outputs = []
for b in range(int(len(model.outputs) / 2)):
outputs.append(
concatenate([model.outputs[2 * b], model.outputs[2 * b + 1]],
name='blk%d' % (b + 1)))
model = Model(model.input, outputs, name=model.name)
logger.debug("DATASETS")
"""Load the MPII dataset."""
mpii = MpiiSinglePerson('datasets/MPII', dataconf=mpii_sp_dataconf)
logger.debug(mpii.dataset_path)
"""Pre-load validation samples and generate the eval. callback."""
mpii_val = BatchLoader(mpii,
x_dictkeys=['frame'],
y_dictkeys=['pose', 'afmat', 'headsize'],
mode=VALID_MODE,
batch_size=mpii.get_length(VALID_MODE),
num_predictions=1,
shuffle=False)
logger.debug(mpii_val.datasets)
printcn(OKBLUE, 'Pre-loading MPII validation data...')
[x_val], [p_val, afmat_val, head_val] = mpii_val[0]
pose_pred = np.zeros_like(p_val)
scores, y_pred = eval_singleperson_pckh(model, x_val, p_val[:, :, 0:2],
afmat_val, head_val)
logger.info("SCORES ")
logger.debug(scores)
pose_pred = get_pred_data(mpii, pose_pred=pose_pred, pred=y_pred, mode=mode)
# poselayout=pa17j3d, topology='frames')f
penn_sf = PennAction(datasetpath('Penn_Action'), pennaction_dataconf,
poselayout=pa17j3d, topology='frames', use_gt_bbox=True)
ntu_sf = Ntu(datasetpath('NTU'), ntu_pe_dataconf, poselayout=pa17j3d,
topology='frames', use_gt_bbox=True)
"""Create an object to load data from all datasets."""
data_tr = BatchLoader([mpii, penn_sf, ntu_sf], ['frame'], ['pose'],
TRAIN_MODE, batch_size=[batch_size_mpii, batch_size_ar,
batch_size_ar], num_predictions=num_predictions, shuffle=True)
"""MPII validation samples."""
mpii_val = BatchLoader(mpii, ['frame'], ['pose', 'afmat', 'headsize'],
VALID_MODE, batch_size=mpii.get_length(VALID_MODE), shuffle=True)
printcn(OKBLUE, 'Pre-loading MPII validation data...')
[x_val], [p_val, afmat_val, head_val] = mpii_val[0]
mpii_callback = MpiiEvalCallback(x_val, p_val, afmat_val, head_val,
map_to_pa16j=pa17j3d.map_to_pa16j, logdir=logdir)
# """Human3.6H validation samples."""
# h36m_val = BatchLoader(h36m, ['frame'],
# ['pose_w', 'pose_uvd', 'afmat', 'camera', 'action'], VALID_MODE,
# batch_size=h36m.get_length(VALID_MODE), shuffle=True)
# printcn(OKBLUE, 'Preloading Human3.6M validation samples...')
# [x_val], [pw_val, puvd_val, afmat_val, scam_val, action] = h36m_val[0]
#
# h36m_callback = H36MEvalCallback(x_val, pw_val, afmat_val,
# puvd_val[:,0,2], scam_val, action, logdir=logdir)
poselayout=pa17j3d,
topology='frames',
use_gt_bbox=True)
"""Create an object to load data from all datasets."""
data_tr = BatchLoader([mpii, h36m, penn_sf, ntu_sf], ['frame'], ['pose'],
TRAIN_MODE,
batch_size=[
batch_size_mpii, batch_size_mpii, batch_size_ar,
batch_size_ar
],
num_predictions=num_predictions,
shuffle=True)
"""MPII validation samples."""
mpii_val = BatchLoader(mpii, ['frame'], ['pose', 'afmat', 'headsize'],
VALID_MODE,
batch_size=mpii.get_length(VALID_MODE),
shuffle=True)
printcn(OKBLUE, 'Pre-loading MPII validation data...')
[x_val], [p_val, afmat_val, head_val] = mpii_val[0]
mpii_callback = MpiiEvalCallback(x_val,
p_val,
afmat_val,
head_val,
map_to_pa16j=pa17j3d.map_to_pa16j,
logdir=logdir)
"""Human3.6H validation samples."""
h36m_val = BatchLoader(h36m, ['frame'],
['pose_w', 'pose_uvd', 'afmat', 'camera', 'action'],
VALID_MODE,
batch_size=h36m.get_length(VALID_MODE),
shuffle=True)
num_joints = 16
model = reception.build(input_shape, num_joints, dim=2,
num_blocks=num_blocks, num_context_per_joint=2, ksize=(5, 5),
concat_pose_confidence=False)
"""Load pre-trained model."""
