def get_batch_stats(self):
ori_centers = np.array(self.ori_centers)
ori_heading_classes = np.array(self.ori_heading_classes)
ori_heading_residuals = np.array(self.ori_heading_residuals)
ori_size_classes = np.array(self.ori_size_classes)
ori_size_residuals = np.array(self.ori_size_residuals)
del_centers = np.array(self.del_centers)
del_heading_classes = np.array(self.del_heading_classes)
del_heading_residuals = np.array(self.del_heading_residuals)
del_size_classes = np.array(self.del_size_classes)
del_size_residuals = np.array(self.del_size_residuals)
y_centers = np.array(self.y_centers)
y_heading_classes = np.array(self.y_heading_classes)
y_heading_residuals = np.array(self.y_heading_residuals)
y_size_classes = np.array(self.y_size_classes)
y_size_residuals = np.array(self.y_size_residuals)
y_clses = np.array(self.y_clses)
assert(ori_centers.shape == del_centers.shape == y_centers.shape)
assert(ori_size_classes.shape == del_size_classes.shape)
assert(len(ori_centers) == len(del_centers) == len(y_centers) == len(y_clses))
iou3ds_ori, iou3ds_del = [], []
for i in range(len(ori_centers)):
ori_lwh = class2size(ori_size_classes[i], ori_size_residuals[i])
ori_ry = class2angle(ori_heading_classes[i], ori_heading_residuals[i], 12)
ori_box3d = get_3d_box(ori_lwh, ori_ry, ori_centers[i])
del_lwh = class2size(del_size_classes[i], del_size_residuals[i])
del_ry = class2angle(del_heading_classes[i], del_heading_residuals[i], 12)
del_box3d = get_3d_box(del_lwh, del_ry, del_centers[i])
y_lwh = class2size(y_size_classes[i], y_size_residuals[i])
y_ry = class2angle(y_heading_classes[i], y_heading_residuals[i], 12)
y_box3d = get_3d_box(y_lwh, y_ry, y_centers[i])
ori_iou3d, _ = box3d_iou(y_box3d, ori_box3d)
del_iou3d, _ = box3d_iou(y_box3d, del_box3d)
iou3ds_ori.append(ori_iou3d)
iou3ds_del.append(del_iou3d)
iou3ds_ori = np.array(iou3ds_ori)
iou3ds_del = np.array(iou3ds_del)
stats = {}
for c in range(self.num_classes):
is_curr_class = (y_clses == c)
support = np.sum(is_curr_class)
if support == 0: continue
iou3ds_ori_curr_class = iou3ds_ori[is_curr_class,...]
iou3ds_del_curr_class = iou3ds_del[is_curr_class,...]
mean_iou3d_ori = np.mean(iou3ds_ori_curr_class)
mean_iou3d_del = np.mean(iou3ds_del_curr_class)
change_in_iou3d = mean_iou3d_del - mean_iou3d_ori
stats[self.classes[c]] = (mean_iou3d_ori, mean_iou3d_del, change_in_iou3d, support)
return stats
def evaluate_predictions(predictions, dataset, classes, test_dataset, test_classes):
ps_list, _, segp_list, center_list, heading_cls_list, heading_res_list, size_cls_list, size_res_list, \
rot_angle_list, score_list, cls_list, file_num_list, _, _ = predictions
print('Number of PRED boxes: %d, Number of GT boxes: %d' % (len(segp_list), len(test_dataset)))
# For detection evaluation
pred_all = {}
gt_all = {}
ovthresh = 0.25
# A) Get GT boxes
# print('Constructing GT boxes...')
for i in range(len(test_dataset)):
img_id = test_dataset.idx_l[i]
if img_id in gt_all: continue # All ready counted..
