def postprocess_regular(image_info, np_pred_boxes, np_pred_confidences, H,
options):
pred_anno = al.Annotation()
pred_anno.imageName = image_info['path']
pred_anno.imagePath = os.path.abspath(image_info['path'])
_, rects = add_rectangles(H, [image_info['transformed']],
np_pred_confidences,
np_pred_boxes,
use_stitching=True,
rnn_len=H['rnn_len'],
min_conf=options['min_conf'],
tau=options['tau'],
show_suppressed=False)
h, w = image_info['original_shape']
if 'rotate90' in H['data'] and H['data']['rotate90']:
# original image height is a width for rotated one
rects = Rotate90.invert(h, rects)
rects = [
r for r in rects
if r.x1 < r.x2 and r.y1 < r.y2 and r.score > options['min_conf']
]
pred_anno.rects = rects
pred_anno = rescale_boxes((H['image_height'], H['image_width']), pred_anno,
h, w)
return pred_anno
def annotation_labelbox_from_result(result, columns, url_prefix):
annotation = AnnotationLib.Annotation()
image_url = get_path_from_s3(result[columns['annotation']], url_prefix)
boxes = parse_boxes(result[columns['Answer.results']])
for box in boxes:
annotation.rects.append(AnnotationLib.AnnoRect(*box))
# remove parameters from filename
param_idx = image_url.index('&');
annotation.imageName = image_url[:param_idx];
return annotation
def annotation_empty_from_result(result, columns, url_prefix):
annotation = AnnotationLib.Annotation()
image_url = get_path_from_s3(result[columns['annotation']], url_prefix)
# remove parameters from filename
param_idx = image_url.index('&');
annotation.imageName = image_url[:param_idx];
# MA: assume filenames don't contain ","
cidx = annotation.imageName.find(',')
if cidx >= 0:
annotation.imageName = annotation.imageName[:cidx];
assert(len(annotation.imageName) > 0);
return annotation
def annotation_labelact_from_result(result, columns, url_prefix):
annotation = AnnotationLib.Annotation()
image_url = get_path_from_s3(result[columns['annotation']], url_prefix)
# remove parameters from filename
param_idx = image_url.index('&');
image_url_split = image_url[:param_idx].split(',');
assert(len(image_url_split) == 5);
annotation.imageName = image_url_split[0];
rect = AnnotationLib.AnnoRect();
rect.x1 = int(image_url_split[1])
rect.y1 = int(image_url_split[2])
rect.x2 = int(image_url_split[3])
rect.y2 = int(image_url_split[4])
result_split = result[columns['Answer.results']].split(',');
assert(len(result_split) == 1 + 1 + 4 + 4);
# male/female
gender_idx_to_val = {0: ATTR_VAL_GENDER_MALE, 1: ATTR_VAL_GENDER_FEMALE};
ptype_idx_to_val = {0: ATTR_VAL_PTYPE_SALES, 1: ATTR_VAL_PTYPE_CUST};
sales_act_idx_to_val = {0: ATTR_VAL_ACT_SALES_INT, 1: ATTR_VAL_ACT_SALES_CLEAN, 2: ATTR_VAL_ACT_SALES_OTHER};
cust_act_idx_to_val = {0: ATTR_VAL_ACT_CUST_QUEUE, 1: ATTR_VAL_ACT_CUST_INT, 2: ATTR_VAL_ACT_CUST_BROWSE, 3: ATTR_VAL_ACT_CUST_OTHER};
gender_idx = int(result_split[-4]);
rect.at["gender"] = gender_idx_to_val[gender_idx];
# sales/cust
ptype_idx = int(result_split[-3]);
rect.at["ptype"] = ptype_idx_to_val[ptype_idx];
if ptype_idx == 0:
# interact/clean/other
act_idx = int(result_split[-2]);
rect.at["act"] = sales_act_idx_to_val[act_idx];
else:
# queue/interact/browse/other
act_idx = int(result_split[-1]);
rect.at["act"] = cust_act_idx_to_val[act_idx];
annotation.rects.append(rect);
return annotation
def eval(self, weights, test_boxes, min_conf, tau, show_suppressed, expname):
self.H["grid_width"] = self.H["image_width"] / self.H["region_size"]
self.H["grid_height"] = self.H["image_height"] / self.H["region_size"]
x_in = tf.placeholder(tf.float32, name='x_in', shape=[self.H['image_height'], self.H['image_width'], 3])
if self.H['use_rezoom']:
pred_boxes, pred_logits, pred_confidences, pred_confs_deltas, pred_boxes_deltas = self.build_forward(tf.expand_dims(x_in, 0), 'test', reuse=None)
grid_area = self.H['grid_height'] * self.H['grid_width']
pred_confidences = tf.reshape(tf.nn.softmax(tf.reshape(pred_confs_deltas, [grid_area * self.H['rnn_len'], 2])),
[grid_area, self.H['rnn_len'], 2])
if self.H['reregress']:
pred_boxes = pred_boxes + pred_boxes_deltas
else:
pred_boxes, pred_logits, pred_confidences = self.build_forward(tf.expand_dims(x_in, 0), 'test', reuse=None)
