def main():
opt.manualSeed = random.randint(1, 10000)
random.seed(opt.manualSeed)
torch.manual_seed(opt.manualSeed)
if opt.dataset == 'ycb':
opt.num_objects = 21 #number of object classes in the dataset
opt.num_points = 1000 #number of points on the input pointcloud
opt.outf = 'trained_models/ycb' #folder to save trained models
opt.log_dir = 'experiments/logs/ycb' #folder to save logs
opt.repeat_epoch = 1 #number of repeat times for one epoch training
elif opt.dataset == 'linemod':
opt.num_objects = 13
opt.num_points = 500
opt.outf = 'trained_models/linemod'
opt.log_dir = 'experiments/logs/linemod'
opt.repeat_epoch = 20
else:
print('Unknown dataset')
return
estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects)
estimator.cuda()
refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects)
refiner.cuda()
if opt.resume_posenet != '':
estimator.load_state_dict(
torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet)))
if opt.resume_refinenet != '':
refiner.load_state_dict(
torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet)))
opt.refine_start = True
opt.decay_start = True
opt.lr *= opt.lr_rate
opt.w *= opt.w_rate
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
else:
opt.refine_start = False
opt.decay_start = False
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
if opt.dataset == 'ycb':
dataset = PoseDataset_ycb('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.workers)
if opt.dataset == 'ycb':
test_dataset = PoseDataset_ycb('test', opt.num_points, False,
opt.dataset_root, 0.0, opt.refine_start)
elif opt.dataset == 'linemod':
test_dataset = PoseDataset_linemod('test', opt.num_points, False,
opt.dataset_root, 0.0,
opt.refine_start)
testdataloader = torch.utils.data.DataLoader(test_dataset,
batch_size=1,
shuffle=False,
num_workers=opt.workers)
opt.sym_list = dataset.get_sym_list()
opt.num_points_mesh = dataset.get_num_points_mesh()
print(
'>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'
.format(len(dataset), len(test_dataset), opt.num_points_mesh,
opt.sym_list))
criterion = Loss(opt.num_points_mesh, opt.sym_list)
criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
best_test = np.Inf
if opt.start_epoch == 1:
for log in os.listdir(opt.log_dir):
os.remove(os.path.join(opt.log_dir, log))
st_time = time.time()
for epoch in range(opt.start_epoch, opt.nepoch):
logger = setup_logger(
'epoch%d' % epoch,
os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch))
logger.info('Train time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) +
', ' + 'Training started'))
train_count = 0
train_dis_avg = 0.0
if opt.refine_start:
estimator.eval()
refiner.train()
else:
estimator.train()
optimizer.zero_grad()
for rep in range(opt.repeat_epoch):
for i, data in enumerate(dataloader, 0):
points, choose, img, target, model_points, idx = data
points, choose, img, target, model_points, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target).cuda(), \
Variable(model_points).cuda(), \
Variable(idx).cuda()
pred_r, pred_t, pred_c, emb = estimator(
img, points, choose, idx)
loss, dis, new_points, new_target = criterion(
pred_r, pred_t, pred_c, target, model_points, idx, points,
opt.w, opt.refine_start)
if opt.refine_start:
for ite in range(0, opt.iteration):
pred_r, pred_t = refiner(new_points, emb, idx)
dis, new_points, new_target = criterion_refine(
pred_r, pred_t, new_target, model_points, idx,
new_points)
dis.backward()
else:
loss.backward()
train_dis_avg += dis.item()
train_count += 1
if train_count % opt.batch_size == 0:
logger.info(
'Train time {0} Epoch {1} Batch {2} Frame {3} Avg_dis:{4}'
.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)),
epoch, int(train_count / opt.batch_size),
train_count, train_dis_avg / opt.batch_size))
optimizer.step()
optimizer.zero_grad()
train_dis_avg = 0
if train_count != 0 and train_count % 1000 == 0:
if opt.refine_start:
torch.save(
refiner.state_dict(),
'{0}/pose_refine_model_current.pth'.format(
opt.outf))
else:
torch.save(
estimator.state_dict(),
'{0}/pose_model_current.pth'.format(opt.outf))
print(
'>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format(
epoch))
logger = setup_logger(
'epoch%d_test' % epoch,
os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch))
logger.info('Test time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) +
', ' + 'Testing started'))
test_dis = 0.0
test_count = 0
estimator.eval()
refiner.eval()
for j, data in enumerate(testdataloader, 0):
points, choose, img, target, model_points, idx = data
points, choose, img, target, model_points, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target).cuda(), \
Variable(model_points).cuda(), \
Variable(idx).cuda()
pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx)
_, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c,
target, model_points,
idx, points, opt.w,
opt.refine_start)
if opt.refine_start:
for ite in range(0, opt.iteration):
pred_r, pred_t = refiner(new_points, emb, idx)
dis, new_points, new_target = criterion_refine(
pred_r, pred_t, new_target, model_points, idx,
new_points)
test_dis += dis.item()
logger.info('Test time {0} Test Frame No.{1} dis:{2}'.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)), test_count,
dis))
test_count += 1
test_dis = test_dis / test_count
logger.info('Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)),
epoch, test_dis))
if test_dis <= best_test:
best_test = test_dis
if opt.refine_start:
torch.save(
refiner.state_dict(),
'{0}/pose_refine_model_{1}_{2}.pth'.format(
opt.outf, epoch, test_dis))
else:
torch.save(
estimator.state_dict(),
'{0}/pose_model_{1}_{2}.pth'.format(
opt.outf, epoch, test_dis))
print(epoch,
'>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<')
if best_test < opt.decay_margin and not opt.decay_start:
opt.decay_start = True
opt.lr *= opt.lr_rate
opt.w *= opt.w_rate
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
if best_test < opt.refine_margin and not opt.refine_start:
opt.refine_start = True
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
if opt.dataset == 'ycb':
dataset = PoseDataset_ycb('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('train', opt.num_points, True,
opt.dataset_root,
opt.noise_trans,
opt.refine_start)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.workers)
if opt.dataset == 'ycb':
test_dataset = PoseDataset_ycb('test', opt.num_points, False,
opt.dataset_root, 0.0,
opt.refine_start)
elif opt.dataset == 'linemod':
test_dataset = PoseDataset_linemod('test', opt.num_points,
False, opt.dataset_root,
0.0, opt.refine_start)
testdataloader = torch.utils.data.DataLoader(
test_dataset,
batch_size=1,
shuffle=False,
num_workers=opt.workers)
opt.sym_list = dataset.get_sym_list()
opt.num_points_mesh = dataset.get_num_points_mesh()
print(
'>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'
.format(len(dataset), len(test_dataset), opt.num_points_mesh,
opt.sym_list))
criterion = Loss(opt.num_points_mesh, opt.sym_list)
criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
def main():
# g13: parameter setting -------------------
batch_id = 1
opt.dataset ='linemod'
opt.dataset_root = './datasets/linemod/Linemod_preprocessed'
estimator_path = 'trained_checkpoints/linemod/pose_model_9_0.01310166542980859.pth'
refiner_path = 'trained_checkpoints/linemod/pose_refine_model_493_0.006761023565178073.pth'
opt.resume_posenet = estimator_path
opt.resume_posenet = refiner_path
dataset_config_dir = 'datasets/linemod/dataset_config'
output_result_dir = 'experiments/eval_result/linemod'
bs = 1 #fixed because of the default setting in torch.utils.data.DataLoader
opt.iteration = 2 #default is 4 in eval_linemod.py
t1_idx = 0
t1_total_eval_num = 3
axis_range = 0.1 # the length of X, Y, and Z axis in 3D
vimg_dir = 'verify_img'
if not os.path.exists(vimg_dir):
os.makedirs(vimg_dir)
#-------------------------------------------
if opt.dataset == 'ycb':
opt.num_objects = 21 #number of object classes in the dataset
opt.num_points = 1000 #number of points on the input pointcloud
opt.outf = 'trained_models/ycb' #folder to save trained models
opt.log_dir = 'experiments/logs/ycb' #folder to save logs
opt.repeat_epoch = 1 #number of repeat times for one epoch training
elif opt.dataset == 'linemod':
opt.num_objects = 13
opt.num_points = 500
opt.outf = 'trained_models/linemod'
opt.log_dir = 'experiments/logs/linemod'
opt.repeat_epoch = 20
else:
print('Unknown dataset')
return
estimator = PoseNet(num_points = opt.num_points, num_obj = opt.num_objects)
estimator.cuda()
refiner = PoseRefineNet(num_points = opt.num_points, num_obj = opt.num_objects)
refiner.cuda()
if opt.resume_posenet != '':
estimator.load_state_dict(torch.load(estimator_path))
if opt.resume_refinenet != '':
refiner.load_state_dict(torch.load(refiner_path))
opt.refine_start = True
opt.decay_start = True
opt.lr *= opt.lr_rate
opt.w *= opt.w_rate
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
else:
opt.refine_start = False
opt.decay_start = False
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
if opt.dataset == 'ycb':
test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start)
elif opt.dataset == 'linemod':
test_dataset = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0, opt.refine_start)
testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers)
print('complete loading testing loader\n')
opt.sym_list = test_dataset.get_sym_list()
opt.num_points_mesh = test_dataset.get_num_points_mesh()
print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\n\