gt_all[img_id] = []
objects = dataset.get_label_objects(img_id)
calib = dataset.get_calibration(img_id)
for obj in objects:
if obj.classname not in test_classes: continue
box3d_pts_2d, box3d_pts_3d = compute_box_3d(obj, calib)
box3d_pts_3d = calib.project_upright_depth_to_upright_camera(box3d_pts_3d)
box3d_pts_3d_flipped = np.copy(box3d_pts_3d)
box3d_pts_3d_flipped[0:4,:] = box3d_pts_3d[4:,:]
box3d_pts_3d_flipped[4:,:] = box3d_pts_3d[0:4,:]
gt_all[img_id].append((obj.classname, box3d_pts_3d_flipped))
# B) Get PRED boxes
# print('Constructing PRED boxes...')
for i in range(len(ps_list)):
img_id = file_num_list[i]
classname = classes[cls_list[i]]
if classname not in test_classes: raise Exception('Not supposed to have class: %s' % classname)
center = center_list[i].squeeze()
rot_angle = rot_angle_list[i]
# Get heading angle and size
heading_angle = roi_seg_box3d_dataset.class2angle(heading_cls_list[i], heading_res_list[i], NUM_HEADING_BIN)
box_size = roi_seg_box3d_dataset.class2size(size_cls_list[i], size_res_list[i])
corners_3d_pred = roi_seg_box3d_dataset.get_3d_box(box_size, heading_angle, center)
corners_3d_pred = rotate_pc_along_y(corners_3d_pred, -rot_angle)
if img_id not in pred_all:
pred_all[img_id] = []
pred_all[img_id].append((classname, corners_3d_pred, score_list[i]))
# Compute AP
rec, prec, ap = eval_det(pred_all, gt_all, ovthresh)
mean_ap = np.mean([ap[classname] for classname in ap])
return rec, prec, ap, mean_ap
box3d = TEST_DATASET.get_center_view_box3d(i)
ps = ps_list[i]
segp = segp_list[i].squeeze()
center = center_list[i].squeeze()
ret = TEST_DATASET[i]
rot_angle = ret[7]
# Get heading angle and size
print heading_cls_list[i], heading_res_list[i], size_cls_list[
i], size_res_list[i]
heading_angle = roi_seg_box3d_dataset.class2angle(heading_cls_list[i],
heading_res_list[i], 12)
box_size = roi_seg_box3d_dataset.class2size(size_cls_list[i],
size_res_list[i])
corners_3d_pred = roi_seg_box3d_dataset.get_3d_box(box_size, heading_angle,
center)
# NOTE: fix this, box3d (projected from upright_depth coord) has flipped ymin,ymax as that in corners_3d_pred
box3d_new = np.copy(box3d)
box3d_new[0:4, :] = box3d[4:, :]
box3d_new[4:, :] = box3d[0:4, :]
iou_3d, iou_2d = box3d_iou(corners_3d_pred, box3d_new)
print corners_3d_pred
print box3d_new
print 'Ground/3D IoU: ', iou_2d, iou_3d
correct = int(iou_3d >= 0.25)
total_cnt += 1
correct_cnt += correct
class_total_cnt[classname] += 1
class_correct_cnt[classname] += correct
def vis_predictions3D(pred_files, gt_file, number_to_show=10, filenums=None):
from roi_seg_box3d_dataset import class2type
idx = 0
COLS = number_to_show
ap_infos = {}
classes, file_nums, mean_box_ious, mean_seg_ious, box_ious, seg_ious = [], [], [], [], [], []
vtk_pcs_with_col, vtk_pcs_wo_col, vtk_imgs, vtk_gt_boxes, vtk_pred_boxes, vtk_texts = [], [], [], [], [], []
choices = []
test_dataset = ROISegBoxDataset(WHITE_LIST, npoints=2048,
split='val', rotate_to_center=True,
overwritten_data_path=gt_file,
from_rgb_detection=False)
for n, pred_file in enumerate(pred_files):
