# retrained version: PoseNet
last_cpt = tf.train.latest_checkpoint(PATH_TO_POSENET_SNAPSHOTS)
assert last_cpt is not None, "Could not locate snapshot to load. Did you already train the network and set the path accordingly?"
load_weights_from_snapshot(sess,
last_cpt,
discard_list=['Adam', 'global_step', 'beta'])
else:
# load weights used in the paper
net.init(sess,
weight_files=[
'./weights/handsegnet-rhd.pickle',
'./weights/posenet-rhd-stb.pickle'
],
exclude_var_list=['PosePrior', 'ViewpointNet'])
util = EvalUtil()
# iterate dataset
for i in range(dataset.num_samples):
# get prediction
keypoints_scoremap_v,\
scale_crop_v, center_v, kp_uv21_gt, kp_vis = sess.run([keypoints_scoremap, scale_crop, center, data['keypoint_uv21'], data['keypoint_vis21']])
keypoints_scoremap_v = np.squeeze(keypoints_scoremap_v)
kp_uv21_gt = np.squeeze(kp_uv21_gt)
kp_vis = np.squeeze(kp_vis)
# detect keypoints
coord_hw_pred_crop = detect_keypoints(np.squeeze(keypoints_scoremap_v))
coord_hw_pred = trafo_coords(coord_hw_pred_crop, center_v, scale_crop_v,
256)
coord_uv_pred = np.stack([coord_hw_pred[:, 1], coord_hw_pred[:, 0]], 1)
# initialize network weights
if USE_RETRAINED:
# retrained version
last_cpt = tf.train.latest_checkpoint(PATH_TO_SNAPSHOTS)
assert last_cpt is not None, "Could not locate snapshot to load. Did you already train the network and set the path accordingly?"
load_weights_from_snapshot(sess,
last_cpt,
discard_list=['Adam', 'global_step', 'beta'])
else:
# load weights used in the paper
net.init(sess,
weight_files=['./weights/posenet-rhd-stb.pickle'],
exclude_var_list=['PosePrior', 'ViewpointNet'])
util = EvalUtil()
# iterate dataset
for i in range(dataset.num_samples):
# get prediction
crop_scale, keypoints_scoremap_v, kp_uv21_gt, kp_vis = sess.run([
data['crop_scale'], keypoints_scoremap, data['keypoint_uv21'],
data['keypoint_vis21']
])
keypoints_scoremap_v = np.squeeze(keypoints_scoremap_v)
kp_uv21_gt = np.squeeze(kp_uv21_gt)
kp_vis = np.squeeze(kp_vis)
crop_scale = np.squeeze(crop_scale)
# detect keypoints
coord_hw_pred_crop = detect_keypoints(np.squeeze(keypoints_scoremap_v))
# Start TF
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8,
allow_growth=True)
config = tf.ConfigProto(gpu_options=gpu_options)
config.gpu_options.allow_growth = True
sess = tf.Session(config=config)
tf.train.start_queue_runners(sess=sess)
# initialize network with weights used in the paper
net.init(sess,
weight_files=[
'./weights/handsegnet-rhd.pickle',
'./weights/posenet3d-rhd-stb.pickle'
])
util = EvalUtil()
# iterate dataset
for i in range(dataset.num_samples):
# get prediction
import pdb
pdb.set_trace()
keypoint_xyz21, keypoint_vis21, keypoint_scale, coord3d_pred_v = sess.run([
data['keypoint_xyz21'], data['keypoint_vis21'], data['keypoint_scale'],
coord3d_pred
])
keypoint_xyz21 = np.squeeze(keypoint_xyz21)
keypoint_vis21 = np.squeeze(keypoint_vis21)
coord3d_pred_v = np.squeeze(coord3d_pred_v)
keypoint_scale = np.squeeze(keypoint_scale)
# build network
net = CPM(out_chan=22)
# feed through network
scoremap, _ = net.inference(image_crop)[-1]
# Start TF
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.3)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess=sess)
weight_path = './weights/pose_model.npy'
net.init(weight_path, sess)
util = EvalUtil()
# iterate dataset
for i in range(dataset.num_samples):
# get prediction
keypoint_xyz21, keypoint_vis21, keypoint_scale, keypoint_uv21_v, image_crop_v, scoremap_v = \
sess.run([data['keypoint_xyz21'], data['keypoint_vis21'], data['keypoint_scale'], data['keypoint_uv21'], image_crop, scoremap])
keypoint_xyz21 = np.squeeze(keypoint_xyz21)
keypoint_vis21 = np.squeeze(keypoint_vis21)
keypoint_scale = np.squeeze(keypoint_scale)
keypoint_uv21_v = np.squeeze(keypoint_uv21_v)
image_crop_v = np.squeeze((image_crop_v + 0.5) * 256).astype(np.uint8)
scoremap_v = np.squeeze(scoremap_v)
for ik in (1, 5, 9, 13, 17):
scoremap_v[:, :, ik:ik + 4] = scoremap_v[:, :, ik + 3:ik - 1:-1]
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.7)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
tf.train.start_queue_runners(sess=sess)
colorlist_pred = ['#660000', '#b30000', '#ff0000', '#ff4d4d', '#ff9999']
colorlist_gt = ['#000066', '#0000b3', '#0000ff', '#4d4dff', '#9999ff']
