def update_valid(reset=False):
print('[interact] updating valid')
if reset is True:
state.reset()
is_valid[:] = True
if state.scale_min:
is_valid[:] = np.bitwise_and(scale >= state.scale_min, is_valid)
if state.scale_max:
is_valid[:] = np.bitwise_and(scale <= state.scale_max, is_valid)
print(state)
print('%d valid keypoints' % sum(is_valid))
print('kpts scale ' + helpers.printable_mystats(scale[is_valid]))
select_ith_keypoint(fx_ptr[0])
def leave_out(expt_func=None, split_test=False, **kwargs):
'''
do with TF-IDF on the zebra data set.
Let M be the total number of *animals* (not images and not chips) in an experimental data set.
Do a series of leave-M-out (M >= 1) experiments on the TF-IDF scoring,
where the "left out" M are M different zebras,
so that there are no images of these zebras in the images used to form the vocabulary.
The vocabulary is formed from the remaining N-M animals.
Test how well TF-IDF recognition does with these M animals.
Repeat for different subsets of M animals.
import experiments as expt
from experiments import *
'''
# ---
# Testing should have animals I have seen and animals I haven't seen.
# Make sure num descriptors -per- word is about the same as Oxford
# ---
# Notes from Monday:
# 1) Larger training set (see how animals in training do vs animals out of training)
# 2) More detailed analysis of failures
# 3) Aggregate scores across different pictures of the same animal
if not 'expt_func' in vars() or expt_func is None:
expt_func = run_experiment
# Load tables
hs = ld2.HotSpotter(ld2.DEFAULT, load_basic=True)
# Grab names
db_names_info = db_info.get_db_names_info(hs)
nx2_cxs = db_names_info['nx2_cxs']
valid_nxs = db_names_info['valid_nxs']
multiton_nxs = db_names_info['multiton_nxs']
# How to generate samples/splits for names
num_nsplits = 5
nsplit_size = (db_names_info['num_names_with_gt']//num_nsplits)
# How to generate samples/splits for chips
csplit_size = 1 # number of indexed chips per Jth experiment
# Generate name splits
kx2_name_split = far_appart_splits(multiton_nxs, nsplit_size, num_nsplits)
result_map = {}
kx = 0
# run K experiments
all_cxs = np.hstack(nx2_cxs[list(valid_nxs)])
for kx in xrange(num_nsplits):
print('***************')
print('[expt] Leave M=%r names out iteration: %r/%r' % (nsplit_size, kx+1, num_nsplits))
print('***************')
# Get name splits
(test_nxs, train_nxs) = kx2_name_split[kx]
# Lock in TRAIN sample
train_cxs_list = nx2_cxs[list(train_nxs)]
train_samp = np.hstack(train_cxs_list)
# Generate chip splits
test_cxs_list = nx2_cxs[list(test_nxs)]
test_nChip = map(len, test_cxs_list)
print('[expt] testnames #cxs stats: %r' % helpers.printable_mystats(test_nChip))
test_cx_splits = []
if not split_test:
# Chucks version of the test (much simplier and better)
indx_samp = all_cxs
train_samp = train_samp
test_samp = all_cxs
hs.set_samples(test_samp, train_samp, indx_samp)
m_label = '[LNO: %r/%r]' % (kx+1, num_nsplits)
expt_locals = expt_func(hs, pprefix=m_label, **kwargs)
#result_map[kx] = expt_locals['allres']
return locals()
def leave_out(expt_func=None, split_test=False, **kwargs):
'''
do with TF-IDF on the zebra data set.
Let M be the total number of *animals* (not images and not chips) in an experimental data set.
Do a series of leave-M-out (M >= 1) experiments on the TF-IDF scoring,
where the "left out" M are M different zebras,
so that there are no images of these zebras in the images used to form the vocabulary.
The vocabulary is formed from the remaining N-M animals.
Test how well TF-IDF recognition does with these M animals.
Repeat for different subsets of M animals.
import experiments as expt
from experiments import *
'''
# ---
# Testing should have animals I have seen and animals I haven't seen.
# Make sure num descriptors -per- word is about the same as Oxford
# ---
# Notes from Monday:
# 1) Larger training set (see how animals in training do vs animals out of training)
# 2) More detailed analysis of failures
# 3) Aggregate scores across different pictures of the same animal
if not 'expt_func' in vars() or expt_func is None:
expt_func = run_experiment
# Load tables
hs = ld2.HotSpotter(ld2.DEFAULT, load_basic=True)
# Grab names
db_names_info = db_info.get_db_names_info(hs)
nx2_cxs = db_names_info['nx2_cxs']
valid_nxs = db_names_info['valid_nxs']
multiton_nxs = db_names_info['multiton_nxs']
# How to generate samples/splits for names
num_nsplits = 5
nsplit_size = (db_names_info['num_names_with_gt'] // num_nsplits)
# How to generate samples/splits for chips
csplit_size = 1 # number of indexed chips per Jth experiment
# Generate name splits
kx2_name_split = far_appart_splits(multiton_nxs, nsplit_size, num_nsplits)
result_map = {}
kx = 0
# run K experiments
all_cxs = np.hstack(nx2_cxs[list(valid_nxs)])
for kx in xrange(num_nsplits):
print('***************')
print('[expt] Leave M=%r names out iteration: %r/%r' %
(nsplit_size, kx + 1, num_nsplits))
print('***************')
# Get name splits
(test_nxs, train_nxs) = kx2_name_split[kx]
# Lock in TRAIN sample
train_cxs_list = nx2_cxs[list(train_nxs)]
train_samp = np.hstack(train_cxs_list)
# Generate chip splits
test_cxs_list = nx2_cxs[list(test_nxs)]
test_nChip = map(len, test_cxs_list)
print('[expt] testnames #cxs stats: %r' %
helpers.printable_mystats(test_nChip))
test_cx_splits = []
if not split_test:
# Chucks version of the test (much simplier and better)
indx_samp = all_cxs
train_samp = train_samp
test_samp = all_cxs
hs.set_samples(test_samp, train_samp, indx_samp)
m_label = '[LNO: %r/%r]' % (kx + 1, num_nsplits)
expt_locals = expt_func(hs, pprefix=m_label, **kwargs)
#result_map[kx] = expt_locals['allres']
return locals()
