def _test_RCNN2Labels():
inDir = '/mnt/Ext/data/'
db.connect()
#convert to frames and store in a temp directory
imProd = imc.File2Im()
bgr = imc.RGB2BGR()
#run rcnn on these frames
prms = cfg.set_rcnn_prms(trainDataSet='coco', netName='vgg16-coco-rcnn')
print cfg.get_rcnn_prms(**prms)
rcnn = cc.Im2RCNNDet(prms)
# glue to Jpkg
jpkg = RCNN2Labels()
for session in NSVideoSession.fetch_many(query={'excluded_status': 'MANUAL_STEP_1'}, count=3):
vidName = osp.join(inDir, session.storage_path)
#tmp directory to store the frames
tmpDir = '/tmp/NSBackEnd/alg_output'
hashStr = hashlib.sha256(vidName).hexdigest()
hashDir = osp.join(tmpDir, hashStr)
vid2im = imc.Video2ImNames({'op_dir': hashDir, 'vidName': vidName})
# run chain
chain1 = ch.Chainer([vid2im, imProd, bgr, rcnn])
chain1Out = chain1.produce(vidName)
chain2 = ch.Chainer([jpkg]) # seperate to obtain aggregated output of chain1
allDet = []
while chain1Out:
allDet.append(chain1Out)
chain1Out = chain1.produce(vidName)
chain2Out = chain2.produce(allDet)
# save output to database
session.save_annotations(chain2Out, {}, NSExecutorType.ALGORITHM, 'rcnn_' + cfg.get_rcnn_prms()['trainDataSet'], NSProcessStage.AUTO_STEP_1)
os.system('rm -r ' + tmpDir + '/*')
def _test_mAP_pipeline():
inDir = '/mnt/Ext/data/'
db.connect()
#convert to frames and store in a temp directory
imProd = imc.File2Im()
bgr = imc.RGB2BGR()
#run rcnn on these frames
prms = cfg.set_rcnn_prms(trainDataSet='coco', netName='vgg16-coco-rcnn')
print cfg.get_rcnn_prms(**prms)
rcnn = cc.Im2RCNNDet(prms)
# glue to Jpkg
jlbl = RCNN2Labels()
fmt = MetricList2FormatMetricList()
scoredImDir = []
sessionQuery={'required_status': 'MANUAL_STEP_1|CHECKED'}
for session in NSVideoSession.fetch_many(query=sessionQuery, count=12):
seshCheck = [session] # inside mutable object because no nonlocal keyword in python2
while not seshCheck[0].annotations:
seshCheck[0] = NSVideoSession.fetch_one(query=sessionQuery)
session = seshCheck[0]
vidName = osp.join(inDir, session.storage_path)
#tmp directory to store the frames
tmpDir = '/tmp/NSBackEnd/alg_output'
hashStr = hashlib.sha256(vidName).hexdigest()
hashDir = osp.join(tmpDir, hashStr)
vid2im = imc.Video2ImNames({'op_dir': hashDir, 'vidName': vidName})
# chain 1: vid --> rcnn detections
chain1 = ch.Chainer([vid2im, imProd, bgr, rcnn])
chain1Out = chain1.produce(vidName)
# seperate chains to obtain aggregated output of chain1
# chain2: detections --> mAP format
pred = Labels2MetricList()
chain2 = ch.Chainer([jlbl, pred])
allDet = []
while chain1Out:
allDet.append(chain1Out)
chain1Out = chain1.produce(vidName)
chain2Out = chain2.produce(allDet)
# chain3: annotations to mAP format
act = Labels2MetricList()
chain3 = ch.Chainer([act])
chain3Out = chain3.produce(session.annotations)
# chain4: mAP calc
mapget = mc.Labels2mAP({'object': 'Person', 'occlusion': None})
chain4 = ch.Chainer([fmt, mapget])
chain4Out = chain4.produce([chain3Out, chain2Out])
print 'mAP at {0}:\n{1}'.format(vidName, chain4Out)
scoredImDir.append((hashDir, chain2Out, chain4Out))
viser = vc.VismAP({'outDir': 'successes_failures', 'n': 3})
viser.produce(scoredImDir)
os.system('rm -r ' + tmpDir + '/*')
def _test_Labels2RCNNTrainTxt():
inDir = '/mnt/Ext/data/'
prms = cfg.set_rcnn_prms(trainDataSet='coco', netName='vgg16-coco-rcnn')
print cfg.get_rcnn_prms(**prms)
# rcnn = cc.Im2RCNNDet(prms)
txtProd = Labels2RCNNTrainTxt(prms)
db.connect()
# add count argument if wish not to create text file from all labeled videos
for session in NSVideoSession.fetch_many(query={'required_status': 'MANUAL_STEP_1|CHECKED'}):
print txtProd._convert_one(vidName = osp.join(inDir, session.storage_path),
labels = session.annotations,
height = session.height,
width = session.width)
def __init__(self, prms={}):
# define location for output file and image folder
try:
self.outFile = prms['outFile']
except KeyError:
outFolder = '/mnt/Ext/training_data/rcnn'
dateExt = cuu.get_datetime_ext()
self.outFile = osp.join(outFolder, dateExt, 'rcnn_' + dateExt + '.txt')
os.system('mkdir -p ' + osp.dirname(self.outFile))
prms['outFile'] = self.outFile
try:
self.imageFolder = prms['imageFolder']
except KeyError:
self.imageFolder = osp.join(osp.dirname(self.outFile), 'imageFolder')
os.system('mkdir -p ' + self.imageFolder)
prms['imageFolder'] = self.imageFolder
# define dataset used for pretraining
self.pretrainDataSet = cfg.get_rcnn_prms(**prms)['trainDataSet']
# match available labels with available classes from the pretraining dataset
clsNames = cfg.dataset2classnames(self.pretrainDataSet)
labeledObjs = cfg.get_label_types(category='object')
self.clsLookup = {}
for obj in labeledObjs:
try:
self.clsLookup[obj] = clsNames.index(cfg.label2dataset(obj, dataset=self.pretrainDataSet))
except ValueError as e:
print e
ch.ChainObject.__init__(self, prms)
def __init__(self, prms={}):
prms = edict(cfg.get_rcnn_prms(**prms))
ch.ChainObject.__init__(self, prms)
self.setup_net()
import metric_chains as mc
import config as cfg
from ns_backend import db, NSVideoSession
# setup input/output
inDir = '/mnt/Ext/data/'
outDir = 'output/'
prmsFp = 'input.sweep'
fileDict = yaml.safe_load(open(prmsFp, 'r'))
## Set up chains which only need 1-time setup
#convert to frames and store in a temp directory
imProd = imc.File2Im()
bgr = imc.RGB2BGR()
# set up RCNN
prms = cfg.set_rcnn_prms(**fileDict['input'])
print cfg.get_rcnn_prms(**prms)
rcnn = cc.Im2RCNNDet(prms)
# glue to Jpkg
jlbl = jc.RCNN2Labels()
fmt = jc.MetricList2FormatMetricList()
## Iterate through a sufficiently large sample of videos to make a good estimate
db.connect()
pPred = []
pAct = []
files = []
count = 0
for session in NSVideoSession.fetch_many(query={'required_status': 'MANUAL_STEP_1'}, count=30):
if count == 15:
break
if not session.annotations:
def __init__(self, prms={}):
prms = cfg.get_rcnn_prms(**prms)
ch.ChainObject.__init__(self, prms)
self.setup_net()