masks_to_hbase(self):
import redis
import ast
import imfeat
import cv2
r = redis.StrictRedis(port=6381, db=6)
responses = [r.hgetall(x) for x in r.keys()]
print('Total Responses[%d]' % len(responses))
image_class_segments = {} # [row][class_name] = segments
for x in responses:
if 'user_data' in x:
x['user_data'] = ast.literal_eval(x['user_data'])
if x['user_data']['segments']:
row_key = x['image']
image_class_segments.setdefault(row_key, {}).setdefault(x['user_data']['name'], []).append(x['user_data']['segments'])
for row_key, class_segments in image_class_segments.items():
columns = dict((x, y.value) for x, y in self.hb.getRowWithColumns(self.images_table, row_key, [self.image_column, self.superpixel_column])[0].columns.items())
image = imfeat.image_fromstring(columns[self.image_column])
segments = json.loads(columns[self.superpixel_column])
class_masks = {}
class_masks = np.zeros((image.shape[0], image.shape[1], self.texton_num_classes))
for name, user_segment_groups in class_segments.items():
cur_mask = np.zeros(image.shape[:2], dtype=np.uint8)
for user_segment_group in user_segment_groups:
for user_segment in user_segment_group:
hull = segments[user_segment]
hull = np.asarray(hull).astype(np.int32).reshape(1, -1, 2)
mask_color = 255
cv2.drawContours(cur_mask, hull, -1, mask_color, -1)
cv2.drawContours(cur_mask, hull, -1, mask_color, 2)
class_masks[:, :, self.texton_classes[name]['mask_num']] = cur_mask / 255.
class_masks_ser = picarus.api.np_tostring(class_masks)
print('Storing row [%s]' % repr(row_key))
self.hb.mutateRow(self.images_table, row_key, [hadoopy_hbase.Mutation(column=self.masks_gt_column, value=class_masks_ser)])
def inner(num_rows, **kw):
row_cols = hadoopy_hbase.scanner(self.hb, self.images_table,
columns=[self.image_column, self.indoor_class_column], **kw)
for x, (_, cols) in enumerate(row_cols):
print(repr(x))
if x >= num_rows:
break
yield cols[self.indoor_class_column], imfeat.image_fromstring(cols[self.image_column])
def _map(self, row, image_binary):
try:
image = imfeat.image_fromstring(image_binary)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
out = self.sp(image, 25)
hulls = self.sp.label_image_to_contours(out, 1.)
yield row, json.dumps(hulls, separators=(',', ':'))
def map(self, image_id, image_binary):
try:
boxes = self.image_box_fns[image_id]
except KeyError:
pass
else:
image = imfeat.image_fromstring(image_binary)
size_array = np.array([
image.shape[0], image.shape[1], image.shape[0], image.shape[1]
])
scale_boxes = {}
for box, fn in boxes:
fbox = size_array * box
scale = int(
np.round(np.log2(
(fbox[2] - fbox[0]) / feature.PATCH_SIZE)))
scale_check = int(
np.round(np.log2(
(fbox[3] - fbox[1]) / feature.PATCH_SIZE)))
if scale != scale_check:
raise ValueError('Box is not square.')
