def multiview_debug_save_v2(save_dir, base, names, images, points, rev_points):
save_dir.mkdir(parents=True, exist_ok=True)
for index, (name, image) in enumerate(zip(names, images)):
_points = points[index].transpose(1, 0)
pil_img = draw_image_by_points(image, _points, 2, (255, ), False,
False, False)
pil_img.save(str(save_dir / '{:}-trans-x-{:}'.format(base, name)))
_points = rev_points[index].transpose(1, 0)
pil_img = draw_image_by_points(image, _points, 2, (0, ), False, False,
False)
pil_img.save(str(save_dir / '{:}-trans-p-{:}'.format(base, name)))
def multiview_debug_save(save_dir, base, image_paths, points, rev_points):
save_dir.mkdir(parents=True, exist_ok=True)
images = [pil_loader(x) for x in image_paths]
names = [Path(x).name for x in image_paths]
for index, (name, image) in enumerate(zip(names, images)):
_points = points[index].transpose(1, 0)
pil_img = draw_image_by_points(image, _points, 2, (102, 255, 102),
False, False, False)
pil_img.save(str(save_dir / '{:}-ori-x-{:}'.format(base, name)))
_points = rev_points[index].transpose(1, 0)
pil_img = draw_image_by_points(image, _points, 2, (30, 144, 255),
False, False, False)
pil_img.save(str(save_dir / '{:}-ori-p-{:}'.format(base, name)))
def main(save_dir, meta, mindex, maximum):
save_dir = Path(save_dir)
save_dir.mkdir(parents=True, exist_ok=True)
assert osp.isfile(meta), 'invalid meta file : {:}'.format(meta)
checkpoint = torch.load(meta)
xmeta = checkpoint[mindex]
RED, GREEN, BLUE = (255, 0, 0), (0, 255, 0), (0, 0, 255)
random.seed(111)
index_list = list(range(len(xmeta)))
random.shuffle(index_list)
for i in range(0, min(maximum, len(xmeta))):
index = index_list[i]
image, predicts, gts = xmeta[index]
crop_box = get_box(gts)
num_pts = predicts.shape[1]
predicts, gts = torch.Tensor(predicts), torch.Tensor(gts)
avaliable = gts[2, :] == 1
predicts, gts = predicts[:2, avaliable], gts[:2, avaliable]
colors = [BLUE for _ in range(avaliable.sum().item())
] + [GREEN for _ in range(avaliable.sum().item())]
points = torch.cat((gts, predicts), dim=1)
image = draw_image_by_points(image, points, 3, colors, crop_box,
(400, 500))
image.save('{:}/image-{:05d}.png'.format(save_dir, index))
print('save into {:}'.format(save_dir))
def evaluate(args):
assert torch.cuda.is_available(), 'CUDA is not available.'
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
print ('The image is {:}'.format(args.image))
print ('The model is {:}'.format(args.model))
snapshot = Path(args.model)
assert snapshot.exists(), 'The model path {:} does not exist'
print ('The face bounding box is {:}'.format(args.face))
assert len(args.face) == 4, 'Invalid face input : {:}'.format(args.face)
snapshot = torch.load(snapshot)
# General Data Argumentation
mean_fill = tuple( [int(x*255) for x in [0.485, 0.456, 0.406] ] )
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
param = snapshot['args']
import pdb; pdb.set_trace()
eval_transform = transforms.Compose([transforms.PreCrop(param.pre_crop_expand), transforms.TrainScale2WH((param.crop_width, param.crop_height)), transforms.ToTensor(), normalize])
model_config = load_configure(param.model_config, None)
dataset = Dataset(eval_transform, param.sigma, model_config.downsample, param.heatmap_type, param.data_indicator)
dataset.reset(param.num_pts)
net = obtain_model(model_config, param.num_pts + 1)
net = net.cuda()
weights = remove_module_dict(snapshot['detector'])
net.load_state_dict(weights)
print ('Prepare input data')
[image, _, _, _, _, _, cropped_size], meta = dataset.prepare_input(args.image, args.face)
inputs = image.unsqueeze(0).cuda()
# network forward
with torch.no_grad():
batch_heatmaps, batch_locs, batch_scos = net(inputs)
# obtain the locations on the image in the orignial size
cpu = torch.device('cpu')
np_batch_locs, np_batch_scos, cropped_size = batch_locs.to(cpu).numpy(), batch_scos.to(cpu).numpy(), cropped_size.numpy()
locations, scores = np_batch_locs[0,:-1,:], np.expand_dims(np_batch_scos[0,:-1], -1)
scale_h, scale_w = cropped_size[0] * 1. / inputs.size(-2) , cropped_size[1] * 1. / inputs.size(-1)
locations[:, 0], locations[:, 1] = locations[:, 0] * scale_w + cropped_size[2], locations[:, 1] * scale_h + cropped_size[3]
prediction = np.concatenate((locations, scores), axis=1).transpose(1,0)
print ('the coordinates for {:} facial landmarks:'.format(param.num_pts))
for i in range(param.num_pts):
point = prediction[:, i]
print ('the {:02d}/{:02d}-th point : ({:.1f}, {:.1f}), score = {:.2f}'.format(i, param.num_pts, float(point[0]), float(point[1]), float(point[2])))
if args.save:
resize = 512
image = draw_image_by_points(args.image, prediction, 2, (255, 0, 0), args.face, resize)
image.save(args.save)
print ('save the visualization results into {:}'.format(args.save))
else:
print ('ignore the visualization procedure')
def evaluate(args):
assert torch.cuda.is_available(), 'CUDA is not available.'