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
saver.restore(sess, weights)
pred_annolist = al.AnnoList()
true_annolist = al.parse(test_boxes)
data_dir = os.path.dirname(test_boxes)
image_dir = self.get_image_dir(weights, expname, test_boxes)
subprocess.call('mkdir -p %s' % image_dir, shell=True)
for i in range(len(true_annolist)):
true_anno = true_annolist[i]
orig_img = imread('%s/%s' % (data_dir, true_anno.imageName))[:,:,:3]
img = imresize(orig_img, (self.H["image_height"], self.H["image_width"]), interp='cubic')
feed = {x_in: img}
(np_pred_boxes, np_pred_confidences) = sess.run([pred_boxes, pred_confidences], feed_dict=feed)
pred_anno = al.Annotation()
pred_anno.imageName = true_anno.imageName
new_img, rects = add_rectangles(self.H, [img], np_pred_confidences, np_pred_boxes,
use_stitching=True, rnn_len=self.H['rnn_len'], min_conf=min_conf, tau=tau, show_suppressed=show_suppressed)
pred_anno.rects = rects
pred_anno.imagePath = os.path.abspath(data_dir)
pred_anno = rescale_boxes((self.H["image_height"], self.H["image_width"]), pred_anno, orig_img.shape[0], orig_img.shape[1])
pred_annolist.append(pred_anno)
imname = '%s/%s' % (image_dir, os.path.basename(true_anno.imageName))
misc.imsave(imname, new_img)
if i % 25 == 0:
print(i)
return pred_annolist, true_annolist
def pal2al(_annolist):
annotations = []
for _a in _annolist.annotation:
anno = AnnotationLib.Annotation()
anno.imageName = _a.imageName
anno.rects = []
for _r in _a.rect:
rect = AnnotationLib.AnnoRect()
rect.x1 = _r.x1
rect.x2 = _r.x2
rect.y1 = _r.y1
rect.y2 = _r.y2
if _r.HasField("id"):
rect.id = _r.id
if _r.HasField("track_id"):
rect.track_id = _r.track_id
if _r.HasField("score"):
rect.score = _r.score
if _r.HasField("distance3d"):
rect.distance3d = _r.distance3d
if _r.HasField("width3d"):
rect.width3d = _r.width3d
if _r.HasField("height3d"):
rect.height3d = _r.height3d
if _r.HasField("length3d"):
rect.length3d = _r.length3d
anno.rects.append(rect)
annotations.append(anno)
return annotations
def pal2al(_annolist):
#annotations = [];
annotations = AnnotationLib.AnnoList()
for adesc in _annolist.attribute_desc:
annotations.attribute_desc[adesc.name] = adesc
print "attribute: ", adesc.name, adesc.id
for valdesc in adesc.val_to_str:
annotations.add_attribute_val(adesc.name, valdesc.s, valdesc.id)
attribute_name_from_id = {
adesc.id: aname
for aname, adesc in annotations.attribute_desc.iteritems()
}
attribute_dtype_from_id = {
adesc.id: adesc.dtype
for aname, adesc in annotations.attribute_desc.iteritems()
}
for _a in _annolist.annotation:
anno = AnnotationLib.Annotation()
anno.imageName = _a.imageName
anno.rects = []
for _r in _a.rect:
rect = AnnotationLib.AnnoRect()
rect.x1 = _r.x1
rect.x2 = _r.x2
rect.y1 = _r.y1
rect.y2 = _r.y2
if _r.HasField("id"):
rect.id = _r.id
if _r.HasField("track_id"):
rect.track_id = _r.track_id
if _r.HasField("score"):
rect.score = _r.score
for _at in _r.attribute:
try:
cur_aname = attribute_name_from_id[_at.id]
cur_dtype = attribute_dtype_from_id[_at.id]
except KeyError as e:
print "attribute: ", _at.id
print e
assert (False)
if cur_dtype == AnnotationLib.AnnoList.TYPE_INT32:
rect.at[cur_aname] = _at.val
elif cur_dtype == AnnotationLib.AnnoList.TYPE_FLOAT:
rect.at[cur_aname] = _at.fval
elif cur_dtype == AnnotationLib.AnnoList.TYPE_STRING:
rect.at[cur_aname] = _at.strval
else:
assert (False)
anno.rects.append(rect)
annotations.append(anno)
return annotations
if not os.path.exists(opts.output_dir):
print "ERROR: output dir not found"
exit()
if not os.path.exists(opts.images_dir):
print "ERROR: images dir not found"
exit()
imglist = glob.glob(opts.images_dir + "/*.jpeg")
imglist.sort()
# create image list
annolist = []
for imgidx in xrange(0, len(imglist)):
anno = AnnotationLib.Annotation()
anno.imageName = imglist[imgidx]
anno.rects = []
annolist.append(anno)
# load vatic tracks
vatic_dump = pickle.load(open(opts.vatic_filename, "rb"))
num_tracks = len(vatic_dump)
print "number of tracks: ", num_tracks
for tidx in xrange(0, num_tracks):
vatic_boxes = vatic_dump[tidx]["boxes"]
track_len = len(vatic_boxes)
print "track ", tidx, ", track_len: ", track_len
