def evaluate(options):
start_time_1 = time.time()
config = InferenceConfig(options)
config.FITTING_TYPE = options.numAnchorPlanes
if options.dataset == '':
dataset = PlaneDataset(options,
config,
split='test',
random=False,
load_semantics=False)
elif options.dataset == 'occlusion':
config_dataset = copy.deepcopy(config)
config_dataset.OCCLUSION = False
dataset = PlaneDataset(options,
config_dataset,
split='test',
random=False,
load_semantics=True)
elif 'nyu' in options.dataset:
dataset = NYUDataset(options, config, split='val', random=False)
elif options.dataset == 'synthia':
dataset = SynthiaDataset(options, config, split='val', random=False)
elif options.dataset == 'kitti':
camera = np.zeros(6)
camera[0] = 9.842439e+02
camera[1] = 9.808141e+02
camera[2] = 6.900000e+02
camera[3] = 2.331966e+02
camera[4] = 1242
camera[5] = 375
dataset = InferenceDataset(
options,
config,
image_list=glob.glob('../../Data/KITTI/scene_3/*.png'),
camera=camera)
elif options.dataset == '7scene':
camera = np.zeros(6)
camera[0] = 519
camera[1] = 519
camera[2] = 320
camera[3] = 240
camera[4] = 640
camera[5] = 480
dataset = InferenceDataset(
options,
config,
image_list=glob.glob('../../Data/SevenScene/scene_3/*.png'),
camera=camera)
elif options.dataset == 'tanktemple':
camera = np.zeros(6)
camera[0] = 0.7
camera[1] = 0.7
camera[2] = 0.5
camera[3] = 0.5
camera[4] = 1
camera[5] = 1
dataset = InferenceDataset(
options,
config,
image_list=glob.glob('../../Data/TankAndTemple/scene_4/*.jpg'),
camera=camera)
elif options.dataset == 'make3d':
camera = np.zeros(6)
camera[0] = 0.7
camera[1] = 0.7
camera[2] = 0.5
camera[3] = 0.5
camera[4] = 1
camera[5] = 1
dataset = InferenceDataset(
options,
config,
image_list=glob.glob('../../Data/Make3D/*.jpg'),
camera=camera)
elif options.dataset == 'popup':
camera = np.zeros(6)
camera[0] = 0.7
camera[1] = 0.7
camera[2] = 0.5
camera[3] = 0.5
camera[4] = 1
camera[5] = 1
dataset = InferenceDataset(
options,
config,
image_list=glob.glob('../../Data/PhotoPopup/*.jpg'),
camera=camera)
elif options.dataset == 'cross' or options.dataset == 'cross_2':
image_list = [
'test/cross_dataset/' + str(c) + '_image.png' for c in range(12)
]
cameras = []
camera = np.zeros(6)
camera[0] = 587
camera[1] = 587
camera[2] = 320
camera[3] = 240
camera[4] = 640
camera[5] = 480
for c in range(4):
cameras.append(camera)
continue
camera_kitti = np.zeros(6)
camera_kitti[0] = 9.842439e+02
camera_kitti[1] = 9.808141e+02
camera_kitti[2] = 6.900000e+02
camera_kitti[3] = 2.331966e+02
camera_kitti[4] = 1242.0
camera_kitti[5] = 375.0
for c in range(2):
cameras.append(camera_kitti)
continue
camera_synthia = np.zeros(6)
camera_synthia[0] = 133.185088
camera_synthia[1] = 134.587036
camera_synthia[2] = 160.000000
camera_synthia[3] = 96.000000
camera_synthia[4] = 320
camera_synthia[5] = 192
for c in range(2):
cameras.append(camera_synthia)
continue
camera_tanktemple = np.zeros(6)
camera_tanktemple[0] = 0.7
camera_tanktemple[1] = 0.7
camera_tanktemple[2] = 0.5
camera_tanktemple[3] = 0.5
camera_tanktemple[4] = 1
camera_tanktemple[5] = 1
for c in range(2):
cameras.append(camera_tanktemple)
continue
for c in range(2):
cameras.append(camera)
continue
dataset = InferenceDataset(options,
config,
image_list=image_list,
camera=cameras)
elif options.dataset == 'selected':
image_list = glob.glob('test/selected_images/*_image_0.png')
image_list = [
filename for filename in image_list