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
print ('The image is {:}'.format(args.image))
print ('The model is {:}'.format(args.model))
snapshot = Path(args.model)
assert snapshot.exists(), 'The model path {:} does not exist'
print ('The face bounding box is {:}'.format(args.face))
assert len(args.face) == 4, 'Invalid face input : {:}'.format(args.face)
snapshot = torch.load(snapshot)
# General Data Argumentation
mean_fill = tuple( [int(x*255) for x in [0.485, 0.456, 0.406] ] )
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
param = snapshot['args']
eval_transform = transforms.Compose([transforms.PreCrop(param.pre_crop_expand), transforms.TrainScale2WH((param.crop_width, param.crop_height)), transforms.ToTensor(), normalize])
model_config = load_configure(param.model_config, None)
dataset = Dataset(eval_transform, param.sigma, model_config.downsample, param.heatmap_type, param.data_indicator)
dataset.reset(param.num_pts)
net = obtain_model(model_config, param.num_pts + 1)
net = net.cuda()
weights = remove_module_dict(snapshot['state_dict'])
net.load_state_dict(weights)
print ('Prepare input data')
[image, _, _, _, _, _, cropped_size], meta = dataset.prepare_input(args.image, args.face)
inputs = image.unsqueeze(0).cuda()
# network forward
with torch.no_grad():
batch_heatmaps, batch_locs, batch_scos = net(inputs)
# obtain the locations on the image in the orignial size
cpu = torch.device('cpu')
np_batch_locs, np_batch_scos, cropped_size = batch_locs.to(cpu).numpy(), batch_scos.to(cpu).numpy(), cropped_size.numpy()
locations, scores = np_batch_locs[0,:-1,:], np.expand_dims(np_batch_scos[0,:-1], -1)
scale_h, scale_w = cropped_size[0] * 1. / inputs.size(-2) , cropped_size[1] * 1. / inputs.size(-1)
locations[:, 0], locations[:, 1] = locations[:, 0] * scale_w + cropped_size[2], locations[:, 1] * scale_h + cropped_size[3]
prediction = np.concatenate((locations, scores), axis=1).transpose(1,0)
print ('the coordinates for {:} facial landmarks:'.format(param.num_pts))
for i in range(param.num_pts):
point = prediction[:, i]
print ('the {:02d}/{:02d}-th point : ({:.1f}, {:.1f}), score = {:.2f}'.format(i, param.num_pts, float(point[0]), float(point[1]), float(point[2])))
if args.save:
resize = 512
image = draw_image_by_points(args.image, prediction, 2, (255, 0, 0), args.face, resize)
image.save(args.save)
print ('save the visualization results into {:}'.format(args.save))
else:
print ('ignore the visualization procedure')
def __getitem__(self, index):
assert index >= 0 and index < self.length, 'Invalid index : {:}'.format(
index)
image_path, points = self.all_image_ps[index], self.all_results[index]
ctr_x, ctr_y = self.get_center(index)
W, H = self.crop_size, self.crop_size
image = draw_image_by_points(
image_path, points, 2, self.color,
[ctr_x - W, ctr_y - H, ctr_x + W, ctr_y + H], False)
image.save(str(self.save_dir / image_path.split('/')[-1]))
return index
def evaluate(args):
assert torch.cuda.is_available(), 'CUDA is not available.'
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
print('The image is {:}'.format(args.image))
print('The face bounding box is {:}'.format(args.face))
assert len(args.face) == 4, 'Invalid face input : {:}'.format(args.face)
# General Data Argumentation
print('Prepare input data')
[image, _, _, _, _, _,
cropped_size], meta = dataset.prepare_input(args.image, args.face)
# network forward
with torch.no_grad():
inputs = image.unsqueeze(0).cuda()
batch_heatmaps, batch_locs, batch_scos = net(inputs)
flops, params = get_model_infos(net, inputs.shape)
print('IN-shape : {:}, FLOPs : {:} MB, Params : {:} MB'.format(
list(inputs.shape), flops, params))
# obtain the locations on the image in the orignial size
cpu = torch.device('cpu')
np_batch_locs, np_batch_scos, cropped_size = batch_locs.to(
cpu).numpy(), batch_scos.to(cpu).numpy(), cropped_size.numpy()
locations, scores = np_batch_locs[0, :-1, :], np.expand_dims(
np_batch_scos[0, :-1], -1)
scale_h, scale_w = cropped_size[0] * 1. / \
inputs.size(-2), cropped_size[1] * 1. / inputs.size(-1)
locations[:, 0], locations[:, 1] = locations[:, 0] * scale_w + \
cropped_size[2], locations[:, 1] * scale_h + cropped_size[3]
prediction = np.concatenate((locations, scores), axis=1).transpose(1, 0)
print('the coordinates for {:} facial landmarks:'.format(param.num_pts))
for i in range(param.num_pts):
point = prediction[:, i]
print('the {:02d}/{:02d}-th point : ({:.1f}, {:.1f}), score = {:.2f}'.