# Plots all 5 fingers
def plot_fingers(points, plt_specs, c, ax):
for i in range(5):
start, end = i*4+1, (i+1)*4+1
to_plot = np.concatenate((points[start:end], points[0:1]), axis=0)
ax.plot(to_plot[:,0], to_plot[:,1], to_plot[:,2], plt_specs, color=c[i])
fig = None
util_vae = EvalUtil()
# iterate dataset
for i in range(dataset.num_samples):
# Get required data
keypoint_xyz21, keypoint_vis21, keypoint_scale, img_crop, hand_side = \
sess.run([data['keypoint_xyz21'], data['keypoint_vis21'], data['keypoint_scale'], data['image_crop'], data['hand_side']])
keypoint_xyz21 = np.squeeze(keypoint_xyz21)
keypoint_vis21 = np.squeeze(keypoint_vis21)
keypoint_scale = np.squeeze(keypoint_scale)
img_crop = np.squeeze(img_crop)
# Get VAE prediction
img_res = cv.resize(img_crop, end_size)
img_pyt = img_res.transpose(2, 0, 1).reshape((1, 3, end_size[0], end_size[1]))
img_crop_var = Variable(np2pyt(img_pyt), volatile=True).cuda()
sess.run(tf.global_variables_initializer())
tf.train.start_queue_runners(sess=sess)
# initialize network weights
if USE_RETRAINED:
# retrained version
last_cpt = tf.train.latest_checkpoint(PATH_TO_SNAPSHOTS)
assert last_cpt is not None, "Could not locate snapshot to load. Did you already train the network and set the path accordingly?"
load_weights_from_snapshot(sess, last_cpt, discard_list=['Adam', 'global_step', 'beta'])
print('loading weights from {}'.format(last_cpt))
else:
# load weights used in the paper
net.init('./weights/pose_model.npy', sess)
# net.init_pickle(sess, ['./snapshots_cpm_rotate_s10_wrist_dome/model-100000.pickle'], ['scale'])
util = EvalUtil()
# iterate dataset
results = []
for i in range(dataset.num_samples):
# get prediction
# crop_scale, keypoints_scoremap_v, kp_uv21_gt, kp_vis, image_crop, crop_center, img_dir, hand_side, head_size \
# = sess.run([data['crop_scale'], keypoints_scoremap, data['keypoint_uv21'], data['keypoint_vis21'], data['image_crop'], data['crop_center'], data['img_dir'], data['hand_side'], data['head_size']])
crop_scale, keypoints_scoremap_v, kp_uv21_gt, kp_vis, image_crop, crop_center, img_dir, hand_side \
= sess.run([data['crop_scale'], keypoints_scoremap, data['keypoint_uv21'], data['keypoint_vis21'], data['image_crop'], data['crop_center'], data['img_dir'], data['hand_side']])
keypoints_scoremap_v = np.squeeze(keypoints_scoremap_v)
kp_uv21_gt = np.squeeze(kp_uv21_gt)
kp_vis = np.squeeze(kp_vis)
crop_scale = np.squeeze(crop_scale)
crop_center = np.squeeze(crop_center)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
tf.train.start_queue_runners(sess=sess)
# initialize network with weights used in the paper
if USE_RETRAINED:
# retrained version: HandSegNet
last_cpt = tf.train.latest_checkpoint('./snapshots_lifting_%s_drop/' %
VARIANT)
assert last_cpt is not None, "Could not locate snapshot to load. Did you already train the network?"
load_weights_from_snapshot(sess,
last_cpt,
discard_list=['Adam', 'global_step', 'beta'])
else:
net.init(sess, weight_files=['./weights/lifting-%s.pickle' % VARIANT])
util = EvalUtil()
# iterate dataset
for i in range(dataset.num_samples):
# get prediction
keypoint_xyz21, keypoint_scale, coord3d_pred_v = sess.run([
data['keypoint_xyz21'],
data['keypoint_scale'],
coord3d_pred,
])
keypoint_xyz21 = np.squeeze(keypoint_xyz21)
keypoint_scale = np.squeeze(keypoint_scale)
coord3d_pred_v = np.squeeze(coord3d_pred_v)
# rescale to meters
coord3d_pred_v *= keypoint_scale
]) # left hand (true for all samples provided)
evaluation = tf.placeholder_with_default(True, shape=())
# build network
net = ColorHandPose3DNetwork()
hand_scoremap_tf, image_crop_tf, scale_tf, center_tf, \
keypoints_scoremap_tf, keypoint_coord3d_tf = net.inference_crop(image_tf, hand_side_tf, evaluation)
# Start TF
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
# initialize network
net.init(sess)
# Feed image list through network
eval2d = EvalUtil()
eval3d = EvalUtil()
import tqdm
import cv2
for i in tqdm.tqdm(range(len(data))):
sample = data[i]
image_v = sample['image']
hand_scoremap_v, image_crop_v, scale_v, center_v, \
keypoints_scoremap_v, keypoint_coord3d_v = sess.run([hand_scoremap_tf, image_crop_tf, scale_tf, center_tf,
keypoints_scoremap_tf, keypoint_coord3d_tf],
feed_dict={image_tf: image_v})
hand_scoremap_v = np.squeeze(hand_scoremap_v)
image_crop_v = np.squeeze(image_crop_v)