def load_bbs_from_ann(data_path, n_images=-1):
'''
load bounding boxes from annotation files
'''
jpg_train = [
img_f for img_f in os.listdir(data_path) if img_f.find('.jpg') > 0
]
# if n_images is specified, then only look at the first n_images
if n_images > 1:
jpg_train = jpg_train[:min(len(jpg_train), n_images)]
bbs_gt_dict = {}
for ind_img, img_file in enumerate(jpg_train):
logger.debug("processing %s" % img_file)
ann_file = img_file.split('.')[0]
ann_path = ann_path = os.path.join(data_path, ann_file)
annotation = get_annotation(ann_path)
# get all bbs for this image
bbs_gt_raw = get_bbs(annotation)
bbs_gt = np.empty((len(bbs_gt_raw), 4))
for kk, (xy, width, height) in enumerate(bbs_gt_raw):
x, y = xy
bbs_gt[kk, :] = [x, y, x + width, y + height]
bbs_gt_dict[img_file] = bbs_gt
return bbs_gt_dict
for i, j in enumerate(jpg_train + jpg_test):
try:
im = scipy.misc.imread(os.path.join(train_path, j))
except IOError:
print "There was a problem reading the jpg: %s." % j
continue
# the rollaxis command rolls the last (-1) axis back until the start
# do a colourspace conversion
im_y, im_i, im_q = colorsys.rgb_to_yiq(*np.rollaxis(im[..., :3], axis=-1))
ann_file = j.split('.')[0]
ann_path = ann_path = os.path.join(train_path, ann_file)
annotation = get_annotation(ann_path)
# get all bbs for this image
bbs = get_bbs(annotation)
for xy, width, height in bbs:
x, y = xy
# remember y is indexed first in image
moth = im_y[y:(y + height), x:(x + width)]
moth_list.append(moth)
n_moths = len(moth_list)
widths = np.array([m.shape[1] for m in moth_list])
max_w = widths.max()
heights = np.array([m.shape[0] for m in moth_list])
max_h = heights.max()
moth_array = np.zeros((n_moths, max_h, max_w))
for i, m in enumerate(moth_list):
pos_dir = '/mnt/data/datasets/bugs_annotated_2014/Good Images/Positive_Counts_All'
neg_dir = '/mnt/data/datasets/bugs_annotated_2014/Good Images/No_Counts_All'
# pos_name = '1471_39381.jpg'
# pos_name = '1088_26202.jpg'
# pos_name = '1227_35266.jpg'
pos_name = '1227_39869.jpg'
neg_name = '501_30706.jpg'
pos_path = os.path.join(pos_dir, pos_name)
neg_path = os.path.join(neg_dir, neg_name)
img_pos = imread(pos_path)
img_neg = imread(neg_path)
bbs_pos = get_bbs(get_annotation(pos_path.strip('.jpg')))
plt.ioff()
fig = plt.figure()
ax = plt.subplot(1, 1, 1)
annotate_bbs(ax, map(xywh_to_x1y1x2y2, bbs_pos))
plt.imshow(img_pos)
plt.axis('off')
plt.tight_layout()
plt.savefig(os.path.join(fig_dir, "example_pos.png"))
# TODO: make the boundaries tighter
# plot_margin = 0.25
# x0, x1, y0, y1 = plt.axis()
# plt.axis((x0 - plot_margin,
DEBUG = False
dir_root = '/mnt/data/datasets/bugs_annotated_2014/Good Images'
dir_all = '/mnt/data/datasets/bugs_annotated_2014/Good Images/All'
dir_no_cnt_all = '/mnt/data/datasets/bugs_annotated_2014/Good Images/No_Counts_All'
dir_pos_cnt_all = '/mnt/data/datasets/bugs_annotated_2014/Good Images/Positive_Counts_All'
if not os.path.isdir(dir_no_cnt_all):
os.makedirs(dir_no_cnt_all)
if not os.path.isdir(dir_pos_cnt_all):
os.makedirs(dir_pos_cnt_all)
