if FLAGS.svm:
logging.info("Performing svm classification")
solver = classifier.SolverMC(
FLAGS.reg, classifier.Loss.loss_hinge, classifier.Reg.reg_l2, fminargs={"maxfun": 1000}
)
w, b = solver.solve(Xtrain, classifier.to_one_of_k_coding(Ytrain, fill=-1))
pred = np.dot(Xtrain, w) + b
accu_train = classifier.Evaluator.accuracy(Ytrain, pred)
pred = np.dot(Xtest, w) + b
accu_test = classifier.Evaluator.accuracy(Ytest, pred)
logging.info("Reg %f, train accu %f, test accu %f" % (FLAGS.reg, accu_train, accu_test))
mpi.root_pickle((w, b, FLAGS.reg, accu_train, accu_test), __file__ + str(FLAGS.reg) + ".svm.pickle")
if gflags.FLAGS.hier:
logging.info("Performing hierarchical classification")
utility = np.exp(birdtax.bird_info_gain())
utility /= utility.sum(axis=1)[:, np.newaxis]
solver = classifier.SolverMC(
FLAGS.reg, classifier.Loss.loss_multiclass_logistic, classifier.Reg.reg_l2, fminargs={"maxfun": 1000}
)
w, b = solver.solve(Xtrain, np.ascontiguousarray(utility[Ytrain.astype(int)]))
pred = np.dot(Xtrain, w) + b
accu_train = classifier.Evaluator.accuracy(Ytrain, pred)
pred = np.dot(Xtest, w) + b
accu_test = classifier.Evaluator.accuracy(Ytest, pred)
logging.info("Reg %f, train accu %f, test accu %f" % (FLAGS.reg, accu_train, accu_test))
mpi.root_pickle((w, b, FLAGS.reg, accu_train, accu_test), __file__ + str(FLAGS.reg) + ".hier.pickle")
if gflags.FLAGS.hierlog:
logging.info("Performing hierarchical classification")
utility = birdtax.bird_info_gain()
classifier.Loss.loss_hinge,
classifier.Reg.reg_l2,
fminargs = {'maxfun': 1000})
w,b = solver.solve(Xtrain, classifier.to_one_of_k_coding(Ytrain, fill=-1))
pred = np.dot(Xtrain, w) + b
accu_train = classifier.Evaluator.accuracy(Ytrain, pred)
pred = np.dot(Xtest, w) + b
accu_test = classifier.Evaluator.accuracy(Ytest, pred)
logging.info("Reg %f, train accu %f, test accu %f" % \
(FLAGS.reg, accu_train, accu_test))
mpi.root_pickle((w, b, FLAGS.reg, accu_train, accu_test),
__file__ + str(FLAGS.reg) + ".svm.pickle")
if gflags.FLAGS.hier:
logging.info("Performing hierarchical classification")
utility = np.exp(birdtax.bird_info_gain())
utility /= utility.sum(axis=1)[:, np.newaxis]
solver = classifier.SolverMC(FLAGS.reg,
classifier.Loss.loss_multiclass_logistic,
classifier.Reg.reg_l2,
fminargs = {'maxfun': 1000})
w,b = solver.solve(Xtrain,
np.ascontiguousarray(utility[Ytrain.astype(int)]))
pred = np.dot(Xtrain, w) + b
accu_train = classifier.Evaluator.accuracy(Ytrain, pred)
pred = np.dot(Xtest, w) + b
accu_test = classifier.Evaluator.accuracy(Ytest, pred)
logging.info("Reg %f, train accu %f, test accu %f" % \
(FLAGS.reg, accu_train, accu_test))
mpi.root_pickle((w, b, FLAGS.reg, accu_train, accu_test),
__file__ + str(FLAGS.reg) + ".hier.pickle")
########
# Settings
########
FEATDIR = "/u/vis/ttmp/jiayq/birds/"
########
# Main script
########
if mpi.SIZE > 1:
raise RuntimeError, "This script runs on single machine only."
Xtest = mpi.load_matrix_multi(os.path.join(FEATDIR,'Xtest'))
Ytest = mpi.load_matrix_multi(os.path.join(FEATDIR,'Ytest')).astype(np.int)
infogain = birdtax.bird_info_gain()
info_mean = infogain.mean(axis=1)
info_max = infogain.max(axis=1)
randguess = sum([info_mean[y] for y in Ytest]) / float(len(Ytest))
bestguess = sum([info_max[y] for y in Ytest]) / float(len(Ytest))
print 'Random guess baseline:', randguess
print 'Best guess baseline:', bestguess
for filename in sys.argv[1:]:
data = pickle.load(open(filename))
w, b = data[:2]
accu_test = data[-1]
pred = np.argmax(np.dot(Xtest, w) + b, axis=1)