scale_boxes.setdefault(scale, []).append((box, fn))
# Order boxes and fn's by scale
for scale in range(max(scale_boxes.keys()) + 1):
if scale > 0:
height, width = np.array(image.shape[:2]) / 2
image = image[:height * 2, :width * 2, :]
if min(width, height) < 1:
raise ValueError('Image is too small')
image = cv2.resize(image, (width, height))
if image is None: # NOTE(brandyn): It is too small
raise ValueError('Image is too small')
try:
boxes = scale_boxes[scale]
except KeyError:
continue
size_array = np.array([
image.shape[0], image.shape[1], image.shape[0],
image.shape[1]
])
for box, fn in boxes:
box = np.round(size_array * box).astype(np.int)
print(box)
if self.type == 'image':
image_box = np.ascontiguousarray(
image[box[0]:box[2], box[1]:box[3], :])
yield fn, imfeat.image_tostring(image_box, 'png')
elif self.type == 'feature':
image_box = np.ascontiguousarray(
image[box[0]:box[2], box[1]:box[3], :])
yield fn, feature.compute_patch(image_box)
elif self.type == 'box':
image2 = image.copy()
cv2.rectangle(image2, (box[1], box[0]),
(box[3], box[2]), (0, 255, 0), 4)
yield fn, imfeat.image_tostring(image2, 'jpg')
else:
raise ValueError(self.type)
def map(self, image_id, image_binary):
image = resize(imfeat.image_fromstring(image_binary))
print(image.shape)
st = time.time()
box_num = -1
for box_num, (box, f) in enumerate(feature.image_patch_features_dense(image, normalize_box=True)):
yield (image_id, box.tolist()), np.dot(self.coefs, f.reshape((f.size, 1))).ravel() + self.intercepts
hadoopy.counter('stats', 'num_boxes', box_num + 1)
print('ImageTime[%f]' % (time.time() - st))
def reduce(self, key, values):
"""
For this to work we need a modified partitioner on the substring before the first tab.
This method operates on a single tile at level 0, and more tiles at higher zoom levels (4x each level).
Args:
key: (tile_id, subtile_id)
values: Iterator of [dist, images] where images are power of 2 JPEG
images in descending order by size
Yields:
Tuple of (key, value) where
key: Tile name
value: JPEG Image Data
"""
# Select minimum distance image, throw away score, and order images from smallest to largest powers of 2
self._sub_tiles[key] = min(values, key=lambda x: x[0])[1][::-1]
# As the images were JPEG, we need to make them arrays again
self._sub_tiles[key] = [
imfeat.image_fromstring(x) for x in self._sub_tiles[key]
]
# If we don't have all of the necessary subtiles.
if len(self._sub_tiles) != _subtiles_per_tile:
return
self._verify_subtile_keys()
for level in range(_levels):
# Each image is smaller than the tile
scale = 2**level
num_tiles = scale * scale
subtiles_per_tile_len = _subtiles_per_tile_length / scale
subtiles_per_tile = subtiles_per_tile_len**2
subtile_len = _subtile_length * scale
cur_subtiles = [(self._find_output(key, scale,
subtiles_per_tile_len,
subtile_len), images[level])
for key, images in self._sub_tiles.items()]
cur_subtiles.sort(key=lambda x: x[0])
cur_tile = np.zeros((_tile_length, _tile_length, 3),
dtype=np.uint8)
assert len(cur_subtiles) / subtiles_per_tile == num_tiles
cur_outtile = None
for subtile_ind, ((xouttile, youttile, xoffset, yoffset),
image) in enumerate(cur_subtiles):
if cur_outtile is None:
cur_outtile = (xouttile, youttile)
assert cur_outtile == (xouttile, youttile)
#cur_tile.paste(image, (xoffset, yoffset)) # TODO Suspect
cur_tile[yoffset:yoffset + image.shape[0],
xoffset:xoffset + image.shape[1], :] = image
if not (subtile_ind + 1) % subtiles_per_tile:
tile_name = '%d_%d_%d.jpg' % (level, xouttile, youttile)
yield tile_name, imfeat.image_tostring(cur_tile, 'jpg')
cur_tile = np.zeros((_tile_length, _tile_length, 3),
dtype=np.uint8)
cur_outtile = None
self._sub_tiles = {}
def map(self, name, image_or_data):
