def batch_query(em, force_recomp=False, test_cxs=None):
'''Runs each test_cxs as a query. If test_cxs is None, then all queries
are run'''
'TODO: Fix up the VM dependencies'
vm, iom, am, cm = em.hs.get_managers('vm', 'iom', 'am', 'cm')
# Compute the matches
qm = vm.hs.qm
vm.sample_train_set()
vm.build_model(force_recomp=force_recomp)
if test_cxs == None:
test_cxs = vm.get_train_cx()
logmsg('Building matching graph. This may take awhile')
depends = ['chiprep', 'preproc', 'model', 'query']
algo_suffix = am.get_algo_suffix(depends)
samp_suffix = vm.get_samp_suffix()
result_dpath = iom.ensure_directory(iom.get_temp_fpath('raw_results'))
rr_fmtstr_cid = os.path.join(
result_dpath, 'rr_cid%07d' + samp_suffix + algo_suffix + '.pkl')
# Find the Queries which need to be run
unsaved_cxs = []
for cx in iter(test_cxs):
cid = cm.cx2_cid[cx]
rr_fpath = rr_fmtstr_cid % cid
if not os.path.exists(rr_fpath):
unsaved_cxs.append(cx)
# Run Unsaved Query
total = len(unsaved_cxs)
for count, cx in enumerate(unsaved_cxs):
logmsg('Query %d/%d' % (count, total))
em.run_and_save_query(cx, rr_fmtstr_cid)
# Read Each Query
cx2_rr = alloc_lists(test_cxs.max() + 1)
total = len(test_cxs)
for count, cx in enumerate(test_cxs):
logmsg('Loading Result %d/%d' % (count, total))
cid = cm.cx2_cid[cx]
rr_fpath = rr_fmtstr_cid % cid
if not os.path.exists(rr_fpath):
logwarn('Result does not exist for CID=%d' % cid)
rr_file = open(rr_fpath, 'rb')
try:
rr = cPickle.load(rr_file)
except EOFError:
rr_file.close()
os.remove(rr_fpath)
logwarn('Result was corrupted for CID=%d' % cid)
rr_file.close()
rr.cx2_cscore_ = []
rr.cx2_fs_ = []
rr.qfdsc = []
rr.qfpts = []
cx2_rr[cx] = rr
return cx2_rr
def batch_query(em, force_recomp=False, test_cxs=None):
'''Runs each test_cxs as a query. If test_cxs is None, then all queries
are run'''
'TODO: Fix up the VM dependencies'
vm, iom, am, cm = em.hs.get_managers('vm','iom','am', 'cm')
# Compute the matches
qm = vm.hs.qm
vm.sample_train_set()
vm.build_model(force_recomp=force_recomp)
if test_cxs == None:
test_cxs = vm.get_train_cx()
logmsg('Building matching graph. This may take awhile')
depends = ['chiprep','preproc','model','query']
algo_suffix = am.get_algo_suffix(depends)
samp_suffix = vm.get_samp_suffix()
result_dpath = iom.ensure_directory(iom.get_temp_fpath('raw_results'))
rr_fmtstr_cid = os.path.join(result_dpath, 'rr_cid%07d'+samp_suffix+algo_suffix+'.pkl')
# Find the Queries which need to be run
unsaved_cxs = []
for cx in iter(test_cxs):
cid = cm.cx2_cid[cx]
rr_fpath = rr_fmtstr_cid % cid
if not os.path.exists(rr_fpath):
unsaved_cxs.append(cx)
# Run Unsaved Query
total = len(unsaved_cxs)
for count, cx in enumerate(unsaved_cxs):
logmsg('Query %d/%d' % (count, total))
em.run_and_save_query(cx, rr_fmtstr_cid)
# Read Each Query
cx2_rr = alloc_lists(test_cxs.max()+1)
total = len(test_cxs)
for count, cx in enumerate(test_cxs):
logmsg('Loading Result %d/%d' % (count, total))
cid = cm.cx2_cid[cx]
rr_fpath = rr_fmtstr_cid % cid
if not os.path.exists(rr_fpath):
logwarn('Result does not exist for CID=%d' % cid)
rr_file = open(rr_fpath,'rb')
try:
rr = cPickle.load(rr_file)
except EOFError:
rr_file.close()
os.remove(rr_fpath)
logwarn('Result was corrupted for CID=%d' % cid)
rr_file.close()
rr.cx2_cscore_ = []
rr.cx2_fs_ = []
rr.qfdsc = []
rr.qfpts = []
cx2_rr[cx] = rr
return cx2_rr
def delete_model(vm):
logdbg('Deleting Sample Index')
if vm.flann != None:
try:
vm.flann.delete_index()
vm.flann = None
except WindowsError:
logwarn('WARNING: FLANN is not deleting correctly')
vm.reset()
def remove_file(iom, fpath):
if iom.dummy_delete:
logdbg("DummyDelete: %s" % fpath)
return False
logdbg("Deleting: %s" % fpath)
try:
os.remove(fpath)
except OSError as e:
logwarn("OSError: %s,\n Could not delete %s" % (str(e), fpath))
return False
return True
def remove_file(iom, fpath):
if iom.dummy_delete:
logdbg('DummyDelete: %s' % fpath)
return False
logdbg('Deleting: %s' % fpath)
try:
os.remove(fpath)
except OSError as e:
logwarn('OSError: %s,\n Could not delete %s' % (str(e), fpath))
return False
return True
def bilateral_filter(img):
try:
import skimage.filter
img_uint8 = img
img_float = float32(img_uint8) / 255
#mode = Points outside the boundaries of the input are filled according to the given mode (?constant?, ?nearest?, ?reflect? or ?wrap?). Default is ?constant?.