if '63_image' not in filename and '77_image' not in filename
] + [
filename for filename in image_list
if '63_image' in filename or '77_image' in filename
]
camera = np.zeros(6)
camera[0] = 587
camera[1] = 587
camera[2] = 320
camera[3] = 240
camera[4] = 640
camera[5] = 480
dataset = InferenceDataset(options,
config,
image_list=image_list,
camera=camera)
elif options.dataset == 'comparison':
image_list = [
'test/comparison/' + str(index) + '_image_0.png'
for index in [65, 11, 24]
]
camera = np.zeros(6)
camera[0] = 587
camera[1] = 587
camera[2] = 320
camera[3] = 240
camera[4] = 640
camera[5] = 480
dataset = InferenceDataset(options,
config,
image_list=image_list,
camera=camera)
elif 'inference' in options.dataset:
image_list = glob.glob(options.customDataFolder +
'/*.png') + glob.glob(options.customDataFolder +
'/*.jpg')
if os.path.exists(options.customDataFolder + '/camera.txt'):
camera = np.zeros(6)
with open(options.customDataFolder + '/camera.txt', 'r') as f:
for line in f:
values = [
float(token.strip()) for token in line.split(' ')
if token.strip() != ''
]
for c in range(6):
camera[c] = values[c]
continue
break
pass
else:
camera = [
filename.replace('.png', '.txt').replace('.jpg', '.txt')
for filename in image_list
]
pass
dataset = InferenceDataset(options,
config,
image_list=image_list,
camera=camera)
pass
print('the number of images', len(dataset))
dataloader = DataLoader(dataset,
batch_size=1,
shuffle=False,
num_workers=1)
epoch_losses = []
data_iterator = tqdm(dataloader, total=len(dataset))
specified_suffix = options.suffix
with torch.no_grad():
detectors = []
for method in options.methods:
if method == 'w':
options.suffix = 'pair_' + specified_suffix if specified_suffix != '' else 'pair'
detectors.append(('warping',
PlaneRCNNDetector(options,
config,
modelType='pair')))
elif method == 'b':
options.suffix = specified_suffix if specified_suffix != '' else ''
detectors.append(('basic',
PlaneRCNNDetector(options,
config,
modelType='pair')))
elif method == 'o':
options.suffix = 'occlusion_' + specified_suffix if specified_suffix != '' else 'occlusion'
detectors.append(('occlusion',
PlaneRCNNDetector(options,
config,
modelType='occlusion')))
elif method == 'p':
detectors.append(
('planenet', PlaneNetDetector(options, config)))
elif method == 'e':
detectors.append(
('planerecover', PlaneRecoverDetector(options, config)))
elif method == 't':
if 'gt' in options.suffix:
detectors.append(
('manhattan_gt',
TraditionalDetector(options, config, 'manhattan_gt')))
else:
detectors.append(
('manhattan_pred',
TraditionalDetector(options, config,
'manhattan_pred')))
pass
elif method == 'n':
options.suffix = specified_suffix if specified_suffix != '' else ''
detectors.append(('non_planar',
DepthDetector(options,
config,
modelType='np')))
elif method == 'r':
options.suffix = specified_suffix if specified_suffix != '' else ''
detectors.append(('refine',
PlaneRCNNDetector(options,
config,
modelType='refine')))
elif method == 's':
options.suffix = specified_suffix if specified_suffix != '' else ''
detectors.append(
('refine_single',
PlaneRCNNDetector(options,
config,
modelType='refine_single')))
elif method == 'f':
options.suffix = specified_suffix if specified_suffix != '' else ''
detectors.append(('final',
PlaneRCNNDetector(options,
config,
modelType='final')))
pass
continue
pass
if not options.debug:
for method_name in [detector[0] for detector in detectors]:
os.system('rm ' + options.test_dir + '/*_' + method_name + '.png')
