def trainModel(params):
drop_ids = params.drop_id.split(',')
dropIdList = []
for dids in drop_ids:
dropIdList.append(int(dids))
import processdata as poseDataset
'''Loads H3.6m dataset'''
sys.path.insert(0,'CRFProblems/H3.6m')
poseDataset.T = params.sequence_length
poseDataset.delta_shift = params.sequence_length - params.sequence_overlap
poseDataset.num_forecast_examples = 24
poseDataset.copy_state = params.copy_state
poseDataset.full_skeleton = params.full_skeleton
poseDataset.train_for = params.train_for
poseDataset.temporal_features = params.temporal_features
poseDataset.crf_file = './CRFProblems/H3.6m/crf' + params.crf
poseDataset.dataset_prefix = params.dataset_prefix
poseDataset.drop_features = params.drop_features
poseDataset.drop_id = dropIdList
poseDataset.subsample_data = params.subsample_data
poseDataset.runall()
if poseDataset.copy_state:
params.batch_size = poseDataset.minibatch_size
path_to_dump = '../dump/'
[nodeNames,nodeList,nodeFeatureLength,nodeConnections,edgeList,edgeListComplete,edgeFeatures,nodeToEdgeConnections,trX,trY,trX_validation,trY_validation,trX_forecasting,trY_forecasting,trX_forecast_nodeFeatures,adjacency] = graph.readCRFgraph(poseDataset)
print '**** H3.6m Loaded ****'
nodeNames = nodeNames.keys()
new_idx = poseDataset.new_idx
featureRange = poseDataset.nodeFeaturesRanges
if params.use_pretrained == 1:
print 'Loading pre-trained model with iter={0}'.format(params.iter_to_load)
params.checkpoint_path = '/users/btech/siddsax/'
model = loadModel(params.checkpoint_path+'checkpoint.'+str(params.iter_to_load))
print 'DRA model loaded successfully'
else:
params.iter_to_load = 0
model = defineGCN(params, nodeNames, nodeList, edgeList, edgeListComplete, edgeFeatures, nodeFeatureLength, nodeToEdgeConnections, new_idx, featureRange,adjacency)
thefile = open('logger.txt', 'w')
logModel(params, thefile, nodeNames, model, poseDataset)
model.fitModel(trX, trY, snapshot_rate=params.snapshot_rate, path=params.checkpoint_path, pathD=path_to_dump, epochs=params.epochs, batch_size=params.batch_size,
decay_after=params.decay_after, learning_rate=params.initial_lr, learning_rate_decay=params.learning_rate_decay, trX_validation=trX_validation,
trY_validation=trY_validation, trX_forecasting=trX_forecasting, trY_forecasting=trY_forecasting,trX_forecast_nodeFeatures=trX_forecast_nodeFeatures, iter_start=params.iter_to_load,
decay_type=params.decay_type, decay_schedule=params.decay_schedule, decay_rate_schedule=params.decay_rate_schedule,
use_noise=params.use_noise, noise_schedule=params.noise_schedule, noise_rate_schedule=params.noise_rate_schedule,
new_idx=new_idx, featureRange=featureRange, poseDataset=poseDataset, graph=graph, maxiter=params.maxiter, ssh_f=len(params.remoteBase), log=True, num_batches= params.curriculum)
'''Loads H3.6m dataset'''
sys.path.insert(0,'CRFProblems/H3.6m')
import processdata as poseDataset
poseDataset.T = args.sequence_length
poseDataset.delta_shift = args.sequence_length - args.sequence_overlap
poseDataset.num_forecast_examples = 24
poseDataset.copy_state = args.copy_state
poseDataset.full_skeleton = args.full_skeleton
poseDataset.train_for = args.train_for
poseDataset.temporal_features = args.temporal_features
poseDataset.crf_file = './CRFProblems/H3.6m/crf' + args.crf
poseDataset.dataset_prefix = args.dataset_prefix
poseDataset.drop_features = args.drop_features
poseDataset.drop_id = drop_id
poseDataset.subsample_data = args.subsample_data
poseDataset.runall()
if poseDataset.copy_state:
args.batch_size = poseDataset.minibatch_size
print '**** H3.6m Loaded ****'
def saveForecastedMotion(forecast,path,prefix='ground_truth_forecast_N_'):
T = forecast.shape[0]
N = forecast.shape[1]
D = forecast.shape[2]
for j in range(N):
motion = forecast[:,j,:]
f = open('{0}{2}{1}'.format(path,j,prefix),'w')
for i in range(T):
st = ''
for k in range(D):
print 'Loading H3.6m'
sys.path.insert(0, 'CRFProblems/H3.6m')
import processdata as poseDataset
poseDataset.T = 150
poseDataset.delta_shift = 100
poseDataset.num_forecast_examples = 24
poseDataset.motion_prefix = args.motion_prefix
poseDataset.motion_suffix = args.motion_suffix
poseDataset.temporal_features = args.temporal_features
poseDataset.full_skeleton = args.full_skeleton
poseDataset.dataset_prefix = args.dataset_prefix
poseDataset.crf_file = './CRFProblems/H3.6m/crf'
poseDataset.train_for = args.train_for
poseDataset.drop_features = args.drop_features
poseDataset.drop_id = [args.drop_id]
poseDataset.runall()
print '**** H3.6m Loaded ****'
new_idx = poseDataset.new_idx
featureRange = poseDataset.nodeFeaturesRanges
base_dir = '.'
# path = '{0}/{1}/'.format(base_dir,args.checkpoint)
path = '..'
if not os.path.exists(path):
print 'Checkpoint path does not exist. Exiting!!'
sys.exit()
crf_file = './CRFProblems/H3.6m/crf'
def convertToSingleVec(X, new_idx, featureRange):