length of the testing set: {0}\nnumber of sample points on mesh: {1}\n\
symmetry object list: {2}'\
.format( len(test_dataset), opt.num_points_mesh, opt.sym_list))
#load pytorch model
estimator.eval()
refiner.eval()
criterion = Loss(opt.num_points_mesh, opt.sym_list)
criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
fw = open('{0}/t1_eval_result_logs.txt'.format(output_result_dir), 'w')
#Pose estimation
for j, data in enumerate(testdataloader, 0):
# g13: modify this part for evaluation target--------------------
if j == t1_total_eval_num:
break
#----------------------------------------------------------------
points, choose, img, target, model_points, idx = data
if len(points.size()) == 2:
print('No.{0} NOT Pass! Lost detection!'.format(j))
fw.write('No.{0} NOT Pass! Lost detection!\n'.format(j))
continue
points, choose, img, target, model_points, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target).cuda(), \
Variable(model_points).cuda(), \
Variable(idx).cuda()
pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx)
_, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c, target, model_points, idx, points, opt.w, opt.refine_start)
#if opt.refine_start: #iterative poserefinement
# for ite in range(0, opt.iteration):
# pred_r, pred_t = refiner(new_points, emb, idx)
# dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_target, model_points, idx, new_points)
pred_r = pred_r / torch.norm(pred_r, dim=2).view(1, opt.num_points, 1)
pred_c = pred_c.view(bs, opt.num_points)
how_max, which_max = torch.max(pred_c, 1)
pred_t = pred_t.view(bs * opt.num_points, 1, 3)
my_r = pred_r[0][which_max[0]].view(-1).cpu().data.numpy()
my_t = (points.view(bs * opt.num_points, 1, 3) + pred_t)[which_max[0]].view(-1).cpu().data.numpy()
my_pred = np.append(my_r, my_t)
for ite in range(0, opt.iteration):
T = Variable(torch.from_numpy(my_t.astype(np.float32))).cuda().view(1, 3).repeat(opt.num_points, 1).contiguous().view(1, opt.num_points, 3)
my_mat = quaternion_matrix(my_r)
R = Variable(torch.from_numpy(my_mat[:3, :3].astype(np.float32))).cuda().view(1, 3, 3)
my_mat[0:3, 3] = my_t
new_points = torch.bmm((points - T), R).contiguous()
pred_r, pred_t = refiner(new_points, emb, idx)
pred_r = pred_r.view(1, 1, -1)
pred_r = pred_r / (torch.norm(pred_r, dim=2).view(1, 1, 1))
my_r_2 = pred_r.view(-1).cpu().data.numpy()
my_t_2 = pred_t.view(-1).cpu().data.numpy()
my_mat_2 = quaternion_matrix(my_r_2)
my_mat_2[0:3, 3] = my_t_2
my_mat_final = np.dot(my_mat, my_mat_2)
my_r_final = copy.deepcopy(my_mat_final)
my_r_final[0:3, 3] = 0
my_r_final = quaternion_from_matrix(my_r_final, True)
my_t_final = np.array([my_mat_final[0][3], my_mat_final[1][3], my_mat_final[2][3]])
my_pred = np.append(my_r_final, my_t_final)
my_r = my_r_final
my_t = my_t_final
# g13: start drawing pose on image------------------------------------
# pick up image
print("index {0}: {1}".format(j, test_dataset.list_rgb[j]))
img = Image.open(test_dataset.list_rgb[j])
# pick up center position by bbox
meta_file = open('{0}/data/{1}/gt.yml'.format(opt.dataset_root, '%02d' % test_dataset.list_obj[j]), 'r')
meta = {}
meta = yaml.load(meta_file)
which_item = test_dataset.list_rank[j]
bbx = meta[which_item][0]['obj_bb']
draw = ImageDraw.Draw(img)
# draw box (ensure this is the right object)
draw.line((bbx[0],bbx[1], bbx[0], bbx[1]+bbx[3]), fill=(255,0,0), width=5)
draw.line((bbx[0],bbx[1], bbx[0]+bbx[2], bbx[1]), fill=(255,0,0), width=5)
draw.line((bbx[0],bbx[1]+bbx[3], bbx[0]+bbx[2], bbx[1]+bbx[3]), fill=(255,0,0), width=5)
draw.line((bbx[0]+bbx[2],bbx[1], bbx[0]+bbx[2], bbx[1]+bbx[3]), fill=(255,0,0), width=5)
#get center
c_x = bbx[0]+int(bbx[2]/2)
c_y = bbx[1]+int(bbx[3]/2)
draw.point((c_x,c_y), fill=(255,255,0))
#get the 3D position of center
cam_intrinsic = np.zeros((3,3))
cam_intrinsic.itemset(0, test_dataset.cam_fx)
cam_intrinsic.itemset(4, test_dataset.cam_fy)
cam_intrinsic.itemset(2, test_dataset.cam_cx)
cam_intrinsic.itemset(5, test_dataset.cam_cy)
cam_intrinsic.itemset(8, 1)
cam_extrinsic = my_mat_final[0:3, :]
cam2d_3d = np.matmul(cam_intrinsic, cam_extrinsic)
cen_3d = np.matmul(np.linalg.pinv(cam2d_3d), [[c_x],[c_y],[1]])
# replace img.show() with plt.imshow(img)
#transpose three 3D axis point into 2D
x_3d = cen_3d + [[axis_range],[0],[0],[0]]
y_3d = cen_3d + [[0],[axis_range],[0],[0]]
z_3d = cen_3d + [[0],[0],[axis_range],[0]]
x_2d = np.matmul(cam2d_3d, x_3d)
y_2d = np.matmul(cam2d_3d, y_3d)
z_2d = np.matmul(cam2d_3d, z_3d)
#draw the axis on 2D
draw.line((c_x, c_y, x_2d[0], x_2d[1]), fill=(255,255,0), width=5)
draw.line((c_x, c_y, y_2d[0], y_2d[1]), fill=(0,255,0), width=5)
draw.line((c_x, c_y, z_2d[0], z_2d[1]), fill=(0,0,255), width=5)
#g13: show image
#img.show()
#save file under file
img_file_name = '{0}/pred_obj{1}_pic{2}.png'.format(vimg_dir, test_dataset.list_obj[j], which_item)
img.save( img_file_name, "PNG" )
img.close()
def main():
# opt.manualSeed = random.randint(1, 10000)
# # opt.manualSeed = 1
# random.seed(opt.manualSeed)
# torch.manual_seed(opt.manualSeed)
torch.set_printoptions(threshold=5000)
# device_ids = [0,1]
cudnn.benchmark = True
if opt.dataset == 'ycb':
opt.num_objects = 21 #number of object classes in the dataset
opt.num_points = 1000 #number of points on the input pointcloud
opt.outf = 'trained_models/ycb' #folder to save trained models
opt.log_dir = 'experiments/logs/ycb' #folder to save logs
opt.repeat_epoch = 3 #number of repeat times for one epoch training
elif opt.dataset == 'linemod':
opt.num_objects = 13
opt.num_points = 500
opt.outf = 'trained_models/linemod'
opt.log_dir = 'experiments/logs/linemod'
opt.repeat_epoch = 20
else:
print('Unknown dataset')
return
estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects)
estimator.cuda()
refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects)
# refiner.cuda()
# estimator = nn.DataParallel(estimator, device_ids=device_ids)
if opt.resume_posenet != '':
estimator.load_state_dict(
torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet)))
print('LOADED!!')
if opt.resume_refinenet != '':
refiner.load_state_dict(
torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet)))
opt.refine_start = True
opt.decay_start = True
opt.lr *= opt.lr_rate
opt.w *= opt.w_rate
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
else:
print('no refinement')
opt.refine_start = False
opt.decay_start = False
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
# optimizer = nn.DataParallel(optimizer, device_ids=device_ids)
if opt.dataset == 'ycb':
dataset = PoseDataset_ycb('train', opt.num_points, False,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
# print(dataset.list)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.workers)
if opt.dataset == 'ycb':
test_dataset = PoseDataset_ycb('test', opt.num_points, False,
opt.dataset_root, 0.0, opt.refine_start)
elif opt.dataset == 'linemod':
test_dataset = PoseDataset_linemod('test', opt.num_points, False,
opt.dataset_root, 0.0,
opt.refine_start)
testdataloader = torch.utils.data.DataLoader(test_dataset,
batch_size=1,
shuffle=False,
num_workers=opt.workers)
opt.sym_list = dataset.get_sym_list()
opt.num_points_mesh = dataset.get_num_points_mesh()
# print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'.format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list))
criterion = Loss(opt.num_points_mesh, opt.sym_list)
# criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
best_test = np.Inf
best_epoch = 0
if opt.start_epoch == 1:
for log in os.listdir(opt.log_dir):
os.remove(os.path.join(opt.log_dir, log))
st_time = time.time()
count_gen = 0
mode = 1
if mode == 1:
for epoch in range(opt.start_epoch, opt.nepoch):
logger = setup_logger(
'epoch%d' % epoch,
os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch))
logger.info('Train time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() -
st_time)) + ', ' +
'Training started'))
train_count = 0
train_dis_avg = 0.0
if opt.refine_start:
estimator.eval()
refiner.train()
else:
estimator.train()
optimizer.zero_grad()
for rep in range(opt.repeat_epoch):
for i, data in enumerate(dataloader, 0):
points, choose, img, target_sym, target_cen, idx, file_list_idx = data
if idx is 9 or idx is 16:
continue
points, choose, img, target_sym, target_cen, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target_sym).cuda(), \
Variable(target_cen).cuda(), \
Variable(idx).cuda()
pred_norm, pred_on_plane, emb = estimator(
img, points, choose, idx)
loss = criterion(pred_norm, pred_on_plane, target_sym,
target_cen, idx, points, opt.w,
opt.refine_start)
# scene_idx = dataset.list[file_list_idx]
loss.backward()
# train_dis_avg += dis.item()
train_count += 1
if train_count % opt.batch_size == 0:
logger.info(
'Train time {0} Epoch {1} Batch {2} Frame {3}'.
format(
time.strftime(
"%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)), epoch,
int(train_count / opt.batch_size),
train_count))
optimizer.step()
# for param_lr in optimizer.module.param_groups:
# param_lr['lr'] /= 2
optimizer.zero_grad()
train_dis_avg = 0
if train_count % 8 == 0:
print(pred_on_plane.max())
print(pred_on_plane.mean())
print(idx)
if train_count != 0 and train_count % 1000 == 0:
if opt.refine_start:
torch.save(
refiner.state_dict(),
'{0}/pose_refine_model_current.pth'.format(
opt.outf))
else:
torch.save(
estimator.state_dict(),
'{0}/pose_model_current.pth'.format(opt.outf))
print('>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.