format(i, param.num_pts, float(point[0]), float(point[1]),
float(point[2])))
if args.save:
resize = 0
image = draw_image_by_points(args.image, prediction, 2, (255, 0, 0),
args.face, resize)
image.save(args.save)
print('save the visualization results into {:}'.format(args.save))
else:
print('ignore the visualization procedure')
def main(use_gray, transform_strs):
if not use_gray:
mean_fill = tuple([int(x * 255) for x in [0.485, 0.456, 0.406]])
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
normalize = transforms.Normalize(mean=[0, 0, 0], std=[1, 1, 1])
color = (102, 255, 102)
else:
mean_fill = (0.5, )
normalize = transforms.Normalize(mean=[mean_fill[0]], std=[0.5])
normalize = transforms.Normalize(mean=[0], std=[1])
color = (255, )
debug_dir = '{:}/cache/gray-{:}'.format(this_dir, use_gray)
if not os.path.isdir(debug_dir):
os.makedirs(debug_dir)
transform_funcs = [transforms.ToTensor(), normalize
] + get_transforms(transform_strs)
transform = transforms.Compose(transform_funcs)
shape = (300, 200)
images, labels, boxes = get_list()
for image, label, box in zip(images, labels, boxes):
imgx = datasets.pil_loader(image, use_gray)
np_points, _ = datasets.anno_parser(label, 68)
meta = Point_Meta(68, np_points, box, image, 'face68')
I, L, theta = transform(imgx, meta)
points = torch.Tensor(L.get_points(True))
points = normalize_points((I.size(1), I.size(2)), points)
name = Path(image).name
image = get_image_from_affine(I, theta, shape)
points = torch.cat((points, torch.ones((1, points.shape[1]))), dim=0)
# new_points, LU = torch.gesv(points, theta)
new_points, _ = torch.solve(points, theta)
PImage = draw_image_by_points(image,
new_points[:2, :],
2,
color,
False,
False,
True,
draw_idx=True)
save_name = os.path.join(debug_dir,
'{:}-{:}'.format(transform_strs, name))
PImage.save(save_name)
def pro_debug_save(save_dir, name, image, heatmap, normpoint, meantheta,
predmap, recover):
name, ext = name.split('.')
save_dir.mkdir(parents=True, exist_ok=True)
C, H, W = image.size()
oriimage = recover(image)
oriimage.save(str(save_dir / '{:}-ori.{:}'.format(name, ext)))
if C == 1: color = (255, )
else: color = (102, 255, 102)
ptsimage = draw_image_by_points(oriimage, normpoint, 2, color, False,
False, True)
ptsimage.save(str(save_dir / '{:}-pts.{:}'.format(name, ext)))
meanI = affine2image(image, meantheta, (H, W))
meanimg = recover(meanI)
meanimg.save(str(save_dir / '{:}-tomean.{:}'.format(name, ext)))
_save_heatmap(oriimage, heatmap, save_dir, name, ext, 'GT')
_save_heatmap(oriimage, predmap, save_dir, name, ext, 'PD')
def visualize(args):
print ('The result file is {:}'.format(args.meta))
print ('The save path is {:}'.format(args.save))
meta = Path(args.meta)
save = Path(args.save)
assert meta.exists(), 'The model path {:} does not exist'
xmeta = Eval_Meta()
xmeta.load(meta)
print ('this meta file has {:} predictions'.format(len(xmeta)))
if not save.exists(): os.makedirs( args.save )
for i in range(len(xmeta)):
image, prediction = xmeta.image_lists[i], xmeta.predictions[i]
name = osp.basename(image)
image = draw_image_by_points(image, prediction, 2, (255, 0, 0), False, False)
path = save / name
image.save(path)
print ('{:03d}-th image is saved into {:}'.format(i, path))
def visualize(args):
print ('The result file is {:}'.format(args.meta))
print ('The save path is {:}'.format(args.save))
meta = Path(args.meta)
save = Path(args.save)
assert meta.exists(), 'The model path {:} does not exist'
xmeta = Eval_Meta()
xmeta.load(meta)
print ('this meta file has {:} predictions'.format(len(xmeta)))
if not save.exists(): os.makedirs( args.save )
for i in range(len(xmeta)):
image, prediction = xmeta.image_lists[i], xmeta.predictions[i]
name = osp.basename(image)
image = draw_image_by_points(image, prediction, 6, (255, 0, 0), False, False)
path = save / name
image.save(path)
print ('{:03d}-th image is saved into {:}'.format(i, path))
def visualize(args):
print('The result file is {:}'.format(args.meta))
print('The save path is {:}'.format(args.save))
meta = Path(args.meta)
save = Path(args.save)
assert meta.exists(), 'The model path {:} does not exist'
eval_metas = torch.load(meta)
print('There are {:} evaluation results and use {:}.'.format(
len(eval_metas), args.idx))
xmeta = eval_metas[args.idx]
print('this meta file has {:} predictions'.format(len(xmeta)))
if not save.exists(): save.mkdir(parents=True, exist_ok=True)
for i in range(len(xmeta)):
image, prediction = xmeta.image_lists[i], xmeta.predictions[i]
name = osp.basename(image)
image = draw_image_by_points(image, prediction, 2, (255, 0, 0), False,
False)
path = save / name
image.save(path)
print('[{:02d}] {:03d}/{:03d}-th image is saved into {:}'.format(
args.idx, i, len(xmeta), path))
def evaluate(args):
if args.cuda:
assert torch.cuda.is_available(), 'CUDA is not available.'