# weights_path = get_file(weights_file, TF_WEIGHTS_PATH, md5_hash=md5_hash, cache_subdir='models')
model.load_weights(weights_path)
"""Merge pose and visibility as a single output."""
outputs = []
for b in range(int(len(model.outputs) / 2)):
outputs.append(concatenate([model.outputs[2*b], model.outputs[2*b + 1]],
name='blk%d' % (b + 1)))
model = Model(model.input, outputs, name=model.name)
"""Load the MPII dataset."""
mpii = MpiiSinglePerson(f"{dataset_path}datasets/MPII", dataconf=mpii_sp_dataconf)
"""Pre-load validation samples and generate the eval. callback."""
mpii_val = BatchLoader(mpii, x_dictkeys=['frame'],
y_dictkeys=['pose', 'afmat', 'headsize'], mode=VALID_MODE,
batch_size=mpii.get_length(VALID_MODE), num_predictions=1,
shuffle=False)
printcn(OKBLUE, 'Pre-loading MPII validation data...')
[x_val], [p_val, afmat_val, head_val] = mpii_val[0]
eval_singleperson_pckh(model, x_val, p_val[:,:,0:2], afmat_val, head_val)
num_joints = 16
model = reception.build(input_shape, num_joints, dim=2,
num_blocks=num_blocks, num_context_per_joint=2, ksize=(5, 5))
"""Load the MPII dataset."""
mpii = MpiiSinglePerson('datasets/MPII', dataconf=mpii_sp_dataconf)
data_tr = BatchLoader(mpii, ['frame'], ['pose'], TRAIN_MODE,
batch_size=batch_size, num_predictions=num_blocks, shuffle=True)
"""Pre-load validation samples and generate the eval. callback."""
mpii_val = BatchLoader(mpii, x_dictkeys=['frame'],
y_dictkeys=['pose', 'afmat', 'headsize'], mode=VALID_MODE,
batch_size=mpii.get_length(VALID_MODE), num_predictions=1,
shuffle=False)
printcn(OKBLUE, 'Pre-loading MPII validation data...')
[x_val], [p_val, afmat_val, head_val] = mpii_val[0]
eval_callback = MpiiEvalCallback(x_val, p_val, afmat_val, head_val,
eval_model=model, batch_size=2, pred_per_block=1, logdir=logdir)
loss = pose_regression_loss('l1l2bincross', 0.01)
model.compile(loss=loss, optimizer=RMSprop())
model.summary()
def lr_scheduler(epoch, lr):
if epoch in [80, 100]:
newlr = 0.2*lr
printcn(WARNING, 'lr_scheduler: lr %g -> %g @ %d' % (lr, newlr, epoch))
"""Load pre-trained weights from pose estimation and copy replica layers."""
# full_model.load_weights(
# "C:\\networks\\deephar\\output\\ntu_baseline\\0429\\base_ntu_model_weights.hdf5",
# by_name=True)
# full_model.load_weights(
# 'output/ntu_spnet_trial-03_fa9d2e2/weights_3dp+ntu_ar_050.hdf5',
# by_name=True)
# 'output/ntu_spnet_trial-03-ft2_0ae2bf7/weights_3dp+ntu_ar_058.hdf5')
# full_model.load_weights(
# 'output/ntu_spnet_trial_06_nopose_f_512a239/weights_3dp+ntu_ar_020.hdf5',
# by_name=True)
"""Trick to pre-load validation samples and generate the eval. callback."""
mpii_val = BatchLoader(mpii, ['frame'], ['pose', 'afmat', 'headsize'],
VALID_MODE, batch_size=mpii.get_length(VALID_MODE), shuffle=False)
printnl('Pre-loading MPII validation data...')
[mpii_x_val], [mpii_p_val, mpii_afmat_val, mpii_head_val] = mpii_val[0]
"""Human3.6H validation samples."""
# h36m_val = BatchLoader(h36m, ['frame'],
# ['pose_w', 'pose_uvd', 'afmat', 'camera', 'action'], VALID_MODE,
# batch_size=h36m.get_length(VALID_MODE), shuffle=False)
# printcn(OKBLUE, 'Preloading Human3.6M validation samples...')
# [h36m_x_val], [h36m_pw_val, h36m_puvd_val, h36m_afmat_val, h36m_scam_val, \
# h36m_action] = h36m_val[0]
"""NTU subset of testing samples"""
ntu_te = BatchLoader(ntu_s1, ['frame'], ['ntuaction'], TEST_MODE,
batch_size=1, shuffle=False)