format(epoch))
logger = setup_logger(
'epoch%d_test' % epoch,
os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch))
logger.info('Test time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() -
st_time)) + ', ' +
'Testing started'))
test_loss = 0.0
test_count = 0
estimator.eval()
logger.info(
'Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)), epoch,
test_loss))
print(pred_on_plane.max())
print(pred_on_plane.mean())
bs, num_p, _ = pred_on_plane.size()
# if epoch % 40 == 0:
# import pdb;pdb.set_trace()
best_test = test_loss
best_epoch = epoch
if opt.refine_start:
torch.save(
refiner.state_dict(),
'{0}/pose_refine_model_{1}_{2}.pth'.format(
opt.outf, epoch, test_loss))
else:
torch.save(
estimator.state_dict(),
'{0}/pose_model_{1}_{2}.pth'.format(
opt.outf, epoch, test_loss))
print(epoch,
'>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<')
if best_test < opt.decay_margin and not opt.decay_start:
opt.decay_start = True
opt.lr *= opt.lr_rate
# opt.w *= opt.w_rate
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
estimator.load_state_dict(
torch.load('{0}/pose_model_{1}_{2}.pth'.format(
opt.outf, best_epoch, best_test)))
else:
estimator.load_state_dict(
torch.load('{0}/pose_model_45_0.0.pth'.format(opt.outf),
map_location='cpu'))
def main():
opt.manualSeed = random.randint(1, 10000)
random.seed(opt.manualSeed)
torch.manual_seed(opt.manualSeed)
if opt.dataset == 'ycb':
opt.dataset_root = 'datasets/ycb/YCB_Video_Dataset'
opt.num_objects = 21
opt.num_points = 1000
opt.result_dir = 'results/ycb'
opt.repeat_epoch = 1
elif opt.dataset == 'linemod':
opt.dataset_root = 'datasets/linemod/Linemod_preprocessed'
opt.num_objects = 13
opt.num_points = 500
opt.result_dir = 'results/linemod'
opt.repeat_epoch = 1
else:
print('unknown dataset')
return
if opt.dataset == 'ycb':
dataset = PoseDataset_ycb('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans)
test_dataset = PoseDataset_ycb('test', opt.num_points, False,
opt.dataset_root, 0.0)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans)
test_dataset = PoseDataset_linemod('test', opt.num_points, False,
opt.dataset_root, 0.0)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.workers)
testdataloader = torch.utils.data.DataLoader(test_dataset,
batch_size=1,
shuffle=False,
num_workers=opt.workers)
opt.sym_list = dataset.get_sym_list()
opt.num_points_mesh = dataset.get_num_points_mesh()
opt.diameters = dataset.get_diameter()
print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<')
print('length of the training set: {0}'.format(len(dataset)))
print('length of the testing set: {0}'.format(len(test_dataset)))
print('number of sample points on mesh: {0}'.format(opt.num_points_mesh))
print('symmetrical object list: {0}'.format(opt.sym_list))
if not os.path.exists(opt.result_dir):
os.makedirs(opt.result_dir)
tb_writer = tf.summary.FileWriter(opt.result_dir)
os.environ['CUDA_VISIBLE_DEVICES'] = opt.gpu_id
# network
estimator = PoseNet(num_points=opt.num_points,
num_obj=opt.num_objects,
num_rot=opt.num_rot)
estimator.cuda()
# loss
criterion = Loss(opt.sym_list, estimator.rot_anchors)
knn = KNearestNeighbor(1)
# learning rate decay
best_test = np.Inf
opt.first_decay_start = False
opt.second_decay_start = False
# if resume training
if opt.resume_posenet != '':
estimator.load_state_dict(torch.load(opt.resume_posenet))
model_name_parsing = (opt.resume_posenet.split('.')[0]).split('_')
best_test = float(model_name_parsing[-1])
opt.start_epoch = int(model_name_parsing[-2]) + 1
if best_test < 0.016 and not opt.first_decay_start:
opt.first_decay_start = True
opt.lr *= 0.6
if best_test < 0.013 and not opt.second_decay_start:
opt.second_decay_start = True
opt.lr *= 0.5
# optimizer
optimizer = torch.optim.Adam(estimator.parameters(), lr=opt.lr)
global_step = (len(dataset) //
opt.batch_size) * opt.repeat_epoch * (opt.start_epoch - 1)
# train
st_time = time.time()
for epoch in range(opt.start_epoch, opt.nepoch):
logger = setup_logger(
'epoch%02d' % epoch,
os.path.join(opt.result_dir, 'epoch_%02d_train_log.txt' % epoch))
logger.info('Train time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) +
', ' + 'Training started'))
train_count = 0
train_loss_avg = 0.0
train_loss_r_avg = 0.0
train_loss_t_avg = 0.0
train_loss_reg_avg = 0.0
estimator.train()
optimizer.zero_grad()
for rep in range(opt.repeat_epoch):
for i, data in enumerate(dataloader, 0):
points, choose, img, target_t, target_r, model_points, idx, gt_t = data
obj_diameter = opt.diameters[idx]
points, choose, img, target_t, target_r, model_points, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target_t).cuda(), \
Variable(target_r).cuda(), \
Variable(model_points).cuda(), \
Variable(idx).cuda()
pred_r, pred_t, pred_c = estimator(img, points, choose, idx)
loss, loss_r, loss_t, loss_reg = criterion(
pred_r, pred_t, pred_c, target_r, target_t, model_points,
idx, obj_diameter)
loss.backward()
train_loss_avg += loss.item()
train_loss_r_avg += loss_r.item()
train_loss_t_avg += loss_t.item()
train_loss_reg_avg += loss_reg.item()
train_count += 1
if train_count % opt.batch_size == 0:
global_step += 1
lr = opt.lr
optimizer.step()
optimizer.zero_grad()
# write results to tensorboard
summary = tf.Summary(value=[
tf.Summary.Value(tag='learning_rate', simple_value=lr),
tf.Summary.Value(tag='loss',
simple_value=train_loss_avg /
opt.batch_size),
tf.Summary.Value(tag='loss_r',
simple_value=train_loss_r_avg /
opt.batch_size),
tf.Summary.Value(tag='loss_t',
simple_value=train_loss_t_avg /
opt.batch_size),
tf.Summary.Value(tag='loss_reg',
simple_value=train_loss_reg_avg /
opt.batch_size)
])
tb_writer.add_summary(summary, global_step)
logger.info(
'Train time {0} Epoch {1} Batch {2} Frame {3} Avg_loss:{4:f}'
.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)),
epoch, int(train_count / opt.batch_size),
train_count, train_loss_avg / opt.batch_size))
train_loss_avg = 0.0
train_loss_r_avg = 0.0
train_loss_t_avg = 0.0
train_loss_reg_avg = 0.0
print(
'>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format(
epoch))
logger = setup_logger(
'epoch%02d_test' % epoch,
os.path.join(opt.result_dir, 'epoch_%02d_test_log.txt' % epoch))
logger.info('Test time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) +
', ' + 'Testing started'))
test_dis = 0.0
test_count = 0
save_model = False
estimator.eval()
success_count = [0 for i in range(opt.num_objects)]
num_count = [0 for i in range(opt.num_objects)]
for j, data in enumerate(testdataloader, 0):
points, choose, img, target_t, target_r, model_points, idx, gt_t = data
obj_diameter = opt.diameters[idx]
points, choose, img, target_t, target_r, model_points, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target_t).cuda(), \
Variable(target_r).cuda(), \
Variable(model_points).cuda(), \
Variable(idx).cuda()
pred_r, pred_t, pred_c = estimator(img, points, choose, idx)
loss, _, _, _ = criterion(pred_r, pred_t, pred_c, target_r,
target_t, model_points, idx,
obj_diameter)
test_count += 1
# evalaution
how_min, which_min = torch.min(pred_c, 1)
pred_r = pred_r[0][which_min[0]].view(-1).cpu().data.numpy()
pred_r = quaternion_matrix(pred_r)[:3, :3]
pred_t, pred_mask = ransac_voting_layer(points, pred_t)
pred_t = pred_t.cpu().data.numpy()
model_points = model_points[0].cpu().detach().numpy()
pred = np.dot(model_points, pred_r.T) + pred_t
target = target_r[0].cpu().detach().numpy() + gt_t[0].cpu(
).data.numpy()
if idx[0].item() in opt.sym_list:
pred = torch.from_numpy(pred.astype(
np.float32)).cuda().transpose(1, 0).contiguous()
target = torch.from_numpy(target.astype(
np.float32)).cuda().transpose(1, 0).contiguous()
inds = knn(target.unsqueeze(0), pred.unsqueeze(0))
target = torch.index_select(target, 1, inds.view(-1) - 1)
dis = torch.mean(torch.norm(
(pred.transpose(1, 0) - target.transpose(1, 0)), dim=1),
dim=0).item()
else:
dis = np.mean(np.linalg.norm(pred - target, axis=1))
logger.info(
'Test time {0} Test Frame No.{1} loss:{2:f} confidence:{3:f} distance:{4:f}'
.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)),
test_count, loss, how_min[0].item(), dis))
if dis < 0.1 * opt.diameters[idx[0].item()]:
success_count[idx[0].item()] += 1
num_count[idx[0].item()] += 1
test_dis += dis
# compute accuracy
accuracy = 0.0
for i in range(opt.num_objects):
accuracy += float(success_count[i]) / num_count[i]
logger.info('Object {0} success rate: {1}'.format(
test_dataset.objlist[i],
float(success_count[i]) / num_count[i]))
accuracy = accuracy / opt.num_objects
test_dis = test_dis / test_count
# log results
logger.info(
'Test time {0} Epoch {1} TEST FINISH Avg dis: {2:f}, Accuracy: {3:f}'
.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)), epoch,
test_dis, accuracy))
# tensorboard
summary = tf.Summary(value=[
tf.Summary.Value(tag='accuracy', simple_value=accuracy),
tf.Summary.Value(tag='test_dis', simple_value=test_dis)
])
tb_writer.add_summary(summary, global_step)
# save model
if test_dis < best_test:
best_test = test_dis
torch.save(
estimator.state_dict(),
'{0}/pose_model_{1:02d}_{2:06f}.pth'.format(
opt.result_dir, epoch, best_test))
# adjust learning rate if necessary
if best_test < 0.016 and not opt.first_decay_start:
opt.first_decay_start = True
opt.lr *= 0.6
optimizer = torch.optim.Adam(estimator.parameters(), lr=opt.lr)
if best_test < 0.013 and not opt.second_decay_start:
opt.second_decay_start = True
opt.lr *= 0.5
optimizer = torch.optim.Adam(estimator.parameters(), lr=opt.lr)
print(
'>>>>>>>>----------epoch {0} test finish---------<<<<<<<<'.format(
epoch))
def main():
if opt.dataset == 'ycb':
opt.num_obj = 21
opt.sym_list = [12, 15, 18, 19, 20]
opt.num_points = 1000
writer = SummaryWriter('experiments/runs/ycb/{0}'.format(opt.experiment_name))
opt.outf = 'trained_models/ycb/{0}'.format(opt.experiment_name)
opt.log_dir = 'experiments/logs/ycb/{0}'.format(opt.experiment_name)
opt.repeat_num = 1
if not os.path.exists(opt.outf):
os.mkdir(opt.outf)
if not os.path.exists(opt.log_dir):
os.mkdir(opt.log_dir)
else:
print('Unknown dataset')
return
estimator = PoseNet(num_points = opt.num_points, num_vote = 9, num_obj = opt.num_obj)
estimator.cuda()
refiner = PoseRefineNet(num_points = opt.num_points, num_obj = opt.num_obj)
refiner.cuda()
if opt.resume_posenet != '':
estimator.load_state_dict(torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet)))
if opt.resume_refinenet != '':
refiner.load_state_dict(torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet)))
opt.refine_start = True
opt.lr = opt.lr_refine
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
else:
opt.refine_start = False
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
dataset = PoseDataset_ycb('train', opt.num_points, True, opt.dataset_root)
