def demo():
net = Resnet18_8s(ver_dim=vote_num * 2, seg_dim=2)
net = NetWrapper(net).cuda()
net = DataParallel(net)
optimizer = optim.Adam(net.parameters(), lr=train_cfg['lr'])
model_dir = os.path.join(cfg.MODEL_DIR, "cat_demo")
load_model(net.module.net, optimizer, model_dir, args.load_epoch)
data, points_3d, bb8_3d = read_data()
image, mask, vertex, vertex_weights, pose, corner_target = [
d.unsqueeze(0).cuda() for d in data
]
seg_pred, vertex_pred, loss_seg, loss_vertex, precision, recall = net(
image, mask, vertex, vertex_weights)
eval_net = DataParallel(EvalWrapper().cuda())
corner_pred = eval_net(seg_pred, vertex_pred).cpu().detach().numpy()[0]
camera_matrix = np.array([[572.4114, 0., 325.2611],
[0., 573.57043, 242.04899], [0., 0., 1.]])
pose_pred = pnp(points_3d, corner_pred, camera_matrix)
projector = Projector()
bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'linemod')
bb8_2d_gt = projector.project(bb8_3d, pose[0].detach().cpu().numpy(),
'linemod')
image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
visualize_bounding_box(image[None, ...], bb8_2d_pred[None, None, ...],
bb8_2d_gt[None, None, ...])
def demo():
net = Resnet18_8s(ver_dim=vote_num * 2, seg_dim=2)
net = NetWrapper(net).cuda()
net = DataParallel(net)
optimizer = optim.Adam(net.parameters(), lr=train_cfg['lr'])
model_dir = os.path.join(cfg.MODEL_DIR, "switch_linemod_train")
load_model(net.module.net, optimizer, model_dir, -1)
image, points_3d, bb8_3d = read_data()
image = image[None, ...]
seg_pred, vertex_pred = net(image)
# visualize_mask(mask)
# visualize_vertex(vertex, vertex_weights)
# visualize_hypothesis(image, seg_pred, vertex_pred, corner_target)
# visualize_voting_ellipse(image, seg_pred, vertex_pred, corner_target)
eval_net = DataParallel(EvalWrapper().cuda())
corner_pred = eval_net(seg_pred, vertex_pred).cpu().detach().numpy()[0]
camera_matrix = np.array([[572.4114, 0., 325.2611],
[0., 573.57043, 242.04899], [0., 0., 1.]])
pose_pred = pnp(points_3d, corner_pred, camera_matrix)
projector = Projector()
bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'linemod')
print(bb8_2d_pred)
image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
visualize_bounding_box(image[None, ...], bb8_2d_pred[None, None, ...])
def demo():
net = Resnet18_8s(ver_dim=vote_num * 2, seg_dim=2)
net = NetWrapper(net).cuda()
net = DataParallel(net)
optimizer = optim.Adam(net.parameters(), lr=train_cfg['lr'])
model_dir = os.path.join(cfg.MODEL_DIR, "cat_linemod_train") #cat_demo
load_model(net.module.net, optimizer, model_dir, args.load_epoch)
data, points_3d, bb8_3d = read_data()
image, mask, vertex, vertex_weights, pose, corner_target = [
d.unsqueeze(0).cuda() for d in data
]
seg_pred, vertex_pred, loss_seg, loss_vertex, precision, recall = net(
image, mask, vertex, vertex_weights)
eval_net = DataParallel(EvalWrapper().cuda())
#向量方形图，语义分割图，然后 ransac 计算 kp，，向量方向图一旦准了，kp也就准了
corner_pred = eval_net(seg_pred, vertex_pred).cpu().detach().numpy()[0]
camera_matrix = np.array([[572.4114, 0., 325.2611],
[0., 573.57043, 242.04899], [0., 0., 1.]])