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
else:
print('Use the CPU mode')
print('The image is {:}'.format(args.image))
print('The model is {:}'.format(args.model))
last_info = Path(args.model)
assert last_info.exists(), 'The model path {:} does not exist'.format(
last_info)
last_info = torch.load(last_info, map_location=torch.device('cpu'))
snapshot = last_info['last_checkpoint']
assert snapshot.exists(), 'The model path {:} does not exist'.format(
snapshot)
print('The face bounding box is {:}'.format(args.face))
assert len(args.face) == 4, 'Invalid face input : {:}'.format(args.face)
snapshot = torch.load(snapshot, map_location=torch.device('cpu'))
param = snapshot['args']
# General Data Argumentation
if param.use_gray == False:
mean_fill = tuple([int(x * 255) for x in [0.485, 0.456, 0.406]])
normalize = transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
else:
mean_fill = (0.5, )
normalize = transforms.Normalize(mean=[mean_fill[0]], std=[0.5])
eval_transform = transforms.Compose2V([transforms.ToTensor(), normalize, \
transforms.PreCrop(param.pre_crop_expand), \
transforms.CenterCrop(param.crop_max)])
model_config = load_configure(param.model_config, None)
dataset = Dataset(eval_transform, param.sigma, model_config.downsample,
param.heatmap_type, (120, 96), param.use_gray, None,
param.data_indicator)
#dataset = Dataset(eval_transform, param.sigma, model_config.downsample, param.heatmap_type, (param.height,param.width), param.use_gray, None, param.data_indicator)
dataset.reset(param.num_pts)
net = obtain_pro_model(model_config, param.num_pts + 1, param.sigma,
param.use_gray)
net.load_state_dict(remove_module_dict(snapshot['state_dict']))
if args.cuda: net = net.cuda()
print('Processing the input face image.')
face_meta = PointMeta(dataset.NUM_PTS, None, args.face, args.image,
'BASE-EVAL')
face_img = pil_loader(args.image, dataset.use_gray)
affineImage, heatmaps, mask, norm_trans_points, transthetas, _, _, _, shape = dataset._process_(
face_img, face_meta, -1)
#import cv2; cv2.imwrite('temp.png', transforms.ToPILImage(normalize, False)(affineImage))
# network forward
with torch.no_grad():
if args.cuda: inputs = affineImage.unsqueeze(0).cuda()
else: inputs = affineImage.unsqueeze(0)
_, _, batch_locs, batch_scos = net(inputs)
batch_locs, batch_scos = batch_locs.cpu(), batch_scos.cpu()
(batch_size, C, H, W), num_pts = inputs.size(), param.num_pts
locations, scores = batch_locs[0, :-1, :], batch_scos[:, :-1]
norm_locs = normalize_points((H, W), locations.transpose(1, 0))
norm_locs = torch.cat((norm_locs, torch.ones(1, num_pts)), dim=0)
transtheta = transthetas[:2, :]
norm_locs = torch.mm(transtheta, norm_locs)
real_locs = denormalize_points(shape.tolist(), norm_locs)
real_locs = torch.cat((real_locs, scores), dim=0)
print('the coordinates for {:} facial landmarks:'.format(param.num_pts))
for i in range(param.num_pts):
point = real_locs[:, i]
print(
'the {:02d}/{:02d}-th landmark : ({:.1f}, {:.1f}), score = {:.2f}'.
format(i, param.num_pts, float(point[0]), float(point[1]),
float(point[2])))
if args.save:
resize = 512
image = draw_image_by_points(args.image, real_locs, 2, (255, 0, 0),
args.face, resize)
image.save(args.save)
print('save the visualization results into {:}'.format(args.save))
else:
print('ignore the visualization procedure')
def main(args):
assert torch.cuda.is_available(), 'CUDA is not available.'