dataloader = torch.utils.data.DataLoader(dataset, batch_size=1, shuffle=True, num_workers=opt.workers)
test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root)
testdataloader = torch.utils.data.DataLoader(test_dataset, batch_size=1, shuffle=False, num_workers=opt.workers)
print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}'.format(len(dataset), len(test_dataset), opt.num_points))
criterion = Loss(opt.num_points, opt.sym_list)
criterion_refine = Loss_refine(opt.num_points, opt.sym_list)
best_test = np.Inf
if opt.start_epoch == 1:
for log in os.listdir(opt.log_dir):
os.remove(os.path.join(opt.log_dir, log))
st_time = time.time()
train_scalar = 0
for epoch in range(opt.start_epoch, opt.nepoch):
logger = setup_logger('epoch%d' % epoch, os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch))
logger.info('Train time {0}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Training started'))
train_count = 0
train_loss_avg = 0.0
train_loss = 0.0
train_dis_avg = 0.0
train_dis = 0.0
if opt.refine_start:
estimator.eval()
refiner.train()
else:
estimator.train()
optimizer.zero_grad()
for rep in range(opt.repeat_num):
for i, data in enumerate(dataloader, 0):
points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = data
points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = points.cuda(), choose.cuda(), img.cuda(), target.cuda(), model_points.cuda(), model_kp.cuda(), vertex_gt.cuda(), idx.cuda(), target_r.cuda(), target_t.cuda()
vertex_pred, c_pred, emb = estimator(img, points, choose, idx)
vertex_loss, pose_loss, dis, new_points, new_target = criterion(vertex_pred, vertex_gt, c_pred, points, target, model_points, model_kp, idx, target_r, target_t)
loss = 10 * vertex_loss + pose_loss
if opt.refine_start:
for ite in range(0, opt.iteration):
pred_r, pred_t = refiner(new_points, emb, idx)
dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_points, new_target, model_points, idx)
dis.backward()
else:
loss.backward()
train_loss_avg += loss.item()
train_loss += loss.item()
train_dis_avg += dis.item()
train_dis += dis.item()
train_count += 1
train_scalar += 1
if train_count % opt.batch_size == 0:
logger.info('Train time {0} Epoch {1} Batch {2} Frame {3} Avg_loss:{4} Avg_diss:{5}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, int(train_count / opt.batch_size), train_count, train_loss_avg / opt.batch_size, train_dis_avg / opt.batch_size))
writer.add_scalar('ycb training loss', train_loss_avg / opt.batch_size, train_scalar)
writer.add_scalar('ycb training dis', train_dis_avg / opt.batch_size, train_scalar)
optimizer.step()
optimizer.zero_grad()
train_loss_avg = 0
train_dis_avg = 0
if train_count != 0 and train_count % 1000 == 0:
if opt.refine_start:
torch.save(refiner.state_dict(), '{0}/pose_refine_model_current.pth'.format(opt.outf))
else:
torch.save(estimator.state_dict(), '{0}/pose_model_current.pth'.format(opt.outf))
print('>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format(epoch))
train_loss = train_loss / train_count
train_dis = train_dis / train_count
logger.info('Train time {0} Epoch {1} TRAIN FINISH Avg loss: {2} Avg dis: {3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, train_loss, train_dis))
logger = setup_logger('epoch%d_test' % epoch, os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch))
logger.info('Test time {0}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) + ', ' + 'Testing started'))
test_loss = 0.0
test_vertex_loss = 0.0
test_pose_loss = 0.0
test_dis = 0.0
test_count = 0
success_count = 0
estimator.eval()
refiner.eval()
for j, data in enumerate(testdataloader, 0):
points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = data
points, choose, img, target, model_points, model_kp, vertex_gt, idx, target_r, target_t = points.cuda(), choose.cuda(), img.cuda(), target.cuda(), model_points.cuda(), model_kp.cuda(), vertex_gt.cuda(), idx.cuda(), target_r.cuda(), target_t.cuda()
vertex_pred, c_pred, emb = estimator(img, points, choose, idx)
vertex_loss, pose_loss, dis, new_points, new_target = criterion(vertex_pred, vertex_gt, c_pred, points, target, model_points, model_kp, idx, target_r, target_t)
loss = 10 * vertex_loss + pose_loss
if opt.refine_start:
for ite in range(0, opt.iteration):
pred_r, pred_t = refiner(new_points, emb, idx)
dis, new_points, new_target = criterion_refine(pred_r, pred_t, new_points, new_target, model_points, idx)
test_loss += loss.item()
test_vertex_loss += vertex_loss.item()
test_pose_loss += pose_loss.item()
test_dis += dis.item()
logger.info('Test time {0} Test Frame No.{1} loss:{2} dis:{3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count, loss, dis))
test_count += 1
if dis.item() < 0.02:
success_count += 1
test_loss = test_loss / test_count
test_vertex_loss = test_vertex_loss / test_count
test_pose_loss = test_pose_loss / test_count
test_dis = test_dis / test_count
logger.info('Test time {0} Epoch {1} TEST FINISH Avg loss: {2} Avg dis: {3}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), epoch, test_loss, test_dis))
logger.info('Success rate: {}'.format(float(success_count) / test_count))
writer.add_scalar('ycb test loss', test_loss, epoch)
writer.add_scalar('ycb test vertex loss', test_vertex_loss, epoch)
writer.add_scalar('ycb test pose loss', test_pose_loss, epoch)
writer.add_scalar('ycb test dis', test_dis, epoch)
writer.add_scalar('ycb success rate', float(success_count) / test_count, epoch)
writer.add_scalar('lr', optimizer.param_groups[0]['lr'], epoch)
if test_dis <= best_test:
best_test = test_dis
if opt.refine_start:
torch.save(refiner.state_dict(), '{0}/pose_refine_model_{1}_{2}.pth'.format(opt.outf, epoch, test_dis))
else:
torch.save(estimator.state_dict(), '{0}/pose_model_{1}_{2}.pth'.format(opt.outf, epoch, test_dis))
print(epoch, '>>>>>>>>----------MODEL SAVED---------<<<<<<<<')
if best_test < opt.refine_margin and not opt.refine_start:
opt.refine_start = True
opt.lr = opt.lr_refine
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
print('>>>>>>>>----------Refine started---------<<<<<<<<')
writer.close()
def main():
# opt.manualSeed = random.randint(1, 10000)
# # opt.manualSeed = 1
# random.seed(opt.manualSeed)
# torch.manual_seed(opt.manualSeed)
torch.set_printoptions(threshold=5000)
# device_ids = [0,1]
cudnn.benchmark = True
if opt.dataset == 'ycb':
opt.num_objects = 21 #number of object classes in the dataset
opt.num_points = 1000 #number of points on the input pointcloud
opt.outf = 'trained_models/ycb' #folder to save trained models
opt.log_dir = 'experiments/logs/ycb' #folder to save logs
opt.repeat_epoch = 3 #number of repeat times for one epoch training
elif opt.dataset == 'linemod':
opt.num_objects = 13
opt.num_points = 500
opt.outf = 'trained_models/linemod'
opt.log_dir = 'experiments/logs/linemod'
opt.repeat_epoch = 20
else:
print('Unknown dataset')
return
estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects)
estimator.cuda()
refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects)
refiner.cuda()
# estimator = nn.DataParallel(estimator, device_ids=device_ids)
if opt.resume_posenet != '':
estimator.load_state_dict(
torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet)))
if opt.resume_refinenet != '':
refiner.load_state_dict(
torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet)))
opt.refine_start = True
opt.decay_start = True
opt.lr *= opt.lr_rate
opt.w *= opt.w_rate
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
else:
print('no refinement')
opt.refine_start = False
opt.decay_start = False
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
# optimizer = nn.DataParallel(optimizer, device_ids=device_ids)
if opt.dataset == 'ycb':
dataset = PoseDataset_ycb('train', opt.num_points, False,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
# print(dataset.list)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.workers)
if opt.dataset == 'ycb':
test_dataset = PoseDataset_ycb('test', opt.num_points, False,
opt.dataset_root, 0.0, opt.refine_start)
elif opt.dataset == 'linemod':
test_dataset = PoseDataset_linemod('test', opt.num_points, False,
opt.dataset_root, 0.0,
opt.refine_start)
testdataloader = torch.utils.data.DataLoader(test_dataset,
batch_size=1,
shuffle=False,
num_workers=opt.workers)
opt.sym_list = dataset.get_sym_list()
opt.num_points_mesh = dataset.get_num_points_mesh()
# print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'.format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list))
criterion = Loss(opt.num_points_mesh, opt.sym_list)
# criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
best_test = np.Inf
best_epoch = 0
if opt.start_epoch == 1:
for log in os.listdir(opt.log_dir):
os.remove(os.path.join(opt.log_dir, log))
st_time = time.time()
count_gen = 0
mode = 1
if mode == 1:
for epoch in range(opt.start_epoch, opt.nepoch):
logger = setup_logger(
'epoch%d' % epoch,
os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch))
logger.info('Train time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() -
st_time)) + ', ' +
'Training started'))
train_count = 0
train_dis_avg = 0.0
if opt.refine_start:
estimator.eval()
refiner.train()
else:
estimator.train()
optimizer.zero_grad()
for rep in range(opt.repeat_epoch):
for i, data in enumerate(dataloader, 0):
points, choose, img, target_sym, target_cen, idx, file_list_idx = data
if idx is 9 or idx is 16:
continue
# points, choose, img, target_sym, target_cen, target, idx, file_list_idx = data
# generate_obj_file(target_sym, target_cen, target, idx.squeeze())
# import pdb;pdb.set_trace()
points, choose, img, target_sym, target_cen, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target_sym).cuda(), \
Variable(target_cen).cuda(), \
Variable(idx).cuda()
# points, choose, img, target_sym, target_cen, idx = Variable(points), \
# Variable(choose), \
# Variable(img), \
# Variable(target_sym), \
# Variable(target_cen), \
# Variable(idx)
pred_norm, pred_on_plane, emb = estimator(
img, points, choose, idx)
# pred_norm_new = torch.cat((pred_norm, torch.zeros(1,pred_norm.size(1),1)),2)
# for i in range(pred_norm.size(1)):
# pred_norm_new[0,i,2] = torch.sqrt(1 - pred_norm[0,i,0] * pred_norm[0,i,0] - pred_norm[0,i,1] * pred_norm[0,i,1])
# if epoch % 10 == 0:
# generate_obj_file_pred(pred_norm, pred_on_plane, points, count_gen, idx)
# count_gen += 1
# print(pred_norm[0,0,:])
loss = criterion(pred_norm, pred_on_plane, target_sym,
target_cen, idx, points, opt.w,
opt.refine_start)
# scene_idx = dataset.list[file_list_idx]
loss.backward()
# train_dis_avg += dis.item()
train_count += 1
if train_count % opt.batch_size == 0:
logger.info(
'Train time {0} Epoch {1} Batch {2} Frame {3}'.