if isinstance(image_or_data, str):
try:
image = imfeat.image_fromstring(image_or_data)
except:
hadoopy.counter("DATA_ERRORS", "ImageLoadError")
return
else:
image = image_or_data
yield name, self._feat(image)
def _map(self, row, image_binary):
try:
if not image_binary:
raise ValueError
image = imfeat.image_fromstring(image_binary)
except:
hadoopy.counter('ERROR', 'FEATURE')
print('Error on row[%r]' % row)
else:
yield row, picarus.api.np_tostring(self._feat.compute_feature(image))
def map(self, name, image_or_data):
if isinstance(image_or_data, str):
try:
image = imfeat.image_fromstring(image_or_data)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
return
else:
image = image_or_data
yield name, self._feat(image)
def map(self, key, value):
"""
Args:
key: Image name
value: Image as jpeg byte data
Yields:
A tuple in the form of (key, value)
key: (Image name, (x, y, w, h))
value: face image (.png)
"""
try:
image = imfeat.image_fromstring(value, {'type': 'numpy', 'dtype': 'uint8', 'mode': 'gray'})
image_color = imfeat.image_fromstring(value, {'type': 'numpy', 'dtype': 'uint8', 'mode': 'bgr'})
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
return
faces = _detect_faces(image, self._cascade)
for x, y, w, h in faces:
yield (key, (x, y, w, h)), imfeat.image_tostring(image_color[y:y + h, x:x + w, :], '.png')
def _get_image():
params = dict(bottle.request.params)
try:
data = base64.b64decode(params['image_b64'])
del params['image_b64']
except KeyError:
try:
data = bottle.request.files['image'].file.read()
except KeyError:
raise ValueError('Missing image')
print('ImageData[%s]' % str(data[:25]))
return imfeat.image_fromstring(data), params
def get_content(content_id):
if content_id.endswith('.b16.html'):
return '<img src="/content/%s.jpg" />' % base64.b16decode(content_id[:-9])
image_data = open(base64.b16decode(content_id[:content_id.find('.b16')])).read()
if content_id.endswith('.b16.thumb.jpg'):
try:
return CACHE[content_id]
except KeyError:
out_data = imfeat.image_tostring(imfeat.resize_image(imfeat.image_fromstring(image_data), 200, 200), 'JPEG')
CACHE[content_id] = out_data
return out_data
return image_data
def _get_image():
params = dict(bottle.request.params)
try:
data = base64.b64decode(params['image_b64'])
del params['image_b64']
except KeyError:
try:
data = bottle.request.files['image'].file.read()
except KeyError:
raise ValueError('Missing image')
print('ImageData[%s]' % str(data[:25]))
return imfeat.image_fromstring(data), params
def cluster_points_local(self, **kw):
row_cols = hadoopy_hbase.scanner(self.hb, self.images_table,
columns=[self.image_column], **kw)
feature_func = imfeat.HOGLatent(16)
num_clusters = 100
features = []
for row, columns in row_cols:
image = imfeat.image_fromstring(columns[self.image_column])
features.append(feature_func.compute_dense(image))
features = np.vstack(features)
clusters = sp.cluster.vq.kmeans(features, num_clusters)[0]
print(clusters.shape)
json.dump(clusters.tolist(), open('clusters.js', 'w'))
def cluster_points_local(self, **kw):
row_cols = hadoopy_hbase.scanner(self.hb, self.images_table,
columns=[self.image_column], **kw)
feature_func = imfeat.HOGLatent(16)
num_clusters = 100
features = []
for row, columns in row_cols:
image = imfeat.image_fromstring(columns[self.image_column])
features.append(feature_func.compute_dense(image))
features = np.vstack(features)
clusters = sp.cluster.vq.kmeans(features, num_clusters)[0]
print(clusters.shape)
json.dump(clusters.tolist(), open('clusters.js', 'w'))
def reduce(self, key, values):
"""
For this to work we need a modified partitioner on the substring before the first tab.
This method operates on a single tile at level 0, and more tiles at higher zoom levels (4x each level).
