Mercurial Hosting > traffic-intelligence
changeset 878:8e8ec4ece66e
minor + bug corrected in motion pattern learning
author | Nicolas Saunier <nicolas.saunier@polymtl.ca> |
---|---|
date | Fri, 10 Mar 2017 15:31:26 -0500 |
parents | d1ff6917d082 |
children | f9ea5083588e |
files | python/ml.py python/tests/utils.txt scripts/learn-motion-patterns.py |
diffstat | 3 files changed, 10 insertions(+), 4 deletions(-) [+] |
line wrap: on
line diff
--- a/python/ml.py Wed Mar 08 17:46:28 2017 -0500 +++ b/python/ml.py Fri Mar 10 15:31:26 2017 -0500 @@ -150,6 +150,10 @@ TODO: at each step, optimize the prototype as the most similar in its current cluster (can be done easily if similarities are already computed)''' # sort instances based on length + if len(instances) == 0: + print('no instances to cluster (empty list)') + return None + indices = range(len(instances)) if randomInitialization: indices = np.random.permutation(indices)
--- a/python/tests/utils.txt Wed Mar 08 17:46:28 2017 -0500 +++ b/python/tests/utils.txt Fri Mar 10 15:31:26 2017 -0500 @@ -10,7 +10,7 @@ True >>> computeChi2([],[]) -0.0 +0 >>> computeChi2(range(1,10),range(1,10)) 0.0 >>> computeChi2(range(1,9),range(1,10))
--- a/scripts/learn-motion-patterns.py Wed Mar 08 17:46:28 2017 -0500 +++ b/scripts/learn-motion-patterns.py Fri Mar 10 15:31:26 2017 -0500 @@ -10,7 +10,7 @@ parser = argparse.ArgumentParser(description='The program learns prototypes for the motion patterns') #, epilog = '' #parser.add_argument('--cfg', dest = 'configFilename', help = 'name of the configuration file') parser.add_argument('-d', dest = 'databaseFilename', help = 'name of the Sqlite database file', required = True) -parser.add_argument('-t', dest = 'trajectoryType', help = 'type of trajectories to display', choices = ['objectfeatures', 'feature', 'object'], default = 'objectfeatures') +parser.add_argument('-t', dest = 'trajectoryType', help = 'type of trajectories to learn from', choices = ['objectfeatures', 'feature', 'object'], default = 'objectfeatures') parser.add_argument('--max-nobjectfeatures', dest = 'maxNObjectFeatures', help = 'maximum number of features per object to load', type = int, default = 3) parser.add_argument('-n', dest = 'nTrajectories', help = 'number of the object or feature trajectories to load', type = int, default = None) parser.add_argument('-e', dest = 'epsilon', help = 'distance for the similarity of trajectory points', type = float, required = True) @@ -28,8 +28,10 @@ # TODO add possibility to cluter with velocities trajectoryType = args.trajectoryType +prototypeType = args.trajectoryType if args.trajectoryType == 'objectfeatures': trajectoryType = 'object' + prototypeType = 'feature' #features = storage.loadTrajectoriesFromSqlite(databaseFilename, args.trajectoryType) objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, trajectoryType, withFeatures = (args.trajectoryType == 'objectfeatures'), objectNumbers = args.nTrajectories, timeStep = args.positionSubsamplingRate) @@ -37,7 +39,7 @@ if args.trajectoryType == 'objectfeatures': features = [] for o in objects: - o.getNLongestFeatures(args.maxNObjectFeatures) + features += o.getNLongestFeatures(args.maxNObjectFeatures) objects = features trajectories = [o.getPositions().asArray().T for o in objects] @@ -52,7 +54,7 @@ clusterSizes = ml.computeClusterSizes(labels, prototypeIndices, -1) print(clusterSizes) -storage.savePrototypesToSqlite(args.databaseFilename, [objects[i].getNum() for i in prototypeIndices], args.trajectoryType, [clusterSizes[i] for i in prototypeIndices]) # if saving filenames, add for example [objects[i].dbFilename for i in prototypeIndices] +storage.savePrototypesToSqlite(args.databaseFilename, [objects[i].getNum() for i in prototypeIndices], prototypeType, [clusterSizes[i] for i in prototypeIndices]) # if saving filenames, add for example [objects[i].dbFilename for i in prototypeIndices] if args.saveSimilarities: np.savetxt(utils.removeExtension(args.databaseFilename)+'-prototype-similarities.txt.gz', similarities, '%.4f')