format(
time.strftime(
"%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)), epoch,
int(train_count / opt.batch_size),
train_count))
optimizer.step()
# for param_lr in optimizer.module.param_groups:
# param_lr['lr'] /= 2
optimizer.zero_grad()
train_dis_avg = 0
if train_count % 5000 == 0:
print(pred_on_plane.max())
print(pred_on_plane.mean())
if train_count != 0 and train_count % 1000 == 0:
if opt.refine_start:
torch.save(
refiner.state_dict(),
'{0}/pose_refine_model_current.pth'.format(
opt.outf))
else:
torch.save(
estimator.state_dict(),
'{0}/pose_model_current.pth'.format(opt.outf))
print('>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.
format(epoch))
logger = setup_logger(
'epoch%d_test' % epoch,
os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch))
logger.info('Test time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() -
st_time)) + ', ' +
'Testing started'))
test_loss = 0.0
test_count = 0
estimator.eval()
# refiner.eval()
# for rep in range(opt.repeat_epoch):
# for j, data in enumerate(testdataloader, 0):
# points, choose, img, target_sym, target_cen, idx, img_idx = data
# # points, choose, img, target, model_points, idx = Variable(points).cuda(), \
# # Variable(choose).cuda(), \
# # Variable(img).cuda(), \
# # Variable(target).cuda(), \
# # Variable(model_points).cuda(), \
# # Variable(idx).cuda()
# points, choose, img, target_sym, target_cen, idx = Variable(points), \
# Variable(choose), \
# Variable(img), \
# Variable(target_sym), \
# Variable(target_cen), \
# Variable(idx)
# pred_norm, pred_on_plane, emb = estimator(img, points, choose, idx)
# loss = criterion(pred_norm, pred_on_plane, target_sym, target_cen, idx, points, opt.w, opt.refine_start)
# test_loss += loss
# logger.info('Test time {0} Test Frame No.{1}'.format(time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)), test_count))
# test_count += 1
# test_loss = test_loss / test_count
logger.info(
'Test time {0} Epoch {1} TEST FINISH Avg dis: {2}'.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)), epoch,
test_loss))
print(pred_on_plane.max())
print(pred_on_plane.mean())
bs, num_p, _ = pred_on_plane.size()
# if epoch % 40 == 0:
# import pdb;pdb.set_trace()
best_test = test_loss
best_epoch = epoch
if opt.refine_start:
torch.save(
refiner.state_dict(),
'{0}/pose_refine_model_{1}_{2}.pth'.format(
opt.outf, epoch, test_loss))
else:
torch.save(
estimator.state_dict(),
'{0}/pose_model_{1}_{2}.pth'.format(
opt.outf, epoch, test_loss))
print(epoch,
'>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<')
if best_test < opt.decay_margin and not opt.decay_start:
opt.decay_start = True
opt.lr *= opt.lr_rate
# opt.w *= opt.w_rate
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
estimator.load_state_dict(
torch.load('{0}/pose_model_{1}_{2}.pth'.format(
opt.outf, best_epoch, best_test)))
else:
estimator.load_state_dict(
torch.load('{0}/pose_model_11_0.0.pth'.format(opt.outf)))
product_list = []
dist_list = []
true_positives = 0
false_positives = 0
false_negatives = 0
for index in range(len(test_dataset.list)):
img = Image.open('{0}/data_v1/{1}-color.png'.format(
test_dataset.root, test_dataset.list[index]))
depth = np.array(
Image.open('{0}/data_v1/{1}-depth.png'.format(
test_dataset.root, test_dataset.list[index])))
label = np.array(
Image.open('{0}/data_v1/{1}-label.png'.format(
test_dataset.root, test_dataset.list[index])))
meta = scio.loadmat('{0}/data_v1/{1}-meta.mat'.format(
test_dataset.root, test_dataset.list[index]))
cam_cx = test_dataset.cam_cx_1
cam_cy = test_dataset.cam_cy_1
cam_fx = test_dataset.cam_fx_1
cam_fy = test_dataset.cam_fy_1
mask_back = ma.getmaskarray(ma.masked_equal(label, 0))
obj = meta['cls_indexes'].flatten().astype(np.int32)
for idx in range(0, len(obj)):
print('object index: ', obj[idx])
mask_depth = ma.getmaskarray(ma.masked_not_equal(depth, 0))
mask_label = ma.getmaskarray(ma.masked_equal(label, obj[idx]))
mask = mask_label * mask_depth
if not (len(mask.nonzero()[0]) > test_dataset.minimum_num_pt
and len(test_dataset.symmetry[obj[idx]]['mirror']) > 0):
continue
rmin, rmax, cmin, cmax = get_bbox(mask_label)
img_temp = np.transpose(np.array(img)[:, :, :3],
(2, 0, 1))[:, rmin:rmax, cmin:cmax]
img_masked = img_temp
target_r = meta['poses'][:, :, idx][:, 0:3]
target_t = np.array(meta['poses'][:, :, idx][:, 3:4].flatten())
add_t = np.array([
random.uniform(-test_dataset.noise_trans,
test_dataset.noise_trans) for i in range(3)
])
choose = mask[rmin:rmax, cmin:cmax].flatten().nonzero()[0]
if len(choose) > test_dataset.num_pt:
c_mask = np.zeros(len(choose), dtype=int)
c_mask[:test_dataset.num_pt] = 1
np.random.shuffle(c_mask)
choose = choose[c_mask.nonzero()]
else:
choose = np.pad(choose, (0, test_dataset.num_pt - len(choose)),
'wrap')
depth_masked = depth[
rmin:rmax,
cmin:cmax].flatten()[choose][:, np.newaxis].astype(np.float32)
xmap_masked = test_dataset.xmap[
rmin:rmax,
cmin:cmax].flatten()[choose][:, np.newaxis].astype(np.float32)
ymap_masked = test_dataset.ymap[
rmin:rmax,
cmin:cmax].flatten()[choose][:, np.newaxis].astype(np.float32)
choose = np.array([choose])
cam_scale = meta['factor_depth'][0][0]
pt2 = depth_masked / cam_scale
pt0 = (ymap_masked - cam_cx) * pt2 / cam_fx
pt1 = (xmap_masked - cam_cy) * pt2 / cam_fy
cloud = np.concatenate((pt0, pt1, pt2), axis=1)
dellist = [j for j in range(0, len(test_dataset.cld[obj[idx]]))]
# dellist = random.sample(dellist, len(test_dataset.cld[obj[idx]]) - test_dataset.num_pt_mesh_small)
# model_points = np.delete(test_dataset.cld[obj[idx]], dellist, axis=0)
model_points = test_dataset.cld[obj[idx]]
target_sym = []
for sym in test_dataset.symmetry[obj[idx]]['mirror']:
target_sym.append(np.dot(sym, target_r.T))
target_sym = np.array(target_sym)
target_cen = np.add(test_dataset.symmetry[obj[idx]]['center'],
target_t)
target = np.dot(model_points, target_r.T)
target = np.add(target, target_t)
print('ground truth norm: ', target_sym)
print('ground truth center: ', target_cen)
points_ten, choose_ten, img_ten, target_sym_ten, target_cen_ten, target_ten, idx_ten = \
torch.from_numpy(cloud.astype(np.float32)).unsqueeze(0), \
torch.LongTensor(choose.astype(np.int32)).unsqueeze(0), \
test_dataset.norm(torch.from_numpy(img_masked.astype(np.float32))).unsqueeze(0), \
torch.from_numpy(target_sym.astype(np.float32)).unsqueeze(0), \
torch.from_numpy(target_cen.astype(np.float32)).unsqueeze(0), \
torch.from_numpy(target.astype(np.float32)).unsqueeze(0), \
torch.LongTensor([obj[idx]-1]).unsqueeze(0)
# print(img_ten.size())
# print(points_ten.size())
# print(choose_ten.size())
# print(idx_ten.size())
points_ten, choose_ten, img_ten, target_sym_ten, target_cen_ten, idx_ten = Variable(points_ten).cuda(), \
Variable(choose_ten).cuda(), \
Variable(img_ten).cuda(), \
Variable(target_sym_ten).cuda(), \
Variable(target_cen_ten).cuda(), \
Variable(idx_ten).cuda()
pred_norm, pred_on_plane, emb = estimator(img_ten, points_ten,
choose_ten, idx_ten)
# import pdb;pdb.set_trace()
bs, num_p, _ = pred_on_plane.size()
# pred_norm = torch.cat((pred_norm, torch.zeros(1,pred_norm.size(1),1)),2)
# for i in range(pred_norm.size(1)):
# pred_norm[0,i,2] = torch.sqrt(1 - pred_norm[0,i,0] * pred_norm[0,i,0] - pred_norm[0,i,1] * pred_norm[0,i,1])
# pred_norm = pred_norm / (torch.norm(pred_norm, dim=2).view(bs, num_p, 1))
generate_obj_file_norm_pred(
pred_norm / (torch.norm(pred_norm, dim=2).view(bs, num_p, 1)),
pred_on_plane, points_ten,
test_dataset.list[index].split('/')[0],
test_dataset.list[index].split('/')[1], obj[idx])
loss = criterion(pred_norm, pred_on_plane, target_sym_ten,
target_cen_ten, idx, points_ten, opt.w,
opt.refine_start)
# print('test loss: ', loss)
# bs, num_p, _ = pred_on_plane.size()
pred_norm = pred_norm / (torch.norm(pred_norm, dim=2).view(
bs, num_p, 1))
pred_norm = pred_norm.cpu().detach().numpy()
pred_on_plane = pred_on_plane.cpu().detach().numpy()
points = points_ten.cpu().detach().numpy()
clustering_points_idx = np.where(
pred_on_plane > pred_on_plane.max() * PRED_ON_PLANE_FACTOR +
pred_on_plane.mean() * (1 - PRED_ON_PLANE_FACTOR))[1]
clustering_norm = pred_norm[0, clustering_points_idx, :]
clustering_points = points[0, clustering_points_idx, :]
num_points = len(clustering_points_idx)
# import pdb;pdb.set_trace()
close_thresh = 5e-3
broad_thresh = 7e-3
sym_flag = [0 for i in range(target_sym.shape[0])]
sym_max_product = [0.0 for i in range(target_sym.shape[0])]