pose_pred = pnp(points_3d, corner_pred, camera_matrix)
projector = Projector()
#
bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'linemod')
bb8_2d_gt = projector.project(bb8_3d, pose[0].detach().cpu().numpy(),
'linemod')
image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
print("loss_seg:{} , loss_vertex:{} , precision:{},recall:{}, ".format(
loss_seg, loss_vertex, precision, recall))
#399.pth
#loss_seg:tensor([0.0015], device='cuda:0', grad_fn=<MeanBackward0>) , loss_vertex:tensor([0.0016], device='cuda:0', grad_fn=<DivBackward1>) ,
#precision:tensor([0.9434], device='cuda:0'),recall:tensor([0.9677], device='cuda:0'),
#199.pth
# loss_seg:tensor([0.0015], device='cuda:0', grad_fn=<MeanBackward0>) , loss_vertex:tensor([0.0016], device='cuda:0', grad_fn=<DivBackward1>) ,
# precision:tensor([0.9583], device='cuda:0'),recall:tensor([0.9524], device='cuda:0'),
erro = bb8_2d_pred - bb8_2d_gt
erro = np.abs(erro)
err = np.reshape(erro, (erro.size, ))
#abserr = map(abs,err)
print("reproject sum_error:{} ".format(np.sum(err)))
## 199 reproject sum_error:13.385891544820552
## 399 reproject sum_error:12.718721049803733
##看了是有提高 准召定义 准确下降，召回上升
visualize_bounding_box(image[None, ...], bb8_2d_pred[None, None, ...],
bb8_2d_gt[None, None, ...])
def demo(idx):
data, bb8_3d = read_data(idx)
print("BB8_3D: ",bb8_3d)
image, mask, pose = [d.unsqueeze(0).cuda() for d in data]
projector = Projector()
bb8_2d_gt = projector.project(bb8_3d, pose[0].detach().cpu().numpy(), 'blender')
print(bb8_2d_gt)
image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
visualize_bounding_box(image[None, ...], bb8_2d_gt[None, None, ...])
def inference(input_image, count=0):
c_timer = time.time()
rgb = input_image
if args.input != 'image':
color = cv2.cvtColor(input_image, cv2.COLOR_BGR2RGB)
rgb = color
pre_start = time.time()
print(pre_start - c_timer, "s BGR2RGB")
#rgb = Image.open(input_image)
#print(rgb.shape)
start = time.time()
transformer = transforms.Compose([
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225])
])
rgb = transformer(rgb)
rgb = rgb.unsqueeze(0).cuda()
seg_pred, vertex_pred = net(rgb)
eval_net = DataParallel(EvalWrapper().cuda())
corner_pred = eval_net(seg_pred, vertex_pred).cpu().detach().numpy()[0]
end = time.time()
print(end - start, "s - to go from image to corner prediction")
image = imagenet_to_uint8(rgb.detach().cpu().numpy())[0]
pose_pred = pnp(points_3d, corner_pred, camera_matrix)
projector = Projector()
bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'logitech')
end_ = time.time()
print(end_ - end, "s - to project the corners and show the result")
seg_mask = torch.argmax(seg_pred, 1)
if args.debug:
visualize_mask(seg_mask, count)
pose_test = np.array([[1, 0, 0, 0], [0, 1, 0, 0.3], [0, 0, 1, 1.2]])
print(pose_pred)
#print(pose_test)
bb8_2d_gt = projector.project(bb8_3d, pose_test, 'logitech')
if pose_pred[2][3] < 0.4:
if pose_pred[2][3] > -0.4:
if isinstance(rgb, torch.Tensor):
rgb = rgb.permute(0, 2, 3, 1).detach().cpu().numpy()
rgb = rgb.astype(np.uint8)
_, ax = plt.subplots(1)
ax.imshow(cv2.cvtColor(input_image, cv2.COLOR_BGR2RGB))
#plt.show()
plt.savefig('temp{}.png'.format(count))
plt.close()
print("image was culled due to pose being unreasonable")
else:
visualize_bounding_box(image[None, ...],
bb8_2d_pred[None, None, ...],
save=True,
count=count) #,bb8_2d_gt[None, None, ...])