Args:
key: (tile_id, subtile_id)
values: Iterator of [dist, images] where images are power of 2 JPEG
images in descending order by size
Yields:
Tuple of (key, value) where
key: Tile name
value: JPEG Image Data
"""
# Select minimum distance image, throw away score, and order images from smallest to largest powers of 2
self._sub_tiles[key] = min(values, key=lambda x: x[0])[1][::-1]
# As the images were JPEG, we need to make them arrays again
self._sub_tiles[key] = [imfeat.image_fromstring(x) for x in self._sub_tiles[key]]
# If we don't have all of the necessary subtiles.
if len(self._sub_tiles) != _subtiles_per_tile:
return
self._verify_subtile_keys()
for level in range(_levels):
# Each image is smaller than the tile
scale = 2 ** level
num_tiles = scale * scale
subtiles_per_tile_len = _subtiles_per_tile_length / scale
subtiles_per_tile = subtiles_per_tile_len ** 2
subtile_len = _subtile_length * scale
cur_subtiles = [(self._find_output(key, scale, subtiles_per_tile_len, subtile_len), images[level])
for key, images in self._sub_tiles.items()]
cur_subtiles.sort(key=lambda x: x[0])
cur_tile = np.zeros((_tile_length, _tile_length, 3), dtype=np.uint8)
assert len(cur_subtiles) / subtiles_per_tile == num_tiles
cur_outtile = None
for subtile_ind, ((xouttile, youttile, xoffset, yoffset), image) in enumerate(cur_subtiles):
if cur_outtile is None:
cur_outtile = (xouttile, youttile)
assert cur_outtile == (xouttile, youttile)
#cur_tile.paste(image, (xoffset, yoffset)) # TODO Suspect
cur_tile[yoffset:yoffset + image.shape[0], xoffset:xoffset + image.shape[1], :] = image
if not (subtile_ind + 1) % subtiles_per_tile:
tile_name = '%d_%d_%d.jpg' % (level, xouttile, youttile)
yield tile_name, imfeat.image_tostring(cur_tile, 'jpg')
cur_tile = np.zeros((_tile_length, _tile_length, 3), dtype=np.uint8)
cur_outtile = None
self._sub_tiles = {}
def object_rec_parse(self, *args, **kw):
import cv2
try:
for image_fn, objects in self.object_rec_parse_fn(*args, **kw):
yield cv2.imread(image_fn), objects
except NotImplementedError:
import imfeat
try:
for image_url, objects in self.object_rec_parse_url(*args, **kw):
try:
yield imfeat.image_fromstring(urllib.urlopen(image_url).read()), objects
except:
logging.warn('Cannot download/parse [%s], skipping...' % image_url)
except NotImplementedError:
raise NotImplementedError
def replay():
datas = pickle.load(open('results.pkl'))
hs = HBaseCrawlerStore()
import imfeat
for data in datas:
for x in data['result']['items']:
try:
r = requests.get(x['link'], timeout=10)
image = r.content
if r.status_code != 200:
continue
except (requests.exceptions.TooManyRedirects, requests.exceptions.ConnectionError, requests.exceptions.Timeout):
continue
try:
imfeat.image_fromstring(image)
except IOError:
continue
query = data['query'].encode('utf-8')
class_name = data['query'].encode('utf-8')[:-5].lower()
source = 'google'
snippet = x['snippet'].encode('utf-8')
url = x['link'].encode('utf-8')
hs.store(image, class_name, source, query=query, snippet=snippet, url=url)
print(class_name)
def map(self, name, image_data):
try:
image = imfeat.image_fromstring(image_data)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
return
if self.filter_side is not None and min(image.shape[0], image.shape[1]) < self.filter_side:
hadoopy.counter('DATA_ERRORS', 'ImageTooSmallPre')
return
if self.max_side is not None:
image = imfeat.resize_image_max_side(image, self.max_side)
if self.filter_side is not None and min(image.shape[0], image.shape[1]) < self.filter_side:
hadoopy.counter('DATA_ERRORS', 'ImageTooSmallPost')
return
yield name, imfeat.image_tostring(image, 'jpg')
def object_rec_parse(self, *args, **kw):
import cv2
try:
for image_fn, objects in self.object_rec_parse_fn(*args, **kw):
yield cv2.imread(image_fn), objects
except NotImplementedError:
import imfeat
try:
for image_url, objects in self.object_rec_parse_url(*args, **kw):
try:
yield imfeat.image_fromstring(urllib.urlopen(image_url).read()), objects
except:
logging.warn('Cannot download/parse [%s], skipping...' % image_url)
except NotImplementedError:
raise NotImplementedError
def map(self, image_id, image_binary):
image = imfeat.image_fromstring(image_binary)
print(image.shape)
st = time.time()
box_num = -1
for box_num, (box, f) in enumerate(feature.image_patch_features_dense(image, normalize_box=True)):
scores = np.dot(self.coefs, f.reshape((f.size, 1))) + self.intercepts
pred_common = [image_id, box.tolist(), f.tolist()]
for score, preds in zip(scores, self.preds):
pred = self.output_formatter([float(score[0])] + pred_common)
if len(preds) >= self.max_hard:
heapq.heappushpop(preds, pred)
else:
heapq.heappush(preds, pred)
hadoopy.counter("stats", "num_boxes", box_num + 1)
print("ImageTime[%f]" % (time.time() - st))
def map(self, name, image_data):
try:
image = imfeat.image_fromstring(image_data)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
return
try:
image = imfeat.resize_image(image, self._image_height, self._image_width)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
try:
for x in self._feat(image):
yield name, x
except:
hadoopy.counter('DATA_ERRORS', 'UnkImageType')
return
def map(self, image_id, image_binary):
image = imfeat.image_fromstring(image_binary)
print(image.shape)
st = time.time()
box_num = -1
for box_num, (box, f) in enumerate(feature.image_patch_features_dense(image, normalize_box=True)):
scores = np.dot(self.coefs, f.reshape((f.size, 1))) + self.intercepts
pred_common = [image_id, box.tolist(), f.tolist()]
for score, preds in zip(scores, self.preds):
pred = self.output_formatter([float(score[0])] + pred_common)
if len(preds) >= self.max_hard:
heapq.heappushpop(preds, pred)
else:
heapq.heappush(preds, pred)
hadoopy.counter('stats', 'num_boxes', box_num + 1)
print('ImageTime[%f]' % (time.time() - st))
def map(self, image_id, image_binary):
try:
boxes = self.image_box_fns[image_id]
except KeyError:
pass
else:
image = imfeat.image_fromstring(image_binary)
size_array = np.array([image.shape[0], image.shape[1], image.shape[0], image.shape[1]])
scale_boxes = {}
for box, fn in boxes:
fbox = size_array * box
scale = int(np.round(np.log2((fbox[2] - fbox[0]) / feature.PATCH_SIZE)))
scale_check = int(np.round(np.log2((fbox[3] - fbox[1]) / feature.PATCH_SIZE)))
if scale != scale_check:
raise ValueError("Box is not square.")
scale_boxes.setdefault(scale, []).append((box, fn))
# Order boxes and fn's by scale
for scale in range(max(scale_boxes.keys()) + 1):
if scale > 0:
height, width = np.array(image.shape[:2]) / 2
image = image[: height * 2, : width * 2, :]
if min(width, height) < 1:
raise ValueError("Image is too small")
image = cv2.resize(image, (width, height))
if image is None: # NOTE(brandyn): It is too small
raise ValueError("Image is too small")
try:
boxes = scale_boxes[scale]
except KeyError:
continue
size_array = np.array([image.shape[0], image.shape[1], image.shape[0], image.shape[1]])
for box, fn in boxes:
box = np.round(size_array * box).astype(np.int)
print(box)
if self.type == "image":
image_box = np.ascontiguousarray(image[box[0] : box[2], box[1] : box[3], :])
yield fn, imfeat.image_tostring(image_box, "png")
elif self.type == "feature":
image_box = np.ascontiguousarray(image[box[0] : box[2], box[1] : box[3], :])
yield fn, feature.compute_patch(image_box)
elif self.type == "box":
image2 = image.copy()
cv2.rectangle(image2, (box[1], box[0]), (box[3], box[2]), (0, 255, 0), 4)
yield fn, imfeat.image_tostring(image2, "jpg")
else:
raise ValueError(self.type)
def map(self, name, image_data):
try:
image = imfeat.image_fromstring(image_data)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
return