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
torch.set_num_threads(args.workers)
print('Training Base Detector : prepare_seed : {:}'.format(args.rand_seed))
prepare_seed(args.rand_seed)
temporal_main, eval_all = procedures['{:}-train'.format(
args.procedure)], procedures['{:}-test'.format(args.procedure)]
logger = prepare_logger(args)
# General Data Argumentation
normalize, train_transform, eval_transform, robust_transform = prepare_data_augmentation(
transforms, args)
recover = transforms.ToPILImage(normalize)
args.tensor2imageF = recover
assert (args.scale_min +
args.scale_max) / 2 == 1, 'The scale is not ok : {:} ~ {:}'.format(
args.scale_min, args.scale_max)
# Model Configure Load
model_config = load_configure(args.model_config, logger)
sbr_config = load_configure(args.sbr_config, logger)
shape = (args.height, args.width)
logger.log('--> {:}\n--> Sigma : {:}, Shape : {:}'.format(
model_config, args.sigma, shape))
logger.log('--> SBR Configuration : {:}\n'.format(sbr_config))
# Training Dataset
train_data = VDataset(eval_transform, args.sigma, model_config.downsample, args.heatmap_type, shape, args.use_gray, args.mean_point, \
args.data_indicator, sbr_config, transforms.ToPILImage(normalize, 'cv2gray'))
train_data.load_list(args.train_lists, args.num_pts, args.boxindicator,
args.normalizeL, True)
if args.x68to49:
assert args.num_pts == 68, 'args.num_pts is not 68 vs. {:}'.format(
args.num_pts)
if train_data is not None: train_data = convert68to49(train_data)
args.num_pts = 49
# define the temporal model (accelerated SBR)
net = obtain_pro_temporal(model_config, sbr_config, args.num_pts,
args.sigma, args.use_gray)
assert model_config.downsample == net.downsample, 'downsample is not correct : {:} vs {:}'.format(
model_config.downsample, net.downsample)
logger.log("=> network :\n {}".format(net))
logger.log('Training-data : {:}'.format(train_data))
logger.log('arguments : {:}'.format(args))
opt_config = load_configure(args.opt_config, logger)
optimizer, scheduler, criterion = obtain_optimizer(net.parameters(),
opt_config, logger)
logger.log('criterion : {:}'.format(criterion))
net, criterion = net.cuda(), criterion.cuda()
net = torch.nn.DataParallel(net)
last_info = logger.last_info()
try:
last_checkpoint = load_checkpoint(args.init_model)
checkpoint = remove_module_dict(last_checkpoint['state_dict'], False)
net.module.detector.load_state_dict(checkpoint)
except:
last_checkpoint = load_checkpoint(args.init_model)
net.load_state_dict(last_checkpoint['state_dict'])
detector = torch.nn.DataParallel(net.module.detector)
logger.log("=> initialize the detector : {:}".format(args.init_model))
net.eval()
detector.eval()
logger.log('SBR Config : {:}'.format(sbr_config))
save_xdir = logger.path('meta')
random.seed(111)
index_list = list(range(len(train_data)))
random.shuffle(index_list)
#selected_list = index_list[: min(200, len(index_list))]
#selected_list = [7260, 11506, 39952, 75196, 51614, 41061, 37747, 41355]
#for iidx, i in enumerate(selected_list):
index_list.remove(47875)
selected_list = [47875] + index_list
save_xdir = logger.path('meta')
type_error_1, type_error_2, type_error, misses = 0, 0, 0, 0
type_error_pts, total_pts = 0, 0
for iidx, i in enumerate(selected_list):
frames, Fflows, Bflows, targets, masks, normpoints, transthetas, meanthetas, image_index, nopoints, shapes, is_images = train_data[
i]
frames, Fflows, Bflows, is_images = frames.unsqueeze(
0), Fflows.unsqueeze(0), Bflows.unsqueeze(0), is_images.unsqueeze(
0)
# batch_heatmaps is a list for stage-predictions, each element should be [Batch, Sequence, PTS, H/Down, W/Down]
with torch.no_grad():
if args.procedure == 'heatmap':
batch_heatmaps, batch_locs, batch_scos, batch_past2now, batch_future2now, batch_FBcheck = net(
frames, Fflows, Bflows, is_images)
else:
batch_locs, batch_past2now, batch_future2now, batch_FBcheck = net(
frames, Fflows, Bflows, is_images)
(batch_size, frame_length, C, H,
W), num_pts, annotate_index = frames.size(
), args.num_pts, train_data.video_L
batch_locs = batch_locs.cpu()[:, :, :num_pts]
video_mask = masks.unsqueeze(0)[:, :num_pts]
batch_past2now = batch_past2now.cpu()[:, :, :num_pts]
batch_future2now = batch_future2now.cpu()[:, :, :num_pts]
batch_FBcheck = batch_FBcheck[:, :num_pts].cpu()
FB_check_oks = FB_communication(criterion, batch_locs, batch_past2now,
batch_future2now, batch_FBcheck,
video_mask, sbr_config)
# locations
norm_past_det_locs = torch.cat(
(batch_locs[0, annotate_index - 1, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
norm_noww_det_locs = torch.cat(
(batch_locs[0, annotate_index, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
norm_next_det_locs = torch.cat(
(batch_locs[0, annotate_index + 1, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
norm_next_locs = torch.cat(
(batch_past2now[0, annotate_index, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