# Lists of different items from predictions
predictions = load_zipped_pickle(pred_file)
ps_l, seg_gt_l, seg_pred_l, center_l, heading_cls_l, heading_res_l, size_cls_l, size_res_l, rot_angle_l, \
score_l, cls_type_l, file_num_l, box2d_l, box3d_l = predictions
if n == 0:
# Choosing equal number of objects per class to display
cls_types = []
options = {}
for i, cls_type in enumerate(cls_type_l):
if not class2type[cls_type] in WHITE_LIST: continue
if options.get(cls_type) is None:
options[cls_type] = [i]
cls_types.append(cls_type)
else:
options[cls_type].append(i)
# Make use of array_split to divide into fairly equal groups
arr = np.array_split([1] * number_to_show, len(options.keys()))
random.shuffle(arr)
for i, group in enumerate(arr):
cls_type = cls_types[i]
choice_list = np.random.choice(options[cls_type], len(group), replace=False) #replace=True)
choices.extend(choice_list)
print('Number of objects in whitelist: %d' % len(options))
# Compute overall statistics
if not FLAGS.rgb_detection:
print('==== Computing overall statistics for %s ====' % pred_file)
from evaluate import evaluate_predictions, get_ap_info
rec, prec, ap, mean_ap = evaluate_predictions(predictions, dataset, CLASSES,
test_dataset, WHITE_LIST)
ap['Mean AP'] = mean_ap
for classname in ap.keys():
if ap_infos.get(classname) is None: ap_infos[classname] = []
ap_infos[classname].append('%11s: [%.1f]' % (classname, 100. * ap[classname]))
box_iou_sum, seg_iou_sum = 0, 0
for i in range(len(ps_l)):
seg_gt = seg_gt_l[i]
box3d = box3d_l[i]
seg_pred = seg_pred_l[i]
center = center_l[i]
heading_cls = heading_cls_l[i]
heading_res = heading_res_l[i]
size_cls = size_cls_l[i]
size_res = size_res_l[i]
rot_angle = rot_angle_l[i]
gt_box3d = rotate_pc_along_y(np.copy(box3d), rot_angle)
heading_angle = class2angle(heading_cls, heading_res, NUM_HEADING_BIN)
box_size = class2size(size_cls, size_res)
pred_box3d = get_3d_box(box_size, heading_angle, center)
# Box IOU
shift_arr = np.array([4,5,6,7,0,1,2,3])
box_iou3d, _ = box3d_iou(gt_box3d[shift_arr,:], pred_box3d)
# Seg IOU
seg_iou = get_seg_iou(seg_gt, seg_pred, 2)
box_iou_sum += box_iou3d
seg_iou_sum += seg_iou
mean_box_iou = box_iou_sum / len(ps_l)
mean_seg_iou = seg_iou_sum / len(ps_l)
mean_box_ious.append(mean_box_iou)
mean_seg_ious.append(mean_seg_iou)
for i in choices:
row, col = idx // COLS, idx % COLS
idx += 1
ps = ps_l[i]
seg_pred = seg_pred_l[i]
center = center_l[i]
heading_cls = heading_cls_l[i]
heading_res = heading_res_l[i]
size_cls = size_cls_l[i]
size_res = size_res_l[i]
rot_angle = rot_angle_l[i]
score = score_l[i]
cls_type = cls_type_l[i]
file_num = file_num_l[i]
seg_gt = seg_gt_l[i] if not FLAGS.rgb_detection else []
box2d = box2d_l[i]
box3d = box3d_l[i] if not FLAGS.rgb_detection else []
# Visualize point cloud (with and without color)
vtk_pc_wo_col = vis.VtkPointCloud(ps)
vtk_pc = vis.VtkPointCloud(ps, gt_points=seg_gt, pred_points=seg_pred)
vis.vtk_transform_actor(vtk_pc_wo_col.vtk_actor, translate=(SEP*col,SEP*row,0))
vis.vtk_transform_actor(vtk_pc.vtk_actor, translate=(SEP*col,SEP*row,0))