if self.filter_side is not None and min(
image.shape[0], image.shape[1]) < self.filter_side:
hadoopy.counter('DATA_ERRORS', 'ImageTooSmallPre')
return
if self.max_side is not None:
image = imfeat.resize_image_max_side(image, self.max_side)
if self.filter_side is not None and min(
image.shape[0], image.shape[1]) < self.filter_side:
hadoopy.counter('DATA_ERRORS', 'ImageTooSmallPost')
return
yield name, imfeat.image_tostring(image, 'jpg')
def segmentation_boxes(self):
"""
Yields:
Dataset as specified by 'split'
Data is in the form of (masks, numpy array), where
masks is a dict of boolean masks with keys as class names
"""
classes = json.load(open('classes.js'))
for row_key, columns in self.data_source.row_column_values(['gt']):
if not row_key.startswith('sun397train'):
continue
columns = dict(columns)
print(columns.keys())
print(repr(row_key))
image = imfeat.image_fromstring(self.data_source.value(row_key, 'image'))
masks = (255 * picarus.api.np_fromstring(columns['gt'])).astype(np.uint8)
class_masks = dict((y, np.ascontiguousarray(masks[:, :, x])) for x, y in enumerate(classes))
yield class_masks, image
def _crop_image_from_str(s):
"""Load from string, crop to a square, resize to _initial_image_size
Args:
s: String of bytes representing a JPEG image
Returns:
RGB Image with height/width as _initial_image_size
Raises:
ValueError: Image is height/width too small (< _initial_image_size)
or mode isn't RGB
IOError: Image is unreadable
"""
if isinstance(s, tuple):
s = s[0]
try:
img = imfeat.image_fromstring(s)
except IOError, e:
hadoopy.counter('Stats', 'IMG_BAD')
raise e
def _crop_image_from_str(s):
"""Load from string, crop to a square, resize to _initial_image_size
Args:
s: String of bytes representing a JPEG image
Returns:
RGB Image with height/width as _initial_image_size
Raises:
ValueError: Image is height/width too small (< _initial_image_size)
or mode isn't RGB
IOError: Image is unreadable
"""
if isinstance(s, tuple):
s = s[0]
try:
img = imfeat.image_fromstring(s)
except IOError, e:
hadoopy.counter('Stats', 'IMG_BAD')
raise e
def segmentation_boxes(self):
"""
Yields:
Dataset as specified by 'split'
Data is in the form of (masks, numpy array), where
masks is a dict of boolean masks with keys as class names
"""
classes = json.load(open('classes.js'))
for row_key, columns in self.data_source.row_column_values(['gt']):
if not row_key.startswith('sun397train'):
continue
columns = dict(columns)
print(columns.keys())
print(repr(row_key))
image = imfeat.image_fromstring(
self.data_source.value(row_key, 'image'))
masks = (255 * picarus.api.np_fromstring(columns['gt'])).astype(
np.uint8)
class_masks = dict((y, np.ascontiguousarray(masks[:, :, x]))
for x, y in enumerate(classes))
yield class_masks, image
def _mask_annotation_render(self, row_key, class_segments, image_key, image_superpixel_key, min_votes=1):
columns = dict((x, y.value) for x, y in self.hb.getRowWithColumns(self.images_table, row_key, [image_key, image_superpixel_key])[0].columns.items())
image = imfeat.image_fromstring(columns[image_key])
segments = json.loads(columns[image_superpixel_key])
class_masks = {}
class_masks = np.zeros((image.shape[0], image.shape[1], self.texton_num_classes))
for name, user_segment_groups in class_segments.items():
cur_mask = np.zeros(image.shape[:2], dtype=np.uint8)
segment_counts = {}
for x in sum(user_segment_groups, []):
try:
segment_counts[x] += 1
except KeyError:
segment_counts[x] = 1
valid_segments = [x for x, y in segment_counts.items() if y >= min_votes]
for user_segment in valid_segments:
hull = segments[user_segment]
hull = np.asarray(hull).astype(np.int32).reshape(1, -1, 2)
mask_color = 255
cv2.drawContours(cur_mask, hull, -1, mask_color, -1)
cv2.drawContours(cur_mask, hull, -1, mask_color, 2)
class_masks[:, :, self.texton_classes[name]['mask_num']] = cur_mask / 255.