def visualize_hypothesis(image, seg_pred, vertex_pred, corner_target):
from lib.ransac_voting_gpu_layer.ransac_voting_gpu import generate_hypothesis
vertex_pred = vertex_pred.permute(0, 2, 3, 1)
b, h, w, vn_2 = vertex_pred.shape
vertex_pred = vertex_pred.view(b, h, w, vn_2 // 2, 2)
mask = torch.argmax(seg_pred, 1)
hyp, hyp_counts = generate_hypothesis(mask, vertex_pred, 1024, inlier_thresh=0.99)
image = imagenet_to_uint8(image.detach().cpu().numpy())
hyp = hyp.detach().cpu().numpy()
hyp_counts = hyp_counts.detach().cpu().numpy()
from lib.utils.draw_utils import visualize_hypothesis
visualize_hypothesis(image, hyp, hyp_counts, corner_target)
def visualize_voting_ellipse(image, seg_pred, vertex_pred, corner_target):
from lib.ransac_voting_gpu_layer.ransac_voting_gpu import estimate_voting_distribution_with_mean
vertex_pred = vertex_pred.permute(0, 2, 3, 1)
b, h, w, vn_2 = vertex_pred.shape
vertex_pred = vertex_pred.view(b, h, w, vn_2 // 2, 2)
mask = torch.argmax(seg_pred, 1)
mean = ransac_voting_layer_v3(mask, vertex_pred, 512, inlier_thresh=0.99)
mean, var = estimate_voting_distribution_with_mean(mask, vertex_pred, mean)
image = imagenet_to_uint8(image.detach().cpu().numpy())
mean = mean.detach().cpu().numpy()
var = var.detach().cpu().numpy()
corner_target = corner_target.detach().cpu().numpy()
from lib.utils.draw_utils import visualize_voting_ellipse
visualize_voting_ellipse(image, mean, var, corner_target)
def demo():
net = Resnet18_8s(ver_dim=vote_num * 2, seg_dim=2)
net = NetWrapper(net).cuda()
net = DataParallel(net)
optimizer = optim.Adam(net.parameters(), lr=train_cfg['lr'])
model_dir = os.path.join(cfg.MODEL_DIR, "cat_demo")
load_model(net.module.net, optimizer, model_dir, -1)
data, points_3d, bb8_3d = read_data()
#print("BB8_3D: ",bb8_3d)
image, mask, vertex, vertex_weights, pose, corner_target = [
d.unsqueeze(0).cuda() for d in data
]
seg_pred, vertex_pred, loss_seg, loss_vertex, precision, recall = net(
image, mask, vertex, vertex_weights)
seg_mask = torch.argmax(seg_pred, 1)
print("seg_mask", seg_mask, type(seg_mask), seg_mask.shape, seg_mask[0])
visualize_mask(seg_mask)
visualize_mask(mask)
#visualize_vertex(vertex, vertex_weights)
#visualize_hypothesis(image, seg_pred, vertex_pred, corner_target)
visualize_voting_ellipse(image, seg_pred, vertex_pred, corner_target)
eval_net = DataParallel(EvalWrapper().cuda())
corner_pred = eval_net(seg_pred, vertex_pred).cpu().detach().numpy()[0]
print("Corner Predictions: ", corner_pred)
camera_matrix = np.array([[572.4114, 0., 325.2611],
[0., 573.57043, 242.04899], [0., 0., 1.]])
pose_pred = pnp(points_3d, corner_pred, camera_matrix)
projector = Projector()
bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'linemod')
print("Pose prediction :\n", pose_pred)
print("GT pose: \n", pose[0].detach().cpu().numpy())
bb8_2d_gt = projector.project(bb8_3d, pose[0].detach().cpu().numpy(),
'linemod')
print(bb8_2d_gt)
image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
visualize_bounding_box(image[None, ...], bb8_2d_pred[None, None, ...],
bb8_2d_gt[None, None, ...])