sym_dist = [0.0 for i in range(target_sym.shape[0])]
count_pred = 0
while True:
if num_points == 0:
break
count_pred += 1
if count_pred > target_sym.shape[0]:
break
best_fit_num = 0
count_try = 0
while True:
if count_try > 3 or num_points <= 1:
break
pick_idx = np.random.randint(0, num_points - 1)
pick_point = clustering_points[pick_idx]
# proposal_norm = np.array(Plane(Point3D(pick_points[0]),Point3D(pick_points[1]),Point3D(pick_points[2])).normal_vector).astype(np.float32)
proposal_norm = clustering_norm[pick_idx]
proposal_norm = proposal_norm[:, np.newaxis]
# import pdb;pdb.set_trace()
proposal_point = pick_point
# highest_pred_idx = np.argmax(pred_on_plane[0,clustering_points_idx,:])
# highest_pred_loc = clustering_points[highest_pred_idx]
# proposal_norm = clustering_norm[highest_pred_idx][:,np.newaxis]
clustering_diff = clustering_points - proposal_point
clustering_dist = np.abs(
np.matmul(clustering_diff, proposal_norm))
broad_inliers = np.where(clustering_dist < broad_thresh)[0]
broad_inlier_num = len(broad_inliers)
close_inliers = np.where(clustering_dist < close_thresh)[0]
close_inlier_num = len(close_inliers)
if broad_inlier_num > num_points / (5 - count_pred):
best_fit_num = close_inlier_num
best_fit_norm = proposal_norm
best_fit_cen = clustering_points[close_inliers].mean(0)
best_fit_idx = clustering_points_idx[close_inliers]
scrub_idx = clustering_points_idx[broad_inliers]
break
else:
count_try += 1
# else:
# np.delete(clustering_points_idx, highest_pred_idx)
# num_points -= 1
if count_try > 3 or num_points <= 1:
break
for i in range(2):
def f(x):
dist = 0
x = x / LA.norm(x)
for point in clustering_points[broad_inliers]:
dist += np.abs(point[0] * x[0] + point[1] * x[1] +
point[2] * np.sqrt(1 - x[0] * x[0] -
x[1] * x[1]) +
x[2])
return dist
start_point = np.copy(proposal_norm)
start_point[2] = (-proposal_point *
proposal_norm[:, 0]).sum()
min_point = fmin(f, start_point)
new_pred_loc = np.array([
0, 0, -min_point[2] /
np.sqrt(1 - min_point[0] * min_point[0] -
min_point[1] * min_point[1])
])
min_point[2] = np.sqrt(1 - min_point[0] * min_point[0] -
min_point[1] * min_point[1])
new_proposal_norm = min_point
clustering_diff = clustering_points - new_pred_loc
clustering_dist = np.abs(
np.matmul(clustering_diff, new_proposal_norm))
close_inliers = np.where(clustering_dist < close_thresh)[0]
new_close_inlier_num = len(close_inliers)
broad_inliers = np.where(clustering_dist < broad_thresh)[0]
new_broad_inlier_num = len(broad_inliers)
# import pdb;pdb.set_trace()
if new_close_inlier_num > close_inlier_num:
best_fit_num = new_close_inlier_num
# proposal_point = clustering_points_idx[clustering_dist.argmin()]
proposal_point = new_pred_loc
best_fit_norm = new_proposal_norm[:, np.newaxis]
best_fit_idx = clustering_points_idx[close_inliers]
scrub_idx = clustering_points_idx[broad_inliers]
best_fit_cen = new_pred_loc
inlier_num = new_inlier_num
proposal_norm = best_fit_norm
# other_idx_pick = other_idx[other_idx_pick]
# if len(other_idx_pick) > num_points//6:
# pick_idx = np.concatenate((pick_idx, other_idx_pick), 0)
# norm_proposal_new = clustering_norm[pick_idx,:].mean(0)
# norm_proposal_new = norm_proposal_new / LA.norm(norm_proposal_new)
# inlier_num_new = len(np.where(np.abs(clustering_norm-norm_proposal_new).sum(1) < thresh)[0])
# if inlier_num_new > inlier_num:
# best_fit_num = inlier_num_new
# best_fit_idx = np.where(np.abs(clustering_norm-norm_proposal_new).sum(1) < thresh_scrap)
# best_fit_norm = norm_proposal_new
# best_fit_cen = clustering_points[best_fit_idx].mean(0)
if best_fit_num == 0:
break
else:
print('predicted norm:{}, predicted point:{}'.format(
best_fit_norm, best_fit_cen))
max_idx = np.argmax(np.matmul(target_sym, best_fit_norm))
sym_flag[max_idx] += 1
sym_product = np.abs((target_sym[max_idx] *
(best_fit_cen - target_cen)).sum())
if sym_max_product[max_idx] < sym_product:
sym_max_product[max_idx] = sym_product
sym_dist[max_idx] = np.matmul(target_sym,
best_fit_norm)[max_idx]
# generate_obj_file_sym_pred(best_fit_norm, best_fit_cen, target_ten, test_dataset.list[index].split('/')[0], test_dataset.list[index].split('/')[1], obj[idx], count_pred)
# import pdb;pdb.set_trace()
clustering_points_idx = np.setdiff1d(
clustering_points_idx, scrub_idx)
clustering_norm = pred_norm[0, clustering_points_idx, :]
clustering_points = points[0, clustering_points_idx, :]
num_points = len(clustering_points_idx)
for i in range(target_sym.shape[0]):
if sym_flag[i] >= 1:
dist_list.append(sym_dist[i])
product_list.append(sym_max_product[i])
false_positives += sym_flag[i] - 1
else:
false_negatives += 1
product_list = np.array(product_list)
dist_list = np.array(dist_list)
# import pdb;pdb.set_trace()
total_num = len(product_list)
prec = []
recall = []
for t in range(1000):
good_ones = len(
np.logical_and(dist_list < 0.5 * t / 1000,
product_list > math.cos(math.pi * 0.25 * t / 1000)))
prec.append(good_ones * 1.0 / (false_positives + total_num))
recall.append(good_ones * 1.0 / (good_ones + false_negatives))
print(prec)
print(recall)
plt.plot(recall, prec, 'r')
plt.axis([0, 1, 0, 1])
plt.savefig('prec-recall.png')
def main():
opt.manualSeed = random.randint(1, 10000)
random.seed(opt.manualSeed)
torch.manual_seed(opt.manualSeed)
if opt.dataset == 'linemod':
opt.num_objects = 13
opt.num_points = 500
opt.outf = 'trained_models/linemod'
opt.log_dir = 'experiments/logs/linemod'
output_results = 'check_linemod.txt'
opt.repeat_epoch = 20
elif opt.dataset == 'ycb':
opt.num_objects = 21 #number of object classes in the dataset
opt.num_points = 1000 #number of points on the input pointcloud
opt.outf = 'trained_models/ycb' #folder to save trained models
opt.log_dir = 'experiments/logs/ycb' #folder to save logs
opt.repeat_epoch = 1 #number of repeat times for one epoch training
elif opt.dataset == 'ycb-syn':
opt.num_objects = 31 # number of object classes in the dataset
opt.num_points = 1000 # number of points on the input pointcloud
opt.dataset_root = '/data/Akeaveny/Datasets/ycb_syn'
opt.outf = 'trained_models/ycb_syn/ycb_syn2' # folder to save trained models
opt.log_dir = 'experiments/logs/ycb_syn/ycb_syn2' # folder to save logs
output_results = 'check_ycb_syn.txt'
opt.w = 0.05
opt.refine_margin = 0.01
elif opt.dataset == 'arl':
opt.num_objects = 10 # number of object classes in the dataset
opt.num_points = 1000 # number of points on the input pointcloud
opt.dataset_root = '/data/Akeaveny/Datasets/arl_dataset'
opt.outf = 'trained_models/arl/clutter/arl_finetune_syn_2' # folder to save trained models
opt.log_dir = '/home/akeaveny/catkin_ws/src/object-rpe-ak/DenseFusion/experiments/logs/arl/clutter/arl_finetune_syn_2' # folder to save logs
output_results = 'check_arl_syn.txt'
opt.nepoch = 750
opt.w = 0.05
opt.refine_margin = 0.0045
# TODO
opt.repeat_epoch = 20
opt.start_epoch = 0
opt.resume_posenet = 'pose_model_1_0.012397416144377301.pth'
opt.resume_refinenet = 'pose_refine_model_153_0.004032851301599294.pth'
elif opt.dataset == 'arl1':
opt.num_objects = 5 # number of object classes in the dataset
opt.num_points = 1000 # number of points on the input pointcloud
opt.dataset_root = '/data/Akeaveny/Datasets/arl_dataset'
opt.outf = 'trained_models/arl1/clutter/arl_real_2' # folder to save trained models
opt.log_dir = '/home/akeaveny/catkin_ws/src/object-rpe-ak/DenseFusion/experiments/logs/arl1/clutter/arl_real_2' # folder to save logs
output_results = 'check_arl_syn.txt'
opt.nepoch = 750
opt.w = 0.05
opt.refine_margin = 0.015
# opt.start_epoch = 120
# opt.resume_posenet = 'pose_model_current.pth'
# opt.resume_refinenet = 'pose_refine_model_115_0.008727498716640046.pth'
elif opt.dataset == 'elevator':
opt.num_objects = 1 # number of object classes in the dataset
opt.num_points = 1000 # number of points on the input pointcloud
opt.dataset_root = '/data/Akeaveny/Datasets/elevator_dataset'
opt.outf = 'trained_models/elevator/elevator_2' # folder to save trained models
opt.log_dir = '/home/akeaveny/catkin_ws/src/object-rpe-ak/DenseFusion/experiments/logs/elevator/elevator_2' # folder to save logs
output_results = 'check_arl_syn.txt'
opt.nepoch = 750
opt.w = 0.05
opt.refine_margin = 0.015
opt.nepoch = 750
opt.w = 0.05
opt.refine_margin = 0.015
# TODO
opt.repeat_epoch = 40
# opt.start_epoch = 47
# opt.resume_posenet = 'pose_model_current.pth'
# opt.resume_refinenet = 'pose_refine_model_46_0.007581770288279472.pth'
else:
print('Unknown dataset')
return
estimator = PoseNet(num_points=opt.num_points, num_obj=opt.num_objects)
estimator.cuda()
refiner = PoseRefineNet(num_points=opt.num_points, num_obj=opt.num_objects)
refiner.cuda()
if opt.resume_posenet != '':
estimator.load_state_dict(
torch.load('{0}/{1}'.format(opt.outf, opt.resume_posenet)))
if opt.resume_refinenet != '':
refiner.load_state_dict(
torch.load('{0}/{1}'.format(opt.outf, opt.resume_refinenet)))
opt.refine_start = False
opt.decay_start = False
opt.lr *= opt.lr_rate
opt.w *= opt.w_rate
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
else:
opt.refine_start = False
opt.decay_start = False
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
if opt.dataset == 'ycb':
dataset = PoseDataset_ycb('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'ycb-syn':
dataset = PoseDataset_ycb_syn('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'arl':
dataset = PoseDataset_arl('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'arl1':
dataset = PoseDataset_arl1('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'elevator':
dataset = PoseDataset_elevator('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.workers)
if opt.dataset == 'ycb':
test_dataset = PoseDataset_ycb('test', opt.num_points, False,
opt.dataset_root, 0.0, opt.refine_start)
elif opt.dataset == 'linemod':
test_dataset = PoseDataset_linemod('test', opt.num_points, False,
opt.dataset_root, 0.0,
opt.refine_start)
elif opt.dataset == 'ycb-syn':
test_dataset = PoseDataset_ycb_syn('test', opt.num_points, True,
opt.dataset_root, 0.0,
opt.refine_start)
elif opt.dataset == 'arl':
test_dataset = PoseDataset_arl('test', opt.num_points, True,
opt.dataset_root, 0.0, opt.refine_start)
elif opt.dataset == 'arl1':
test_dataset = PoseDataset_arl1('test', opt.num_points, True,
opt.dataset_root, 0.0,
opt.refine_start)
elif opt.dataset == 'elevator':
test_dataset = PoseDataset_elevator('test', opt.num_points, True,
opt.dataset_root, 0.0,
opt.refine_start)
testdataloader = torch.utils.data.DataLoader(test_dataset,
batch_size=1,
shuffle=False,
num_workers=opt.workers)
opt.sym_list = dataset.get_sym_list()
opt.num_points_mesh = dataset.get_num_points_mesh()
print(
'>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'
.format(len(dataset), len(test_dataset), opt.num_points_mesh,
opt.sym_list))
criterion = Loss(opt.num_points_mesh, opt.sym_list)
criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
best_test = np.Inf
if opt.start_epoch == 1:
for log in os.listdir(opt.log_dir):
os.remove(os.path.join(opt.log_dir, log))
st_time = time.time()
######################
######################
# TODO (ak): set up tensor board
# if not os.path.exists(opt.log_dir):
# os.makedirs(opt.log_dir)
#
# writer = SummaryWriter(opt.log_dir)
######################
######################
for epoch in range(opt.start_epoch, opt.nepoch):
logger = setup_logger(
'epoch%d' % epoch,
os.path.join(opt.log_dir, 'epoch_%d_log.txt' % epoch))
logger.info('Train time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) +
', ' + 'Training started'))
train_count = 0
train_dis_avg = 0.0
if opt.refine_start:
estimator.eval()
refiner.train()
else:
estimator.train()
optimizer.zero_grad()
for rep in range(opt.repeat_epoch):
##################
# train
##################
for i, data in enumerate(dataloader, 0):
points, choose, img, target, model_points, idx = data
# TODO: txt file
# fw = open(test_folder + output_results, 'w')
# fw.write('Points\n{0}\n\nchoose\n{1}\n\nimg\n{2}\n\ntarget\n{3}\n\nmodel_points\n{4}'.format(points, choose, img, target, model_points))
# fw.close()
points, choose, img, target, model_points, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target).cuda(), \
Variable(model_points).cuda(), \
Variable(idx).cuda()
pred_r, pred_t, pred_c, emb = estimator(
img, points, choose, idx)
loss, dis, new_points, new_target = criterion(
pred_r, pred_t, pred_c, target, model_points, idx, points,
opt.w, opt.refine_start)
if opt.refine_start:
for ite in range(0, opt.iteration):
pred_r, pred_t = refiner(new_points, emb, idx)
dis, new_points, new_target = criterion_refine(
pred_r, pred_t, new_target, model_points, idx,
new_points)
dis.backward()
else:
loss.backward()
train_dis_avg += dis.item()
train_count += 1
if train_count % opt.batch_size == 0:
logger.info(
'Train time {} Epoch {} Batch {} Frame {}/{} Avg_dis: {:.2f} [cm]'
.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)),
epoch, int(train_count / opt.batch_size),
train_count, len(dataset.list),
train_dis_avg / opt.batch_size * 100))
optimizer.step()
optimizer.zero_grad()
# TODO: tensorboard
# if train_count != 0 and train_count % 250 == 0:
# scalar_info = {'loss': loss.item(),
# 'dis': train_dis_avg / opt.batch_size}
# for key, val in scalar_info.items():
# writer.add_scalar(key, val, train_count)
train_dis_avg = 0
if train_count != 0 and train_count % 1000 == 0:
if opt.refine_start:
torch.save(
refiner.state_dict(),
'{0}/pose_refine_model_current.pth'.format(
opt.outf))
else:
torch.save(
estimator.state_dict(),
'{0}/pose_model_current.pth'.format(opt.outf))
# TODO: tensorboard
# scalar_info = {'loss': loss.item(),
# 'dis': dis.item()}
# for key, val in scalar_info.items():
# writer.add_scalar(key, val, train_count)
print(
'>>>>>>>>----------epoch {0} train finish---------<<<<<<<<'.format(
epoch))
logger = setup_logger(
'epoch%d_test' % epoch,
os.path.join(opt.log_dir, 'epoch_%d_test_log.txt' % epoch))
logger.info('Test time {0}'.format(
time.strftime("%Hh %Mm %Ss", time.gmtime(time.time() - st_time)) +
', ' + 'Testing started'))
test_dis = 0.0
test_count = 0
estimator.eval()
refiner.eval()
for j, data in enumerate(testdataloader, 0):
points, choose, img, target, model_points, idx = data
points, choose, img, target, model_points, idx = Variable(points).cuda(), \
Variable(choose).cuda(), \
Variable(img).cuda(), \
Variable(target).cuda(), \
Variable(model_points).cuda(), \
Variable(idx).cuda()
pred_r, pred_t, pred_c, emb = estimator(img, points, choose, idx)
_, dis, new_points, new_target = criterion(pred_r, pred_t, pred_c,
target, model_points,
idx, points, opt.w,
opt.refine_start)
if opt.refine_start:
for ite in range(0, opt.iteration):
pred_r, pred_t = refiner(new_points, emb, idx)
dis, new_points, new_target = criterion_refine(
pred_r, pred_t, new_target, model_points, idx,
new_points)
test_dis += dis.item()
logger.info('Test time {} Test Frame No.{} dis: {} [cm]'.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)), test_count,
dis * 100))
test_count += 1
test_dis = test_dis / test_count
logger.info(
'Test time {} Epoch {} TEST FINISH Avg dis: {} [cm]'.format(
time.strftime("%Hh %Mm %Ss",
time.gmtime(time.time() - st_time)), epoch,
test_dis * 100))
# TODO: tensorboard
# scalar_info = {'test dis': test_dis}
# for key, val in scalar_info.items():
# writer.add_scalar(key, val, train_count)
if test_dis <= best_test:
best_test = test_dis
if opt.refine_start:
torch.save(
refiner.state_dict(),
'{0}/pose_refine_model_{1}_{2}.pth'.format(
opt.outf, epoch, test_dis))
else:
torch.save(
estimator.state_dict(),
'{0}/pose_model_{1}_{2}.pth'.format(
opt.outf, epoch, test_dis))
print(epoch,
'>>>>>>>>----------BEST TEST MODEL SAVED---------<<<<<<<<')
if best_test < opt.decay_margin and not opt.decay_start:
opt.decay_start = True
opt.lr *= opt.lr_rate
opt.w *= opt.w_rate
optimizer = optim.Adam(estimator.parameters(), lr=opt.lr)
if best_test < opt.refine_margin and not opt.refine_start:
opt.refine_start = True
opt.batch_size = int(opt.batch_size / opt.iteration)
optimizer = optim.Adam(refiner.parameters(), lr=opt.lr)
if opt.dataset == 'ycb':
dataset = PoseDataset_ycb('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('train', opt.num_points, True,
opt.dataset_root,
opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'ycb-syn':
dataset = PoseDataset_ycb_syn('train', opt.num_points, True,
opt.dataset_root,
opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'arl':
dataset = PoseDataset_arl('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'arl1':
dataset = PoseDataset_arl1('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'elevator':
dataset = PoseDataset_elevator('train', opt.num_points, True,
opt.dataset_root,
opt.noise_trans,
opt.refine_start)
dataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=opt.workers)
if opt.dataset == 'ycb':