return class_masks, image
def _map(self, row, image_binary):
try:
image = imfeat.image_fromstring(image_binary)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
yield row, picarus.api.np_tostring(self._feat(image))
def map(self, image_id, image_binary):
image = imfeat.image_fromstring(image_binary)
for box, f in feature.image_patch_features_dense(image,
normalize_box=True):
yield (image_id, box.tolist()), f
import os
import random
import numpy as np
import imfeat
import picarus.modules
import picarus.api
logging.basicConfig(level=logging.DEBUG)
a = hadoopy_hbase.connect()
hrc = picarus.modules.HashRetrievalClassifier()
hrc.load(open('sun397_feature_index.pb').read())
for num, (row, cols) in enumerate(hadoopy_hbase.scanner(a, 'images', start_row='sun397train')):
if num > 2:
break
print cols['feat:superpixel'][:50]
image = imfeat.image_fromstring(cols['data:image_320'])
print imfeat.image_fromstring(cols['data:image']).shape
print imfeat.image_fromstring(cols['data:image_320']).shape
print('image_75sq[%d]' % len(cols['data:image_75sq']))
print row
cur_f = picarus.api.np_fromstring(cols['feat:gist'])
cur_h = np.fromstring(cols['hash:gist'], dtype=np.uint8)
print 'HOG', picarus.api.np_fromstring(cols['feat:bovw_hog_levels2_sbin16_blocks1_clusters100'])
print 'Hash Bits[%d]' % (cur_h.size * 8,)
print 'Feature Dims[%d]' % (cur_f.size,)
f = hrc.feature(image)
h = hrc.hasher(f).ravel()
#print cur_f
#print f
print cur_h
print h
def map(self, image_id, image_binary):
image = imfeat.image_fromstring(image_binary)
for box, f in feature.image_patch_features_dense(image, normalize_box=True):
yield (image_id, box.tolist()), f
import random
import numpy as np
import imfeat
import picarus.modules
import picarus.api
logging.basicConfig(level=logging.DEBUG)
a = hadoopy_hbase.connect()
hrc = picarus.modules.HashRetrievalClassifier()
hrc.load(open('sun397_feature_index.pb').read())
for num, (row, cols) in enumerate(
hadoopy_hbase.scanner(a, 'images', start_row='sun397train')):
if num > 2:
break
print cols['feat:superpixel'][:50]
image = imfeat.image_fromstring(cols['data:image_320'])
print imfeat.image_fromstring(cols['data:image']).shape
print imfeat.image_fromstring(cols['data:image_320']).shape
print('image_75sq[%d]' % len(cols['data:image_75sq']))
print row
cur_f = picarus.api.np_fromstring(cols['feat:gist'])
cur_h = np.fromstring(cols['hash:gist'], dtype=np.uint8)
print 'HOG', picarus.api.np_fromstring(
cols['feat:bovw_hog_levels2_sbin16_blocks1_clusters100'])
print 'Hash Bits[%d]' % (cur_h.size * 8, )
print 'Feature Dims[%d]' % (cur_f.size, )
f = hrc.feature(image)
h = hrc.hasher(f).ravel()
#print cur_f
#print f
print cur_h
def load_data(self, image_data, image_metadata):
image_metadata['tags'] = image_metadata['tags'].split()
image = imfeat.image_fromstring(image_data, {'type': 'numpy', 'dtype': 'uint8', 'mode': 'bgr'})
return image, image_metadata
def _map(self, row, image_binary):
try:
image = imfeat.image_fromstring(image_binary)
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
yield row, picarus.api.np_tostring(self._feat(image))
def _map(self, row, image_binary):
try:
image = imfeat.image_fromstring(image_binary)
yield row, imfeat.image_tostring(imfeat.resize_image_max_side(image, self.max_side), 'jpg')
except:
hadoopy.counter('DATA_ERRORS', 'ImageLoadError')