vtk_pcs_wo_col.append(vtk_pc_wo_col.vtk_actor)
vtk_pcs_with_col.append(vtk_pc.vtk_actor)
# Visualize GT 3D box
if FLAGS.rgb_detection:
objects = dataset.get_label_objects(file_num)
calib = dataset.get_calibration(file_num)
for obj in objects:
if obj.classname not in WHITE_LIST: continue
box3d_pts_2d, box3d_pts_3d = compute_box_3d(obj, calib)
box3d_pts_3d = calib.project_upright_depth_to_upright_camera(box3d_pts_3d)
box3d_pts_3d = rotate_pc_along_y(np.copy(box3d_pts_3d), rot_angle)
vtk_box3D = vis.vtk_box_3D(box3d_pts_3d, color=vis.Color.LightGreen)
vis.vtk_transform_actor(vtk_box3D, translate=(SEP*col,SEP*row,0))
vtk_gt_boxes.append(vtk_box3D)
else:
gt_box3d = rotate_pc_along_y(np.copy(box3d), rot_angle)
vtk_gt_box3D = vis.vtk_box_3D(gt_box3d, color=vis.Color.LightGreen)
vis.vtk_transform_actor(vtk_gt_box3D, translate=(SEP*col,SEP*row,0))
vtk_gt_boxes.append(vtk_gt_box3D)
# Visualize Pred 3D box
heading_angle = class2angle(heading_cls, heading_res, NUM_HEADING_BIN)
box_size = class2size(size_cls, size_res)
pred_box3d = get_3d_box(box_size, heading_angle, center)
vtk_pred_box3D = vis.vtk_box_3D(pred_box3d, color=vis.Color.White)
vis.vtk_transform_actor(vtk_pred_box3D, translate=(SEP*col,SEP*row,0))
vtk_pred_boxes.append(vtk_pred_box3D)
# Visualize Images
box2d_col = vis.Color.LightGreen if not FLAGS.rgb_detection else vis.Color.Orange
img_filename = os.path.join(IMG_DIR, '%06d.jpg' % file_num)
vtk_img = vis.vtk_image(img_filename, box2Ds_list=[[box2d]], box2Ds_cols=[box2d_col])
vis.vtk_transform_actor(vtk_img, scale=(IMG_SCALE,IMG_SCALE,IMG_SCALE),
rot=(0,180,180), translate=(-2+SEP*col,2+SEP*row,10))
vtk_imgs.append(vtk_img)
# Other information
classes.append(class2type[cls_type].capitalize())
file_nums.append(str(file_num))
if not FLAGS.rgb_detection:
shift_arr = np.array([4,5,6,7,0,1,2,3])
box_iou3d, _ = box3d_iou(gt_box3d[shift_arr,:], pred_box3d)
box_ious.append(box_iou3d)
seg_iou = get_seg_iou(seg_gt, seg_pred, 2)
seg_ious.append(seg_iou)
# Visualize overall statistics
vtk_texts.extend(vis.vtk_text([('Model: %s' % pred_file.split('/')[-1]) for pred_file in pred_files], arr_type='text', sep=SEP, cols=1, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-14.5,2.5,2)))
vtk_texts.extend(vis.vtk_text(['Mean Box IOU:'] * len(pred_files), arr_type='text', sep=SEP, cols=1, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-14.5,3,2)))
vtk_texts.extend(vis.vtk_text(mean_box_ious, arr_type='float', color=True, sep=SEP, cols=1, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-10,3,2)))
vtk_texts.extend(vis.vtk_text(['Mean Seg IOU:'] * len(pred_files), arr_type='text', sep=SEP, cols=1, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-14.5,3.5,2)))
vtk_texts.extend(vis.vtk_text(mean_seg_ious, arr_type='float', color=True, sep=SEP, cols=1, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-10,3.5,2)))
for i, (cls_name, ap_info) in enumerate(ap_infos.items()):
vtk_texts.extend(vis.vtk_text(ap_info, arr_type='text', color=True, sep=SEP, cols=1, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-14.5,4+i*0.5,2)))