def val(net,
dataloader,
epoch,
val_prefix='val',
use_camera_intrinsic=False,
use_motion=False):
for rec in recs:
rec.reset()
test_begin = time.time()
evaluator = Evaluator()
eval_net = DataParallel(
EvalWrapper().cuda()) if not use_motion else DataParallel(
MotionEvalWrapper().cuda())
uncertain_eval_net = DataParallel(UncertaintyEvalWrapper().cuda())
net.eval()
for idx, data in enumerate(dataloader):
if use_camera_intrinsic:
image, mask, vertex, vertex_weights, pose, corner_target, Ks = [
d.cuda() for d in data
]
else:
image, mask, vertex, vertex_weights, pose, corner_target = [
d.cuda() for d in data
]
with torch.no_grad():
seg_pred, vertex_pred, loss_seg, loss_vertex, precision, recall = net(
image, mask, vertex, vertex_weights)
loss_seg, loss_vertex, precision, recall = [
torch.mean(val)
for val in (loss_seg, loss_vertex, precision, recall)
]
if (train_cfg['eval_epoch']
and epoch % train_cfg['eval_inter'] == 0 and
epoch >= train_cfg['eval_epoch_begin']) or args.test_model:
if args.use_uncertainty_pnp:
mean, cov_inv = uncertain_eval_net(seg_pred, vertex_pred)
mean = mean.cpu().numpy()
cov_inv = cov_inv.cpu().numpy()
else:
corner_pred = eval_net(seg_pred,
vertex_pred).cpu().detach().numpy()
pose = pose.cpu().numpy()
b = pose.shape[0]
pose_preds = []
for bi in range(b):
intri_type = 'use_intrinsic' if use_camera_intrinsic else 'linemod'
K = Ks[bi].cpu().numpy() if use_camera_intrinsic else None
if args.use_uncertainty_pnp:
pose_preds.append(
evaluator.evaluate_uncertainty(mean[bi],
cov_inv[bi],
pose[bi],
args.linemod_cls,
intri_type,
vote_type,
intri_matrix=K))
else:
pose_preds.append(
evaluator.evaluate(corner_pred[bi],
pose[bi],
args.linemod_cls,
intri_type,
vote_type,
intri_matrix=K))
if args.save_inter_result:
mask_pr = torch.argmax(seg_pred, 1).cpu().detach().numpy()
mask_gt = mask.cpu().detach().numpy()
# assume batch size = 1
imsave(
os.path.join(args.save_inter_dir,
'{}_mask_pr.png'.format(idx)), mask_pr[0])
imsave(
os.path.join(args.save_inter_dir,
'{}_mask_gt.png'.format(idx)), mask_gt[0])
imsave(
os.path.join(args.save_inter_dir,
'{}_rgb.png'.format(idx)),
imagenet_to_uint8(image.cpu().detach().numpy()[0]))
save_pickle([pose_preds[0], pose[0]],
os.path.join(args.save_inter_dir,
'{}_pose.pkl'.format(idx)))
vals = [loss_seg, loss_vertex, precision, recall]
for rec, val in zip(recs, vals):
rec.update(val)
with torch.no_grad():
batch_size = image.shape[0]
nrow = 5 if batch_size > 5 else batch_size
recorder.rec_segmentation(F.softmax(seg_pred, dim=1),
num_classes=2,
nrow=nrow,
step=epoch,
name='{}/image/seg'.format(val_prefix))
recorder.rec_vertex(vertex_pred,
vertex_weights,
nrow=4,
step=epoch,
name='{}/image/ver'.format(val_prefix))
losses_batch = OrderedDict()
for name, rec in zip(recs_names, recs):
losses_batch['{}/'.format(val_prefix) + name] = rec.avg
if (train_cfg['eval_epoch'] and epoch % train_cfg['eval_inter'] == 0
and epoch >= train_cfg['eval_epoch_begin']) or args.test_model:
proj_err, add, cm = evaluator.average_precision(False)
losses_batch['{}/scalar/projection_error'.format(
val_prefix)] = proj_err
losses_batch['{}/scalar/add'.format(val_prefix)] = add
losses_batch['{}/scalar/cm'.format(val_prefix)] = cm
recorder.rec_loss_batch(losses_batch, epoch, epoch, val_prefix)
for rec in recs:
rec.reset()
print('epoch {} {} cost {} s'.format(epoch, val_prefix,
time.time() - test_begin))