continue
pass
all_statistics = []
for name, detector in detectors:
statistics = [[], [], [], []]
for sampleIndex, sample in enumerate(data_iterator):
if options.testingIndex >= 0 and sampleIndex != options.testingIndex:
if sampleIndex > options.testingIndex:
break
continue
input_pair = []
camera = sample[30][0].cuda()
for indexOffset in [
0,
]:
images, image_metas, rpn_match, rpn_bbox, gt_class_ids, gt_boxes, gt_masks, gt_parameters, gt_depth, extrinsics, planes, gt_segmentation = sample[
indexOffset +
0].cuda(), sample[indexOffset + 1].numpy(), sample[
indexOffset +
2].cuda(), sample[indexOffset + 3].cuda(), sample[
indexOffset +
4].cuda(), sample[indexOffset + 5].cuda(), sample[
indexOffset +
6].cuda(), sample[indexOffset + 7].cuda(
), sample[indexOffset + 8].cuda(), sample[
indexOffset + 9].cuda(), sample[
indexOffset +
10].cuda(), sample[indexOffset +
11].cuda()
masks = (
gt_segmentation == torch.arange(gt_segmentation.max() +
1).cuda().view(-1, 1,
1)).float()
input_pair.append({
'image': images,
'depth': gt_depth,
'bbox': gt_boxes,
'extrinsics': extrinsics,
'segmentation': gt_segmentation,
'camera': camera,
'plane': planes[0],
'masks': masks,
'mask': gt_masks
})
continue
if sampleIndex >= options.numTestingImages:
break
with torch.no_grad():
detection_pair = detector.detect(sample)
pass
if options.dataset == 'rob':
depth = detection_pair[0]['depth'].squeeze().detach().cpu(
).numpy()
os.system('rm ' +
image_list[sampleIndex].replace('color', 'depth'))
depth_rounded = np.round(depth * 256)
depth_rounded[np.logical_or(depth_rounded < 0,
depth_rounded >= 256 * 256)] = 0
cv2.imwrite(
image_list[sampleIndex].replace('color', 'depth').replace(
'jpg', 'png'), depth_rounded.astype(np.uint16))
continue
if 'inference' not in options.dataset:
for c in range(len(input_pair)):
evaluateBatchDetection(
options,
config,
input_pair[c],
detection_pair[c],
statistics=statistics,
printInfo=options.debug,
evaluate_plane=options.dataset == '')
continue
else:
for c in range(len(detection_pair)):
np.save(
options.test_dir + '/' + str(sampleIndex % 500) +
'_plane_parameters_' + str(c) + '.npy',
detection_pair[c]['detection'][:, 6:9])
np.save(
options.test_dir + '/' + str(sampleIndex % 500) +
'_plane_masks_' + str(c) + '.npy',
detection_pair[c]['masks'][:, 80:560])
continue
pass
if sampleIndex < 30 or options.debug or options.dataset != '':
visualizeBatchPair(options,
config,
input_pair,
detection_pair,
indexOffset=sampleIndex % 500,
suffix='_' + name + options.modelType,
write_ply=options.testingIndex >= 0,
write_new_view=options.testingIndex >= 0
and 'occlusion' in options.suffix)
pass
if sampleIndex >= options.numTestingImages:
break
continue
if 'inference' not in options.dataset:
options.keyname = name
printStatisticsDetection(options, statistics)
all_statistics.append(statistics)
pass
continue
if 'inference' not in options.dataset:
if options.debug and len(detectors) > 1:
all_statistics = np.concatenate([
np.arange(len(all_statistics[0][0])).reshape((-1, 1)),
] + [np.array(statistics[3]) for statistics in all_statistics],
axis=-1)
print(all_statistics.astype(np.int32))
pass
if options.testingIndex == -1:
np.save('logs/all_statistics.npy', all_statistics)
pass
pass
info = np.array([1.82e+03, 0.00e+00, 1.63e+03, 0.00e+00,\
0.00e+00, 1.82e+03, 1.22e+03, 0.00e+00, 0.00e+00, 0.00e+00, \
1.00e+00, 0.00e+00, 0.00e+00, 0.00e+00, 0.00e+00, 1.00e+00, 3.26e+03, 2.45e+03,\