# Visualize text information
vtk_texts.extend(vis.vtk_text(['Class:'] * len(classes), arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-1.5,3,2)))
vtk_texts.extend(vis.vtk_text(classes, arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(0.5,3,2)))
vtk_texts.extend(vis.vtk_text(['File:'] * len(file_nums), arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-1.5,3.5,2)))
vtk_texts.extend(vis.vtk_text(file_nums, arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(0.25,3.5,2)))
if not FLAGS.rgb_detection:
vtk_texts.extend(vis.vtk_text(['Box:'] * len(box_ious), arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-1.5,4,2)))
vtk_texts.extend(vis.vtk_text(box_ious, arr_type='float', color=True, sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(0,4,2)))
vtk_texts.extend(vis.vtk_text(['Seg:'] * len(seg_ious), arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-1.5,4.5,2)))
vtk_texts.extend(vis.vtk_text(seg_ious, arr_type='float', color=True, sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(0,4.5,2)))
key_to_actors_to_hide = { 'g': vtk_gt_boxes, 'p': vtk_pred_boxes, 'i': vtk_imgs, 'c': vtk_pcs_wo_col, 't': vtk_texts }
return vtk_pcs_with_col, key_to_actors_to_hide
def vis_box_pc_dataset(filename, number):
boxpc_dataset = BoxPCFitDataset(classes=WHITE_LIST,
center_perturbation=0.8, size_perturbation=0.2, angle_perturbation=np.pi,
npoints=2048, rotate_to_center=True, random_flip=True, random_shift=True,
overwritten_data_path=filename)
b_data, b_image, b_label, b_center, b_heading_class, b_heading_residual, b_size_class, \
b_size_residual, b_box2d, b_rilts, b_ks, b_rot_angle, b_img_dims, b_one_hot_vec, \
b_new_center, b_new_heading_class, b_new_heading_residual, b_new_size_class, \
b_new_size_residual, b_box_iou, b_y_center_delta, b_y_size_delta, b_y_angle_delta = \
boxpc_dataset.sample_batch(bsize=number, num_point=2048, num_channel=6,
proportion_of_boxpc_fit=0.5,
boxpc_nofit_bounds=[0.01,0.25],
boxpc_fit_bounds=[0.7,1.0], equal_samples_per_class=True)
classes, box_ious = [], []
vtk_pcs_with_col, vtk_gt_boxes, vtk_perb_boxes, vtk_imgs, vtk_pcs_wo_col, vtk_texts = [], [], [], [], [], []
for idx in range(len(b_data)):
row, col = idx // COLS, idx % COLS
cls_type = np.argmax(b_one_hot_vec[idx])
point_set = b_data[idx]
seg_gt = b_label[idx]
iou3d = b_box_iou[idx]
# GT 3D box
center = b_center[idx]
angle_class = b_heading_class[idx]
angle_res = b_heading_residual[idx]
size_cls = b_size_class[idx]
size_res = b_size_residual[idx]
# Perturbed 3D box
new_center = b_new_center[idx]
new_angle_class = b_new_heading_class[idx]
new_angle_res = b_new_heading_residual[idx]
new_size_cls = b_new_size_class[idx]
new_size_res = b_new_size_residual[idx]
# Visualize point cloud (with and without color)
vtk_pc_wo_col = vis.VtkPointCloud(point_set)
vtk_pc = vis.VtkPointCloud(point_set, gt_points=seg_gt)
vis.vtk_transform_actor(vtk_pc_wo_col.vtk_actor, translate=(SEP*col,SEP*row,0))