# camera_matrix = np.array([[572.4114, 0., 325.2611],
# [0., 573.57043, 242.04899],
# [0., 0., 1.]])
# pose_pred = pnp(points_3d, corner_pred, camera_matrix)
# projector = Projector()
# bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'linemod')
# bb8_2d_gt = projector.project(bb8_3d, pose[0].detach().cpu().numpy(), 'linemod')
# image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
# visualize_bounding_box(image[None, ...], bb8_2d_pred[None, None, ...], bb8_2d_gt[None, None, ...])
=======
seg_pred, vertex_pred, loss_seg, loss_vertex, precision, recall = net(image, mask, vertex, vertex_weights)
raise TypeError
eval_net = DataParallel(EvalWrapper().cuda())
corner_pred = eval_net(seg_pred, vertex_pred).cpu().detach().numpy()[0]
camera_matrix = np.array([[572.4114, 0., 325.2611],
[0., 573.57043, 242.04899],
[0., 0., 1.]])
pose_pred = pnp(points_3d, corner_pred, camera_matrix)
projector = Projector()
bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'linemod')
bb8_2d_gt = projector.project(bb8_3d, pose[0].detach().cpu().numpy(), 'linemod')
image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
visualize_bounding_box(image[None, ...], bb8_2d_pred[None, None, ...], bb8_2d_gt[None, None, ...])
>>>>>>> 2c722555563b8a77e36b246d82747754cf8dfae7
if __name__ == "__main__":
demo()
def demo():
net = Resnet18_8s(ver_dim=vote_num * 2, seg_dim=2)
net = NetWrapper(net).cuda()
net = DataParallel(net)
optimizer = optim.Adam(net.parameters(), lr=train_cfg['lr'])
model_dir = os.path.join(cfg.MODEL_DIR, 'cat_demo')
load_model(net.module.net, optimizer, model_dir, args.load_epoch)
data, points_3d, bb8_3d = read_data()
image, mask, vertex, vertex_weights, pose, corner_target = [
d.unsqueeze(0).cuda() for d in data
]
# Run the net
seg_pred, vertex_pred, loss_seg, loss_vertex, precision, recall = net(
image, mask, vertex, vertex_weights)
print('vertex_pred.shape')
print(vertex_pred.shape)
print(' ')
print('vertex_pred[0]')
print(vertex_pred)
print(' ')
# Various visualizations
#visualize_vertex_field(vertex_pred,vertex_weights, keypointIdx=3)
print('asdasdsadas')
print(seg_pred.shape, mask.shape)
visualize_mask(np.squeeze(seg_pred.cpu().detach().numpy()),
mask.cpu().detach().numpy())
rgb = Image.open('data/demo/cat.jpg')
img = np.array(rgb)
#visualize_overlap_mask(img, np.squeeze(seg_pred.cpu().detach().numpy()), None)
# Run the ransac voting
eval_net = DataParallel(EvalWrapper2().cuda())
#corner_pred = eval_net(seg_pred, vertex_pred).cpu().detach().numpy()[0]
corner_pred, covar = [
x.cpu().detach().numpy()[0] for x in eval_net(seg_pred, vertex_pred)
]
print('Keypoint predictions:')
print(corner_pred)
print(' ')
print('covar: ', covar)
print(' ')
camera_matrix = np.array([[572.4114, 0., 325.2611],
[0., 573.57043, 242.04899], [0., 0., 1.]])