1.00e+03,5.00e+00])
image = cv2.imread(
"test/inference_debug/0_segmentation_0_final.png") #x,x,3
depth = cv2.imread("test/inference_debug/0_depth_0_final_ori.png", 0) #x,x
segmentation = cv2.imread(
"test/inference_debug/0_segmentation_0_final.png", 0) #change it
depth_final = cv2.imread(
"test/inference_debug/0_depth_0_final_ori.png") #x,x
planes = np.load("test/inference_debug/0_plane_parameters_0.npy"
) #change if its not working
original = cv2.imread("demostore/phsample.png")
print(original.shape)
print(depth_final.shape)
print(image.shape)
image_c = np.concatenate((original, depth_final, image), axis=1)
cv2.imwrite("output.png", image_c)
# folder = "genrate_3dmodel/predict3dfol"
index = 0
image_c_written = cv2.imread("output.png")
cv2.imshow("output", image_c_written)
cv2.waitKey(0)
cv2.destroyAllWindows()
print("segmentation time through model done in %s seconds " %
(time.time() - start_time_1))
#predict3D(folder, index, image, depth, segmentation, planes, info)
#print("3d model time through model done in %s seconds "% (time.time() - start_time_1))
filename = 'test/inference_debug/0_model_0_final.ply'
print(filename)
mesh = pv.read(filename)
cpos = mesh.plot()
plotter = pv.Plotter(off_screen=True)
plotter.add_mesh(mesh)
plotter.show(screenshot="myscreenshot.png")
return
class PlaneRecoverDetector():
def __init__(self, options, config, checkpoint_dir=''):
self.options = options
self.config = config
sys.path.append('../../existing_methods/')
from planerecover_ori.inference import PlaneRecoverDetector
self.detector = PlaneRecoverDetector()
return
def detect(self, sample):
detection_pair = []
camera = sample[30][0].cuda()
for indexOffset in [
0,
]:
images, image_metas, rpn_match, rpn_bbox, gt_class_ids, gt_boxes, gt_masks, gt_parameters, gt_depth, extrinsics, planes, gt_segmentation = sample[
indexOffset +
0].cuda(), sample[indexOffset + 1].numpy(), sample[
indexOffset +
2].cuda(), sample[indexOffset + 3].cuda(), sample[
indexOffset +
4].cuda(), sample[indexOffset + 5].cuda(), sample[
indexOffset +
6].cuda(), sample[indexOffset + 7].cuda(), sample[
indexOffset +
8].cuda(), sample[indexOffset + 9].cuda(
), sample[indexOffset +
10].cuda(), sample[indexOffset +
11].cuda()
image = (images[0].detach().cpu().numpy().transpose(
(1, 2, 0)) + self.config.MEAN_PIXEL)[80:560]
pred_dict = self.detector.detect(image)
segmentation = pred_dict['segmentation']
segmentation = np.concatenate([
np.full(
(80, 640), fill_value=-1, dtype=np.int32), segmentation,
np.full((80, 640), fill_value=-1, dtype=np.int32)
],
axis=0)
planes = pred_dict['plane']
masks = (segmentation == np.arange(len(planes),
dtype=np.int32).reshape(
(-1, 1,
1))).astype(np.float32)
detections = np.concatenate(
[np.ones((len(planes), 4)),
np.ones((len(planes), 2)), planes],
axis=-1)
detections = torch.from_numpy(detections).float().cuda()
masks = torch.from_numpy(masks).float().cuda()
XYZ_pred, detection_mask, plane_XYZ = calcXYZModule(
self.config,
camera,
detections,
masks,
torch.zeros((1, 640, 640)).cuda(),
return_individual=True)
depth = XYZ_pred[1:2]
print(planes)
print(np.unique(segmentation))
for mask_index, mask in enumerate(masks.detach().cpu().numpy()):
cv2.imwrite('test/mask_' + str(mask_index) + '.png',
drawMaskImage(mask))
continue
detection_pair.append({
'depth': depth,
'mask': masks.sum(0, keepdim=True),
'masks': masks,
'detection': detections
})
continue
return detection_pair