vis.vtk_transform_actor(vtk_pc.vtk_actor, translate=(SEP*col,SEP*row,0))
vtk_pcs_wo_col.append(vtk_pc_wo_col.vtk_actor)
vtk_pcs_with_col.append(vtk_pc.vtk_actor)
# Visualize GT 3D box
lwh = class2size(size_cls, size_res)
ry = class2angle(angle_class, angle_res, 12)
gt_box3d = get_3d_box(lwh, ry, center)
vtk_gt_box3D = vis.vtk_box_3D(gt_box3d, color=vis.Color.LightGreen)
vis.vtk_transform_actor(vtk_gt_box3D, translate=(SEP*col,SEP*row,0))
vtk_gt_boxes.append(vtk_gt_box3D)
# Visualize Perb 3D box
new_lwh = class2size(new_size_cls, new_size_res)
new_ry = class2angle(new_angle_class, new_angle_res, 12)
perb_box3d = get_3d_box(new_lwh, new_ry, new_center)
vtk_perb_box3D = vis.vtk_box_3D(perb_box3d, color=vis.Color.Blue)
vis.vtk_transform_actor(vtk_perb_box3D, translate=(SEP*col,SEP*row,0))
vtk_perb_boxes.append(vtk_perb_box3D)
# Other information
classes.append(class2type[cls_type].capitalize())
box_iou3d, _ = box3d_iou(gt_box3d, perb_box3d)
print('%d: %.3f, %.3f' % (idx, iou3d, box_iou3d - iou3d))
box_ious.append(iou3d)
# Visualize text information
vtk_texts.extend(vis.vtk_text(['Class:'] * len(classes), arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-1.5,3,2)))
vtk_texts.extend(vis.vtk_text(classes, arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(0.5,3,2)))
vtk_texts.extend(vis.vtk_text(['Box:'] * len(box_ious), arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-1.5,4,2)))
vtk_texts.extend(vis.vtk_text(box_ious, arr_type='float', color=True, sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(0,4,2)))
key_to_actors_to_hide = { 'g': vtk_gt_boxes, 'p': vtk_perb_boxes, 'i': vtk_imgs, 'c': vtk_pcs_wo_col, 't': vtk_texts }
return vtk_pcs_with_col, key_to_actors_to_hide
def vis_seg_box_dataset(filename, number):
rotate_to_center = True
segbox_dataset = ROISegBoxDataset(WHITE_LIST, npoints=2048, split='training',
rotate_to_center=rotate_to_center, random_flip=False, random_shift=False,
overwritten_data_path=filename, from_rgb_detection=FLAGS.rgb_detection)
classes, file_nums = [], []
vtk_pcs_wo_col, vtk_pcs_w_col, vtk_gt_boxes, vtk_imgs, vtk_texts = [], [], [], [], []
#for idx in range(number):
choices = np.random.choice(len(segbox_dataset), number)
choices.sort()
for idx, choice in enumerate(choices):
row, col = idx // COLS, idx % COLS
if FLAGS.rgb_detection:
point_set, img, rot, prob = segbox_dataset[choice]
else:
point_set, img, seg_gt, center, angle_class, angle_res, size_cls, size_res, box2d, rtilt, \
k, rot, img_dims = segbox_dataset[choice]
file_num = segbox_dataset.idx_l[choice]
# Visualize point cloud
vtk_pc_wo_col = vis.VtkPointCloud(point_set)
vtk_pc_w_col = vis.VtkPointCloud(point_set, gt_points=seg_gt)
vis.vtk_transform_actor(vtk_pc_wo_col.vtk_actor, translate=(SEP*col,SEP*row,0))
vis.vtk_transform_actor(vtk_pc_w_col.vtk_actor, translate=(SEP*col,SEP*row,0))
vtk_pcs_wo_col.append(vtk_pc_wo_col.vtk_actor)
vtk_pcs_w_col.append(vtk_pc_w_col.vtk_actor)
# Visualize GT 3D box
if not FLAGS.rgb_detection:
lwh = class2size(size_cls, size_res)
ry = class2angle(angle_class, angle_res, 12)