norm_past_locs = torch.cat(
(batch_future2now[0, annotate_index - 1, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
transtheta = transthetas[:2, :]
norm_past_det_locs = torch.mm(transtheta, norm_past_det_locs)
norm_noww_det_locs = torch.mm(transtheta, norm_noww_det_locs)
norm_next_det_locs = torch.mm(transtheta, norm_next_det_locs)
norm_next_locs = torch.mm(transtheta, norm_next_locs)
norm_past_locs = torch.mm(transtheta, norm_past_locs)
real_past_det_locs = denormalize_points(shapes.tolist(),
norm_past_det_locs)
real_noww_det_locs = denormalize_points(shapes.tolist(),
norm_noww_det_locs)
real_next_det_locs = denormalize_points(shapes.tolist(),
norm_next_det_locs)
real_next_locs = denormalize_points(shapes.tolist(), norm_next_locs)
real_past_locs = denormalize_points(shapes.tolist(), norm_past_locs)
gt_noww_points = train_data.labels[image_index.item()].get_points()
gt_past_points = train_data.find_index(
train_data.datas[image_index.item()][annotate_index - 1])
gt_next_points = train_data.find_index(
train_data.datas[image_index.item()][annotate_index + 1])
FB_check_oks = FB_check_oks[:num_pts].squeeze()
#import pdb; pdb.set_trace()
if FB_check_oks.sum().item() > 2:
# type 1 error : detection at both (t) and (t-1) is wrong, while pass the check
is_type_1, (T_wrong, T_total) = check_is_1st_error(
[real_past_det_locs, real_noww_det_locs, real_next_det_locs],
[gt_past_points, gt_noww_points, gt_next_points], FB_check_oks,
shapes)
# type 2 error : detection at frame t is ok, while tracking are wrong and frame at (t-1) is wrong:
spec_index, is_type_2 = check_is_2nd_error(
real_noww_det_locs, gt_noww_points,
[real_past_locs, real_next_locs],
[gt_past_points, gt_next_points], FB_check_oks, shapes)
type_error_1 += is_type_1
type_error_2 += is_type_2
type_error += is_type_1 or is_type_2
type_error_pts, total_pts = type_error_pts + T_wrong, total_pts + T_total
if is_type_2:
RED, GREEN, BLUE = (255, 0, 0), (0, 255, 0), (0, 0, 255)
[image_past, image_noww,
image_next] = train_data.datas[image_index.item()]
crop_box = train_data.labels[
image_index.item()].get_box().tolist()
point_index = FB_check_oks.nonzero().squeeze().tolist()
colors = [
GREEN if _i in point_index else RED
for _i in range(num_pts)
] + [BLUE for _i in range(num_pts)]
I_past_det = draw_image_by_points(
image_past,
torch.cat((real_past_det_locs, gt_past_points[:2]), dim=1),
3, colors, crop_box, (400, 500))
I_noww_det = draw_image_by_points(
image_noww,
torch.cat((real_noww_det_locs, gt_noww_points[:2]), dim=1),
3, colors, crop_box, (400, 500))
I_next_det = draw_image_by_points(
image_next,
torch.cat((real_next_det_locs, gt_next_points[:2]), dim=1),
3, colors, crop_box, (400, 500))
I_past = draw_image_by_points(
image_past,
torch.cat((real_past_locs, gt_past_points[:2]), dim=1), 3,
colors, crop_box, (400, 500))
I_next = draw_image_by_points(
image_next,
torch.cat((real_next_locs, gt_next_points[:2]), dim=1), 3,
colors, crop_box, (400, 500))
###
I_past.save(str(save_xdir / '{:05d}-v1-a-pastt.png'.format(i)))
I_noww_det.save(
str(save_xdir / '{:05d}-v1-b-curre.png'.format(i)))
I_next.save(str(save_xdir / '{:05d}-v1-c-nextt.png'.format(i)))
I_past_det.save(
str(save_xdir / '{:05d}-v1-det-a-past.png'.format(i)))
I_noww_det.save(
str(save_xdir / '{:05d}-v1-det-b-curr.png'.format(i)))
I_next_det.save(
str(save_xdir / '{:05d}-v1-det-c-next.png'.format(i)))
logger.log('TYPE-ERROR : {:}, landmark-index : {:}'.format(
i, spec_index))
else:
misses += 1
string = 'Handle {:05d}/{:05d} :: {:05d}'.format(
iidx, len(selected_list), i)
string += ', error-1 : {:} ({:.2f}%), error-2 : {:} ({:.2f}%)'.format(
type_error_1, type_error_1 * 100.0 / (iidx + 1), type_error_2,
type_error_2 * 100.0 / (iidx + 1))
string += ', error : {:} ({:.2f}%), miss : {:}'.format(
type_error, type_error * 100.0 / (iidx + 1), misses)
string += ', final-error : {:05d} / {:05d} = {:.2f}%'.format(
type_error_pts, total_pts, type_error_pts * 100.0 / total_pts)
logger.log(string)
def main(args):
assert torch.cuda.is_available(), 'CUDA is not available.'
torch.backends.cudnn.enabled = True
torch.backends.cudnn.benchmark = True
torch.set_num_threads(args.workers)
print('Training Base Detector : prepare_seed : {:}'.format(args.rand_seed))
prepare_seed(args.rand_seed)
temporal_main, eval_all = procedures['{:}-train'.format(
args.procedure)], procedures['{:}-test'.format(args.procedure)]
logger = prepare_logger(args)
# General Data Argumentation
normalize, train_transform, eval_transform, robust_transform = prepare_data_augmentation(
transforms, args)
recover = transforms.ToPILImage(normalize)
args.tensor2imageF = recover
assert (args.scale_min +
args.scale_max) / 2 == 1, 'The scale is not ok : {:} ~ {:}'.format(
args.scale_min, args.scale_max)
# Model Configure Load
model_config = load_configure(args.model_config, logger)