test_dataset = PoseDataset_ycb('test', opt.num_points, False,
opt.dataset_root, 0.0,
opt.refine_start)
elif opt.dataset == 'linemod':
test_dataset = PoseDataset_linemod('test', opt.num_points,
False, opt.dataset_root,
0.0, opt.refine_start)
elif opt.dataset == 'ycb-syn':
test_dataset = PoseDataset_ycb_syn('test', opt.num_points,
True, opt.dataset_root, 0.0,
opt.refine_start)
elif opt.dataset == 'arl':
test_dataset = PoseDataset_arl('test', opt.num_points, True,
opt.dataset_root, 0.0,
opt.refine_start)
elif opt.dataset == 'arl1':
test_dataset = PoseDataset_arl1('test', opt.num_points, True,
opt.dataset_root, 0.0,
opt.refine_start)
elif opt.dataset == 'elevator':
test_dataset = PoseDataset_elevator('test', opt.num_points,
True, opt.dataset_root,
0.0, opt.refine_start)
testdataloader = torch.utils.data.DataLoader(
test_dataset,
batch_size=1,
shuffle=False,
num_workers=opt.workers)
opt.sym_list = dataset.get_sym_list()
opt.num_points_mesh = dataset.get_num_points_mesh()
print(
'>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'
.format(len(dataset), len(test_dataset), opt.num_points_mesh,
opt.sym_list))
criterion = Loss(opt.num_points_mesh, opt.sym_list)
criterion_refine = Loss_refine(opt.num_points_mesh, opt.sym_list)
def main():
opt.manualSeed = random.randint(1, 10000)
random.seed(opt.manualSeed)
torch.manual_seed(opt.manualSeed)
device_cpu = torch.device('cpu')
if opt.gpu:
if torch.cuda.is_available():
device = torch.device('cuda:0')
else:
device = torch.device('cpu')
else:
device = torch.device('cpu')
if torch.cuda.is_available():
torch.cuda.empty_cache()
torch.backends.cudnn.benchmark = True
if opt.dataset == 'ycb':
opt.num_objects = 21 #number of object classes in the dataset
opt.num_points = 1000 #number of points on the input pointcloud
opt.outf = 'trained_models/ycb' #folder to save trained models
opt.log_dir = 'experiments/logs/ycb' #folder to save logs
opt.repeat_epoch = 1 #number of repeat times for one epoch training
elif opt.dataset == 'linemod':
opt.num_objects = 10
opt.num_points = 500
opt.outf = 'trained_models/linemod'
opt.log_dir = 'experiments/logs/linemod'
opt.repeat_epoch = 20
else:
print('Unknown dataset')
return
# check for the network mode
if not opt.vertex_reg and opt.vertex_reg_hough:
assert ValueError('Mode Incorrect')
if opt.mode == "train":
if opt.dataset == 'ycb':
# print("No YCB dataset")
# return
dataset = PoseDataset_ycb('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('train', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start, False, True,
opt.vertex_reg, opt.vertex_reg_hough)
trainloader = torch.utils.data.DataLoader(dataset,
batch_size=opt.batch_size,
shuffle=True,
num_workers=opt.workers)
# print("dataset cld : " + str(dataset.cld))
# return
if opt.mode == "eval":
if opt.dataset == 'ycb':
dataset = PoseDataset_ycb('test', opt.num_points, True,
opt.dataset_root, opt.noise_trans,
opt.refine_start)
# print("No YCB dataset")
# return
# test_dataset = PoseDataset_ycb('test', opt.num_points, False, opt.dataset_root,
# 0.0, opt.refine_start)
elif opt.dataset == 'linemod':
dataset = PoseDataset_linemod('test', opt.num_points, False,
opt.dataset_root, 0.0,
opt.refine_start, False, True,
opt.vertex_reg, opt.vertex_reg_hough)
testdataloader = torch.utils.data.DataLoader(dataset,
batch_size=1,
shuffle=False,
num_workers=opt.workers)
# if opt.dataset == 'ycb':
# pass
# else:
# ap_data = PoseDataset_linemod('test', opt.num_points, False, opt.dataset_root, 0.0,
# opt.refine_start, True, True, opt.vertex_reg, opt.vertex_reg_hough)
# ap_loader = torch.utils.data.DataLoader(ap_data, batch_size=1, shuffle=False, num_workers=opt.workers)
# dataset = test_dataset
opt.sym_list = dataset.get_sym_list()
opt.num_points_mesh = dataset.get_num_points_mesh()
# print(opt.sym_list)
# print('>>>>>>>>----------Dataset loaded!---------<<<<<<<<\nlength of the training set: {0}\nlength of the testing set: {1}\nnumber of sample points on mesh: {2}\nsymmetry object list: {3}'.format(len(dataset), len(test_dataset), opt.num_points_mesh, opt.sym_list))
# Network, optimizer and loss
net = vgg16_convs(None, opt.num_objects, opt.num_objects, opt.scales,
opt.threshold_label, opt.vote_threshold, opt.vertex_reg,
opt.vertex_reg, opt.vertex_reg_hough)
# net = vgg16_convs_comb_seg_center(None, opt.num_objects, opt.num_objects, opt.scales, opt.threshold_label,
# opt.vote_threshold, opt.vertex_reg, opt.combine_seg_center)
optimizer = optim.Adam(net.parameters(), lr=opt.lr)
# weight_class = torch.from_numpy(dataset.weight_clsss).type('torch.FloatTensor').to(device)
# criterion = nn.CrossEntropyLoss(weight_class)
criterion = nn.CrossEntropyLoss()
# criterion = nn.BCELoss()
# criterion = nn.MSELoss()
criterion_center = nn.SmoothL1Loss()
# Load pretrained model
start_epoch = 0
if opt.flag_pretrained and not opt.flag_pretrained_vgg:
# load out model trained before as initialization to continue
if os.path.isfile(opt.path_pretrained):
print("=> Loading Checkpoint '{}'".format(opt.path_pretrained))
pre_trained = torch.load(opt.path_pretrained)
net_dic = net.state_dict()
net_dic_new = net_dic
pretrained_dic = pre_trained['state_dict']
pretrained_list = list(pretrained_dic.items())
# print("pretrained list length : " + str(len(pretrained_list)))
# net.load_state_dict()
start_epoch = pre_trained['epoch']
if opt.num_pretrain_param_load > 0:
count = 0
for k, v in net_dic.items():
if count >= opt.num_pretrain_param_load:
break
name_temp, value_pretrained = pretrained_list[count]
if opt.gpu:
net_dic_new[k] = value_pretrained
else:
net_dic_new[k] = value_pretrained.cpu()
count += 1
# print("net dic new k : " + str(net_dic_new[k]))
print("count : " + str(count))
net.load_state_dict(net_dic_new)
"""
optimizer.load_state_dict(pre_trained['optimizer'])
for state in optimizer.state.values():
for k, v in state.items():
if torch.cuda.is_available:
if isinstance(v, torch.Tensor):
state[k] = v.cuda()
"""
print("=> Loaded Checkpoint '{}'".format(opt.path_pretrained))
print("Start epoch : " + str(start_epoch))
else:
assert ValueError("no pretrained_model found at {}".format(
opt.path_pretrained))
count = 0
for param in net.parameters():
if count >= opt.num_pretrain_param_freeze:
break
param.requires_grad = False
count += 1
elif not opt.flag_pretrained and opt.flag_pretrained_vgg:
# load the pretrained weight of VGG16 net
# 'vgg16': 'https://download.pytorch.org/models/vgg16-397923af.pth'
pretrained_dic = torch.load('pretrained_model\\vgg16-397923af.pth')
pretrained_list = list(pretrained_dic.items())
net_dic = net.state_dict()
net_dic_new = net_dic
count = 0
for k, v in net_dic.items():
name_temp, value_pretrained = pretrained_list[count]
net_dic_new[k] = value_pretrained
count += 1
if count >= opt.num_pretrain_param_vgg:
break
net.load_state_dict(net_dic_new)
count = 0
for param in net.parameters():
param.requires_grad = False
count += 1
if count >= opt.num_pretrain_param_vgg:
break
elif not opt.flag_pretrained and not opt.flag_pretrained_vgg:
print('without laod any pretrained model')
else:
print(
'Collision with the flag of load vgg param and laod pretrain model'
)
net.to(device)
if opt.mode == "train":
loss_his = []
loss_his = train(trainloader, net, criterion, criterion_center,
optimizer, device, device_cpu, start_epoch)
print('>>>>>>>>----------Training Finished!---------<<<<<<<<')
if opt.mode == "eval":
test_loss = 0
test_loss = test(testdataloader, net, criterion, criterion_center,
device, device_cpu)
print('>>>>>>>>----------AP---------<<<<<<<<')
# aps = None
# if opt.train_single_frame:
# aps = cal_AP(ap_loader, net, criterion, device, opt.num_objects, opt)
# aps = np.array(aps)
# print('Final mean AP : {}'.format(np.mean(aps)))
# print('>>>>>>>>----------Save the model weights!---------<<<<<<<<')
# if opt.save_model:
# # save the trained model
# save_checkpoint({
# 'epoch': opt.nepoch,
# 'arch': opt.arch,
# 'state_dict': net.state_dict(),
# 'test_loss': test_loss,
# 'aps': "aps",
# 'optimizer' : optimizer.state_dict(),
# }, False)
# print('>>>>>>>>----------Loss History---------<<<<<<<<')
# np.save('log//loss//loss', np.array(loss_his))
# plt.figure()
# plt.plot(loss_his)
# plt.show()
# <<<<<<< HEAD
# plt.savefig('/home/ubuntu/EECS442_CourseProject/log/loss/unfreeze_seg_ctr.png')
# =======
# plt.savefig('log//loss//loss.png')
# >>>>>>> ce96c070c17b981e90464ae0b458ab905b1009db
print('>>>>>>>>----------The End---------<<<<<<<<')