box3d = get_3d_box(lwh, ry, center)
vtk_box3D = vis.vtk_box_3D(box3d, color=vis.Color.LightGreen)
vis.vtk_transform_actor(vtk_box3D, translate=(SEP*col,SEP*row,0))
vtk_gt_boxes.append(vtk_box3D)
calib = dataset.get_calibration(file_num)
box3d_rot = rotate_pc_along_y(box3d.copy(), -rot)
box3d_pts_3d_orig = calib.project_upright_camera_to_upright_depth(box3d_rot)
box3d_pts_2d, _ = calib.project_upright_depth_to_image(box3d_pts_3d_orig)
# Visualize Images
box2d = segbox_dataset.box2d_l[choice]
box2d_col = vis.Color.LightGreen if not FLAGS.rgb_detection else vis.Color.Orange
img_filename = os.path.join(IMG_DIR, '%06d.jpg' % file_num)
vtk_img = vis.vtk_image(img_filename,
box2Ds_list=[[box2d]], box2Ds_cols=[box2d_col],
proj_box3Ds_list=[box3d_pts_2d],
proj_box3Ds_cols=[vis.Color.LightGreen])
vis.vtk_transform_actor(vtk_img, scale=(IMG_SCALE,IMG_SCALE,IMG_SCALE),
rot=(0,180,180), translate=(-2+SEP*col,2+SEP*row,10))
vtk_imgs.append(vtk_img)
# Text information
classes.append(segbox_dataset.cls_type_l[choice])
file_nums.append(str(file_num))
# Visualize text information
vtk_texts.extend(vis.vtk_text(['Class:'] * len(classes), arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-1.5,3,2)))
vtk_texts.extend(vis.vtk_text(classes, arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(0.5,3,2)))
vtk_texts.extend(vis.vtk_text(['File:'] * len(file_nums), arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(-1.5,3.5,2)))
vtk_texts.extend(vis.vtk_text(file_nums, arr_type='text', sep=SEP, cols=COLS, scale=TEXT_SCALE, rot=TEXT_ROT, translate=(0.25,3.5,2)))
return vtk_pcs_w_col, { 'g': vtk_gt_boxes, 'c': vtk_pcs_wo_col, 'i': vtk_imgs, 't': vtk_texts }
target_obj = obj
break
assert(target_obj is not None)
box3d = TEST_DATASET.get_center_view_box3d(i)
ps = ps_list[i]
segp = segp_list[i].squeeze()
center = center_list[i].squeeze()
ret = TEST_DATASET[i]
rot_angle = ret[7]
# Get heading angle and size
print heading_cls_list[i], heading_res_list[i], size_cls_list[i], size_res_list[i]
heading_angle = roi_seg_box3d_dataset.class2angle(heading_cls_list[i], heading_res_list[i], 12)
box_size = roi_seg_box3d_dataset.class2size(size_cls_list[i], size_res_list[i])
corners_3d_pred = roi_seg_box3d_dataset.get_3d_box(box_size, heading_angle, center)
# NOTE: fix this, box3d (projected from upright_depth coord) has flipped ymin,ymax as that in corners_3d_pred
box3d_new = np.copy(box3d)
box3d_new[0:4,:] = box3d[4:,:]
box3d_new[4:,:] = box3d[0:4,:]
iou_3d, iou_2d = box3d_iou(corners_3d_pred, box3d_new)
print corners_3d_pred
print box3d_new
print 'Ground/3D IoU: ', iou_2d, iou_3d
correct = int(iou_3d >= 0.25)
total_cnt += 1
correct_cnt += correct
class_total_cnt[classname] += 1
class_correct_cnt[classname] += correct
def get_box3d_iou(center_A, box_size_A, heading_angle_A, center_B, box_size_B, heading_angle_B):
corners_3d_A = get_3d_box(box_size_A, heading_angle_A, center_A)
corners_3d_B = get_3d_box(box_size_B, heading_angle_B, center_B)
iou_3d, iou_2d = box3d_iou(corners_3d_A, corners_3d_B)
return iou_3d, iou_2d