sbr_config = load_configure(args.sbr_config, logger)
shape = (args.height, args.width)
logger.log('--> {:}\n--> Sigma : {:}, Shape : {:}'.format(
model_config, args.sigma, shape))
logger.log('--> SBR Configuration : {:}\n'.format(sbr_config))
# Training Dataset
train_data = VDataset(eval_transform, args.sigma, model_config.downsample, args.heatmap_type, shape, args.use_gray, args.mean_point, \
args.data_indicator, sbr_config, transforms.ToPILImage(normalize, 'cv2gray'))
train_data.load_list(args.train_lists, args.num_pts, args.boxindicator,
args.normalizeL, True)
# Evaluation Dataloader
assert len(
args.eval_ilists) == 1, 'invalid length of eval_ilists : {:}'.format(
len(eval_ilists))
eval_data = IDataset(eval_transform, args.sigma, model_config.downsample,
args.heatmap_type, shape, args.use_gray,
args.mean_point, args.data_indicator)
eval_data.load_list(args.eval_ilists[0], args.num_pts, args.boxindicator,
args.normalizeL, True)
if args.x68to49:
assert args.num_pts == 68, 'args.num_pts is not 68 vs. {:}'.format(
args.num_pts)
if train_data is not None: train_data = convert68to49(train_data)
eval_data = convert68to49(eval_data)
args.num_pts = 49
# define the temporal model (accelerated SBR)
net = obtain_pro_temporal(model_config, sbr_config, args.num_pts,
args.sigma, args.use_gray)
assert model_config.downsample == net.downsample, 'downsample is not correct : {:} vs {:}'.format(
model_config.downsample, net.downsample)
logger.log("=> network :\n {}".format(net))
logger.log('Training-data : {:}'.format(train_data))
logger.log('Evaluate-data : {:}'.format(eval_data))
logger.log('arguments : {:}'.format(args))
opt_config = load_configure(args.opt_config, logger)
optimizer, scheduler, criterion = obtain_optimizer(net.parameters(),
opt_config, logger)
logger.log('criterion : {:}'.format(criterion))
net, criterion = net.cuda(), criterion.cuda()
net = torch.nn.DataParallel(net)
last_info = logger.last_info()
try:
last_checkpoint = load_checkpoint(args.init_model)
checkpoint = remove_module_dict(last_checkpoint['state_dict'], False)
net.module.detector.load_state_dict(checkpoint)
except:
last_checkpoint = load_checkpoint(args.init_model)
net.load_state_dict(last_checkpoint['state_dict'])
detector = torch.nn.DataParallel(net.module.detector)
logger.log("=> initialize the detector : {:}".format(args.init_model))
net.eval()
detector.eval()
logger.log('SBR Config : {:}'.format(sbr_config))
save_xdir = logger.path('meta')
type_error = 0
random.seed(111)
index_list = list(range(len(train_data)))
random.shuffle(index_list)
#selected_list = index_list[: min(200, len(index_list))]
selected_list = [
7260, 11506, 39952, 75196, 51614, 41061, 37747, 41355, 47875
]
for iidx, i in enumerate(selected_list):
frames, Fflows, Bflows, targets, masks, normpoints, transthetas, meanthetas, image_index, nopoints, shapes, is_images = train_data[
i]
frames, Fflows, Bflows, is_images = frames.unsqueeze(
0), Fflows.unsqueeze(0), Bflows.unsqueeze(0), is_images.unsqueeze(
0)
# batch_heatmaps is a list for stage-predictions, each element should be [Batch, Sequence, PTS, H/Down, W/Down]
if args.procedure == 'heatmap':
batch_heatmaps, batch_locs, batch_scos, batch_past2now, batch_future2now, batch_FBcheck = net(
frames, Fflows, Bflows, is_images)
else:
batch_locs, batch_past2now, batch_future2now, batch_FBcheck = net(
frames, Fflows, Bflows, is_images)
(batch_size, frame_length, C, H,
W), num_pts, annotate_index = frames.size(
), args.num_pts, train_data.video_L
batch_locs = batch_locs.cpu()[:, :, :num_pts]
video_mask = masks.unsqueeze(0)[:, :num_pts]
batch_past2now = batch_past2now.cpu()[:, :, :num_pts]
batch_future2now = batch_future2now.cpu()[:, :, :num_pts]
batch_FBcheck = batch_FBcheck[:, :num_pts].cpu()
FB_check_oks = FB_communication(criterion, batch_locs, batch_past2now,
batch_future2now, batch_FBcheck,
video_mask, sbr_config)
# locations
norm_past_det_locs = torch.cat(
(batch_locs[0, annotate_index - 1, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
norm_noww_det_locs = torch.cat(
(batch_locs[0, annotate_index, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
norm_next_det_locs = torch.cat(
(batch_locs[0, annotate_index + 1, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
norm_next_locs = torch.cat(
(batch_past2now[0, annotate_index, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
norm_past_locs = torch.cat(
(batch_future2now[0, annotate_index - 1, :num_pts].permute(
1, 0), torch.ones(1, num_pts)),
dim=0)
transtheta = transthetas[:2, :]
norm_past_det_locs = torch.mm(transtheta, norm_past_det_locs)
norm_noww_det_locs = torch.mm(transtheta, norm_noww_det_locs)
norm_next_det_locs = torch.mm(transtheta, norm_next_det_locs)
norm_next_locs = torch.mm(transtheta, norm_next_locs)
norm_past_locs = torch.mm(transtheta, norm_past_locs)
