# images to be shown
image_list = list()
image_list.append('./data/1.png')
image_list.append('./data/2.png')
image_list.append('./data/3.png')
image_list.append('./data/4.png')
image_list.append('./data/5.png')
# network input
image_tf = tf.placeholder(tf.float32, shape=(1, 240, 320, 3))
hand_side_tf = tf.constant([[1.0, 0.0]
]) # left hand (true for all samples provided)
evaluation = tf.placeholder_with_default(True, shape=())
# build network
net = PoseEstimationNetwork()
print("Line 48:Let's test!\n")
hand_scoremap_tf, image_crop_tf, scale_crop_tf, center_tf = net.HandSegCrop(
image_tf)
print("Oops,testcrop_line 49==> The formu is :", hand_scoremap_tf.shape)
# 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)
# retrained version: HandSegNet
last_cpt = tf.train.latest_checkpoint(PATH_TO_HANDSEGNET_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,
'max_iter': 30000,
'show_loss_freq': 1000,
'snapshot_freq': 5000,
'snapshot_dir': 'snapshots_posenet'}
# get dataset
dataset = BinaryDbReader(mode='training',
batch_size=8, shuffle=True, use_wrist_coord=False,
hand_crop=True, coord_uv_noise=True, crop_center_noise=True)
# build network graph
data = dataset.get()
# build network
evaluation = tf.placeholder_with_default(True, shape=())
net = PoseEstimationNetwork()
keypoints_scoremap = net.PoseNet(data['image_crop'], train=True)
s = data['scoremap'].get_shape().as_list()
keypoints_scoremap = [tf.image.resize_images(x, (s[1], s[2])) for x in keypoints_scoremap]
# Start TF
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
tf.train.start_queue_runners(sess=sess)
# Loss
loss = 0.0
s = data['scoremap'].get_shape().as_list()
vis = tf.cast(tf.reshape(data['keypoint_vis21'], [s[0], s[3]]), tf.float32)
for i, pred_item in enumerate(keypoints_scoremap):
loss += tf.reduce_sum(vis * tf.sqrt(tf.reduce_mean(tf.square(pred_item - data['scoremap']), [1, 2]))) / (tf.reduce_sum(vis) + 0.001)
'snapshot_dir': 'snapshots_handsegnet'
}
# get dataset
dataset = BinaryDbReader(mode='training',
batch_size=8,
shuffle=True,
hue_aug=True,
random_crop_to_size=True)
# build network graph
data = dataset.get()
# build network
evaluation = tf.placeholder_with_default(True, shape=())
net = PoseEstimationNetwork()
hand_mask_pred = net.HandSegNet(data['image'], train=True)
# Start TF
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
tf.train.start_queue_runners(sess=sess)
# Loss
loss = 0.0
s = data['hand_mask'].get_shape().as_list()
for i, pred_item in enumerate(hand_mask_pred):
gt = tf.reshape(data['hand_mask'], [s[0] * s[1] * s[2], -1])
pred = tf.reshape(hand_mask_pred, [s[0] * s[1] * s[2], -1])
loss += tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(logits=pred, labels=gt))
# flag that allows to load a retrained snapshot(original weights used in the paper are used otherwise)
USE_RETRAINED = True
PATH_TO_SNAPSHOTS = './snapshots_posenet/' # only used when USE_RETRAINED is true
# get dataset
dataset = BinaryDbReader(mode='evaluation',
shuffle=False,
hand_crop=True,
use_wrist_coord=False)
# build network graph
data = dataset.get()
# build network
evaluation = tf.placeholder_with_default(True, shape=())
net = PoseEstimationNetwork()
keypoints_scoremap = net.PoseNet(data['image_crop'])
keypoints_scoremap = keypoints_scoremap[-1]
# upscale to original size
s = data['image_crop'].get_shape().as_list()
keypoints_scoremap = tf.image.resize_images(keypoints_scoremap, (s[1], s[2]))
# Start TF
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
tf.train.start_queue_runners(sess=sess)
# initialize network weights
if USE_RETRAINED:
# retrained version
# images to be shown
image_list = list()
image_list.append('./data/1.png')
image_list.append('./data/2.png')
image_list.append('./data/3.png')
image_list.append('./data/4.png')
image_list.append('./data/5.png')
# network input
image_tf = tf.placeholder(tf.float32, shape=(1, 240, 320, 3))
hand_side_tf = tf.constant([[1.0, 0.0]
]) # left hand (true for all samples provided)
evaluation = tf.placeholder_with_default(True, shape=())
# build network
net = PoseEstimationNetwork()
hand_scoremap_tf = net.HandSegNet(image_tf)
hand_scoremap_tf = hand_scoremap_tf[-1]
# 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)
# retrained version: HandSegNet
last_cpt = tf.train.latest_checkpoint(PATH_TO_HANDSEGNET_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'])
# get dataset
dataset = BinaryDbReader(mode='training',
batch_size=8,
shuffle=True,
hand_crop=True,
use_wrist_coord=False,
coord_uv_noise=True,
crop_center_noise=True,
crop_offset_noise=True,
crop_scale_noise=True)
# build network graph
data = dataset.get()
# build network
net = PoseEstimationNetwork()
# feed trough network
evaluation = tf.placeholder_with_default(True, shape=())
_, coord3d_pred, R = net.Pose3DNet(data['scoremap'], data['hand_side'],
evaluation)
# Start TF
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options))
tf.train.start_queue_runners(sess=sess)
# Loss
loss = 0.0
loss += tf.reduce_mean(tf.square(coord3d_pred - data['keypoint_xyz21_can']))
from data.BinaryDbReaderSTB import *
from nets.network import PoseEstimationNetwork
from utils.general import EvalUtil, get_stb_ref_curves, calc_auc
# get dataset
# dataset = BinaryDbReader(mode='evaluation', shuffle=False, use_wrist_coord=False)
dataset = BinaryDbReaderSTB(mode='evaluation',
shuffle=False,
use_wrist_coord=False)
# build network graph
data = dataset.get()
image_scaled = tf.image.resize_images(data['image'], (240, 320))
# build network
net = PoseEstimationNetwork()
# feed through network
evaluation = tf.placeholder_with_default(True, shape=())
_, _, _, _, _, coord3d_pred = net.Pose3DNet(image_scaled, data['hand_side'],
evaluation)
coord3d_gt = data['keypoint_xyz21']
# Start TF
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.8)
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
net.init(sess,
weight_files=[
# flag that allows to load a retrained snapshot(original weights used in the paper are used otherwise)
USE_RETRAINED = False
PATH_TO_POSENET_SNAPSHOTS = './snapshots_posenet/' # only used when USE_RETRAINED is true
PATH_TO_HANDSEGNET_SNAPSHOTS = './snapshots_handsegnet/' # only used when USE_RETRAINED is true
# get dataset
dataset = BinaryDbReader(mode='evaluation',
shuffle=False,
use_wrist_coord=True,
scale_to_size=True)
# build network graph
data = dataset.get()
# build network
net = PoseEstimationNetwork()
# scale input to common size for evaluation
image_scaled = tf.image.resize_images(data['image'], (240, 320))
s = data['image'].get_shape().as_list()
scale = (240.0 / s[1], 320.0 / s[2])
hand_scoremap, image_crop, scale_crop, center = net.HandSegCrop(image_scaled)
# detect keypoints in 2D
s = image_crop.get_shape().as_list()
keypoints_scoremap = net.PoseNet(image_crop)
keypoints_scoremap = keypoints_scoremap[-1]
keypoints_scoremap = tf.image.resize_images(keypoints_scoremap, (s[1], s[2]))
# Start TF