# Fit pose to points
#pose_pred = pnp(points_3d, corner_pred, camera_matrix)
#evaluator = Evaluator()
#pose_pred = evaluator.evaluate_uncertainty(corner_pred,covar,pose,'cat',intri_matrix=camera_matrix)
def getWeights(covar):
cov_invs = []
for vi in range(covar.shape[0]): # For every keypoint
if covar[vi, 0, 0] < 1e-6 or np.sum(np.isnan(covar)[vi]) > 0:
cov_invs.append(np.zeros([2, 2]).astype(np.float32))
continue
cov_inv = np.linalg.inv(scipy.linalg.sqrtm(covar[vi]))
cov_invs.append(cov_inv)
cov_invs = np.asarray(cov_invs) # pn,2,2
weights = cov_invs.reshape([-1, 4])
weights = weights[:, (0, 1, 3)]
return weights
weights = getWeights(covar)
pose_pred = uncertainty_pnp(corner_pred, weights, points_3d, camera_matrix)
print('Predicted pose: \n', pose_pred)
print('Ground truth pose: \n', pose[0].detach().cpu().numpy())
print(' ')
projector = Projector()
bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'linemod')
bb8_2d_gt = projector.project(bb8_3d, pose[0].detach().cpu().numpy(),
'linemod')
image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
visualize_points(image[None, ...],
corner_target.detach().cpu().numpy(),
pts_pred=corner_pred[None, :, :])
visualize_bounding_box(image[None, ...], bb8_2d_pred[None, None, ...],
bb8_2d_gt[None, None, ...])
def demo(idx):
net = Resnet18_8s(ver_dim=vote_num * 2, seg_dim=2)
net = NetWrapper(net).cuda()
net = DataParallel(net)
optimizer = optim.Adam(net.parameters(), lr=train_cfg['lr'])
model_dir = os.path.join(cfg.MODEL_DIR, "intake_demo")
load_model(net.module.net, optimizer, model_dir, -1)
data, points_3d, bb8_3d = read_data(idx)
#print("BB8_3D: ",bb8_3d)
image, mask, vertex, vertex_weights, pose, corner_target = [
d.unsqueeze(0).cuda() for d in data
]
seg_pred, vertex_pred, loss_seg, loss_vertex, precision, recall = net(
image, mask, vertex, vertex_weights)
seg_mask = torch.argmax(seg_pred, 1)
visualize_mask(seg_mask)
visualize_mask(mask)
#visualize_vertex(vertex, vertex_weights)
#visualize_hypothesis(image, seg_pred, vertex_pred, corner_target)
#visualize_voting_ellipse(image, seg_pred, vertex_pred, corner_target)
#############
eval_net = DataParallel(EvalWrapper().cuda())
uncertain_eval_net = DataParallel(UncertaintyEvalWrapper().cuda())
corner_pred = eval_net(seg_pred, vertex_pred).cpu().detach().numpy()[0]
net.eval()
loss_seg, loss_vertex, precision, recall = [
torch.mean(val) for val in (loss_seg, loss_vertex, precision, recall)
]
print("LOSS SEG :", loss_seg, "\nLOSS VERTEX : ", loss_vertex,
"\nPRECISION :", precision, '\nRECALL :', recall)
###############
#print("Corner Predictions: ",corner_pred)
camera_matrix = np.array([[700, 0., 320.], [0., 700, 240.], [0., 0., 1.]])
pose_pred = pnp(points_3d, corner_pred, camera_matrix)
projector = Projector()
print("Pose prediction :\n", pose_pred)
pose_gt = pose[0].detach().cpu().numpy()
print("GT Pose :\n", pose[0].detach().cpu().numpy())
s = 0
import math as m
for i in range(3):
if pose_pred[2][3] < 0:
print('NB!')
s += (pose_pred[i][3] - pose_gt[i][3])**2
s = m.sqrt(s)
print("--->",
loss_seg.detach().cpu().numpy(),
loss_vertex.detach().cpu().numpy(),
precision.detach().cpu().numpy(),
recall.detach().cpu().numpy(), s)
bb8_2d_pred = projector.project(bb8_3d, pose_pred, 'blender')
bb8_2d_gt = projector.project(bb8_3d, pose[0].detach().cpu().numpy(),
'blender')
#print(bb8_2d_gt)
image = imagenet_to_uint8(image.detach().cpu().numpy())[0]
visualize_bounding_box(image[None, ...], bb8_2d_pred[None, None, ...],
bb8_2d_gt[None, None, ...])