real_past_det_locs = denormalize_points(shapes.tolist(),
norm_past_det_locs)
real_noww_det_locs = denormalize_points(shapes.tolist(),
norm_noww_det_locs)
real_next_det_locs = denormalize_points(shapes.tolist(),
norm_next_det_locs)
real_next_locs = denormalize_points(shapes.tolist(), norm_next_locs)
real_past_locs = denormalize_points(shapes.tolist(), norm_past_locs)
gt_noww_points = train_data.labels[image_index.item()].get_points()
FB_check_oks = FB_check_oks[:num_pts].squeeze()
#import pdb; pdb.set_trace()
if FB_check_oks.sum().item() > 2:
point_index = FB_check_oks.nonzero().squeeze().tolist()
something_wrong = False
for pidx in point_index:
real_now_det_loc = real_noww_det_locs[:, pidx]
real_pst_det_loc = real_past_det_locs[:, pidx]
real_net_det_loc = real_next_det_locs[:, pidx]
real_nex_loc = real_next_locs[:, pidx]
real_pst_loc = real_next_locs[:, pidx]
grdt_now_loc = gt_noww_points[:2, pidx]
#if torch.abs(real_now_loc - grdt_now_loc).max() > 5:
# something_wrong = True
#if torch.abs(real_nex_loc - grdt_nex_loc).max() > 5:
# something_wrong = True
#if something_wrong == True:
if True:
[image_past, image_noww,
image_next] = train_data.datas[image_index.item()]
try:
crop_box = train_data.labels[
image_index.item()].get_box().tolist()
#crop_box = [crop_box[0]-20, crop_box[1]-20, crop_box[2]+20, crop_box[3]+20]
except:
crop_box = False
RED, GREEN, BLUE = (255, 0, 0), (0, 255, 0), (0, 0, 255)
colors = [
GREEN if _i in point_index else RED
for _i in range(num_pts)
]
if crop_box != False or True:
I_past_det = draw_image_by_points(image_past,
real_past_det_locs[:], 3,
colors, crop_box,
(400, 500))
I_noww_det = draw_image_by_points(image_noww,
real_noww_det_locs[:], 3,
colors, crop_box,
(400, 500))
I_next_det = draw_image_by_points(image_next,
real_next_det_locs[:], 3,
colors, crop_box,
(400, 500))
I_next = draw_image_by_points(image_next,
real_next_locs[:], 3, colors,
crop_box, (400, 500))
I_past = draw_image_by_points(image_past,
real_past_locs[:], 3, colors,
crop_box, (400, 500))
I_past.save(
str(save_xdir / '{:05d}-v1-a-pastt.png'.format(i)))
I_noww_det.save(
str(save_xdir / '{:05d}-v1-b-curre.png'.format(i)))
I_next.save(
str(save_xdir / '{:05d}-v1-c-nextt.png'.format(i)))
I_past_det.save(
str(save_xdir / '{:05d}-v1-det-a-past.png'.format(i)))
I_noww_det.save(
str(save_xdir / '{:05d}-v1-det-b-curr.png'.format(i)))
I_next_det.save(
str(save_xdir / '{:05d}-v1-det-c-next.png'.format(i)))
#[image_past, image_noww, image_next] = train_data.datas[image_index.item()]
#image_noww = draw_image_by_points(image_noww, real_noww_locs[:], 2, colors, False, False)
#image_next = draw_image_by_points(image_next, real_next_locs[:], 2, colors, False, False)
#image_past = draw_image_by_points(image_past, real_past_locs[:], 2, colors, False, False)
#image_noww.save( str(save_xdir / '{:05d}-v2-b-curre.png'.format(i)) )
#image_next.save( str(save_xdir / '{:05d}-v2-c-nextt.png'.format(i)) )
#image_past.save( str(save_xdir / '{:05d}-v2-a-pastt.png'.format(i)) )
#type_error += 1
logger.log(
'Handle {:05d}/{:05d} :: {:05d}, ok-points={:.3f}, wrong data={:}'.
format(iidx, len(selected_list), i,
FB_check_oks.float().mean().item(), type_error))
save_xx_dir = save_xdir.parent / 'image-data'
save_xx_dir.mkdir(parents=True, exist_ok=True)
selected_list = [100, 115, 200, 300, 400] + list(range(200, 220))
for iidx, i in enumerate(selected_list):
inputs, targets, masks, normpoints, transthetas, meanthetas, image_index, nopoints, shapes = eval_data[
i]
inputs = inputs.unsqueeze(0)
(batch_size, C, H, W), num_pts = inputs.size(), args.num_pts
_, _, batch_locs, batch_scos = detector(inputs) # inputs
batch_locs, batch_scos = batch_locs.cpu(), batch_scos.cpu()
norm_locs = normalize_points((H, W),
batch_locs[0, :num_pts].transpose(1, 0))
norm_det_locs = torch.cat((norm_locs, torch.ones(1, num_pts)), dim=0)
norm_det_locs = torch.mm(transthetas[:2, :], norm_det_locs)
real_det_locs = denormalize_points(shapes.tolist(), norm_det_locs)
gt_now_points = eval_data.labels[image_index.item()].get_points()
image_now = eval_data.datas[image_index.item()]
crop_box = eval_data.labels[image_index.item()].get_box().tolist()
RED, GREEN, BLUE = (255, 0, 0), (0, 255, 0), (0, 0, 255)
Gcolors = [GREEN for _ in range(num_pts)]
points = torch.cat((real_det_locs, gt_now_points[:2]), dim=1)
colors = [GREEN
for _ in range(num_pts)] + [BLUE for _ in range(num_pts)]
image = draw_image_by_points(image_now, real_det_locs, 3, Gcolors,
crop_box, (400, 500))
image.save(str(save_xx_dir / '{:05d}-crop.png'.format(i)))
image = draw_image_by_points(image_now, points, 3, colors, False,
False)
#image = draw_image_by_points(image_now, real_det_locs, 3, colors , False, False)
image.save(str(save_xx_dir / '{:05d}-orig.png'.format(i)))
logger.log('Finish drawing : {:}'.format(save_xdir))
logger.log('Finish drawing : {:}'.format(save_xx_dir))
logger.close()