# load the label file and determine no/pos counts and seperate to different
# folders.
for filename in os.listdir(dir_all):
if not filename.endswith(".jpg"):
bbs = get_bbs(get_annotation(os.path.join(dir_all, filename)))
if DEBUG:
print bbs
if len(bbs):
shutil.copyfile(os.path.join(dir_all, filename),
os.path.join(dir_pos_cnt_all, filename))
shutil.copyfile(os.path.join(dir_all, filename + ".jpg"),
os.path.join(dir_pos_cnt_all, filename + ".jpg"))
else:
shutil.copyfile(os.path.join(dir_all, filename),
os.path.join(dir_no_cnt_all, filename))
shutil.copyfile(os.path.join(dir_all, filename + ".jpg"),
os.path.join(dir_no_cnt_all, filename + ".jpg"))
def get_pos(
data_path,
target_height,
target_width,
flag_rescale=False,
flag_multiscale=False,
flag_rgb=True,
detect_width_list=[8, 16, 32, 64],
detect_height_list=[8, 16, 32, 64],
flag_trans_aug=False,
dist_trans_list=(-2, 0, 2),
):
""" Get positive training examples
examples are rescaled to target_height and target_width
With the assumption that the annotation file have the same name with
the image but with no extension
flag_trans_aug: if do translation augmentation
"""
jpg_train = [f for f in os.listdir(data_path) if f.find('.jpg') > 0]
# moths = []
moth_resized_list = []
for i, j in enumerate(jpg_train):
try:
im = scipy.misc.imread(os.path.join(data_path, j))
except IOError:
logger.warn("There was a problem reading the jpg: %s." % j)
continue
im = grey_world(im)
if not flag_rgb:
# im will be assigned to the new gray image
# the rollaxis command rolls the last (-1) axis back until the start
# do a colourspace conversion
im, im_i, im_q = colorsys.rgb_to_yiq(
*np.rollaxis(im[..., :3], axis=-1))
ann_file = j.split('.')[0]
ann_path = os.path.join(data_path, ann_file)
annotation = get_annotation(ann_path)
# get all bbs for this image
bbs = get_bbs(annotation)
if flag_trans_aug:
bbs = augment_bbs_by_trans(bbs, dist_trans_list)
for xy, width, height in bbs:
x, y = xy
# determine if the xy, width, height are postive and within range
values_with_in_range = width > 0 and height > 0 \
and y >= 0 and y + height < im.shape[0] \
and x >= 0 and x + width < im.shape[1]
if not values_with_in_range:
print "Bad boundingbox, ignored"
print xy, width, height
continue
# remember y is indexed first in image
# moth = im[y:(y + height), x:(x + width)]
# moths.append(moth)
# print moth.shape
if flag_multiscale:
moth_resized = crop_and_rescale_nearest(
im,
xy,
width,
height,
target_width,
target_height,
detect_width_list=detect_width_list,
detect_height_list=detect_height_list)
elif flag_rescale:
moth_resized = crop_and_rescale(im, xy, width, height,
target_width, target_height)
else:
moth_resized = crop_centered_box(im, xy, width, height,
target_width, target_height)
moth_resized_list.append(moth_resized)
return moth_resized_list
for i, j in enumerate(jpg_train):
try:
im = plt.imread(os.path.join(train_path, j), 'r')
except IOError:
print "There was a problem reading the jpg: %s." % j
continue
# the rollaxis command rolls the last (-1) axis back until the start
# do a colourspace conversion
im_y, im_i, im_q = colorsys.rgb_to_yiq(*np.rollaxis(im[...,:3], axis=-1))
ann_file = j.split('.')[0]
ann_path = ann_path = os.path.join(train_path, ann_file)
annotation = get_annotation(ann_path)
# get all bbs for this image
bbs = get_bbs(annotation)
for xy, width, height in bbs:
x, y = xy
# remember y is indexed first in image
moth = im_y[y:(y + height), x:(x + width)]
moths.append(moth)
#print moth.shape
moth_resized = crop_and_rescale(im_y, xy, width, height,
target_width=32, target_height=32)
moths_resized.append(moth_resized)
n_moths = len(moths_resized)
m = np.asarray(moths_resized).reshape((n_moths,
target_height * target_width))
for item in list_rm:
os.remove(os.path.join(dir_all, item))
os.remove(os.path.join(dir_all, item + ext_img))
os.remove(os.path.join(dir_all, item + ext_seg))
# step 3, make statistics by looking at the annotation files
list_all = [
filename.strip(ext_img) for filename in os.listdir(dir_all)
if ext_img in filename
]
list_len = []
for item in list_all:
list_len.append(
len(get_bbs(get_annotation(os.path.join(dir_all, item)))))
# report statistics
num_withmoth = np.sum(np.array(list_len) > 0)
num_nomoth = np.sum(np.array(list_len) == 0)
print ''
print 'Total:'
print_nums(list_len)
# distribute
# step sort, and then have probability of going to train and test
# list_all_sorted,
sorted_tuples = sorted(zip(list_len, list_all), reverse=True)
list_ann_sorted = [img for (num, img) in sorted_tuples]