img_bilat = skimage.filter.denoise_bilateral(img_float, win_size=20, sigma_range=1.6, sigma_spatial=1.6, bins=256, mode='reflect', cval='reflect')
return img_bilat
except Exception as ex:
logdbg('Scikits not found: %s' % str(ex))
logwarn('Scikits not found: %s' % str(ex))
return img
def load_result(rr, rr_dpath, rr_suffix):
'Loads the result from the given database'
rr_fpath = rr.rr_fpath(rr_dpath, rr_suffix)
try:
npz = np.load(rr_fpath)
for _key in npz.files:
if _key in ['qcx','qcid','qnid','dbid','qdbid']:
rr.__dict__[_key] = npz[_key].tolist()
else:
rr.__dict__[_key] = npz[_key]
# Numpy saving is werid. gotta cast
except Exception as ex:
os.remove(rr_fpath)
logwarn('Load Result Exception : '+str(ex)+'\nResult was corrupted for CID=%d' % rr.qcid)
def load_features(cm, _cxs=None, force_recomp=False):
if _cxs is None:
cxs = cm.get_valid_cxs()
elif type(_cxs) is types.ListType:
cxs = np.array(_cxs)
elif type(_cxs) in [types.IntType, types.LongType, np.uint32]:
cxs = np.array([_cxs])
else:
cxs = _cxs
count_feat = 0
is_dirty = np.bitwise_or(cm.cx2_dirty_bit[cxs], force_recomp)
num_samp = cxs.size
num_dirty = np.sum(is_dirty)
# HACKS
if not np.iterable(is_dirty):
is_dirty = np.array([is_dirty])
if not np.iterable(cxs):
cxs = np.array([cxs])
load_cx = cxs[is_dirty]
num_clean = num_samp - num_dirty
#logdbg('Loading Features: Dirty=%d ; #Clean=%d' % (num_dirty, num_clean))
if num_dirty == 0:
return
logio('Loading %d Feature Reps' % num_dirty)
am = cm.hs.am
for cx in iter(load_cx):
cid = cm.cx2_cid[cx]
if cid <= 0:
logwarn('WARNING: IX=' + str(cx) + ' is invalid')
continue
chiprep_fpath = cm.hs.iom.get_chiprep_fpath(cid)
# Ensure that the features exists
if force_recomp or not os.path.exists(chiprep_fpath):
logio('Computing and saving features of cid=' + str(cid))
hotspotter.ChipFunctions.precompute_chipreps(
cm.hs, [cx], num_procs=1, force_recompute=force_recomp)
# Load the features
logdbg('Loading features in ' + chiprep_fpath)
npz = np.load(chiprep_fpath)
fpts = npz['arr_0']
fdsc = npz['arr_1']
npz.close()
cm.cx2_fpts[cx] = fpts
cm.cx2_fdsc[cx] = fdsc
cm.cx2_dirty_bit[cx] = False
count_feat += len(fpts)
logdbg('* Loaded ' + str(count_feat) + ' keypoints and fdscriptors')
return True
def _check_altfname(iom, alt_names=None):
'Checks for a legacy data table'
alt_dirs = [iom.get_internal_dpath(),
iom.hs.db_dpath,
join(iom.hs.db_dpath,'data'),
join(iom.hs.db_dpath,'data','..','data','..')]
for adir in iter(alt_dirs):
for aname in iter(alt_names):
alt_fpath = normpath(join(adir,aname))
logdbg('Checking: '+alt_fpath)
if exists(alt_fpath):
logwarn('Using Alternative Datatable '+alt_fpath)
timestamp = str(time.time())
backup_fpath = normpath(alt_fpath+'.'+timestamp+'.bak')
logwarn('Creating Backup: '+backup_fpath)
shutil.copyfile(alt_fpath, backup_fpath)
return alt_fpath
if iom.hs.db_dpath.find(iom.internal_dname) >= 0:
# Disallow Hotspotter directories inside HotSpotter directories
new_db_path = iom.hs.db_dpath[0:iom.hs.db_dpath.find(iom.internal_dname)]
logwarn('Changing this data dir '+iom.hs.db_dpath)
logwarn('To that data dir '+new_db_path)
iom.hs.db_dpath = new_db_path
return 'CSV_Name_not_found'
def _check_altfname(iom, alt_names=None):
"Checks for a legacy data table"
alt_dirs = [
iom.get_internal_dpath(),
iom.hs.db_dpath,
join(iom.hs.db_dpath, "data"),
join(iom.hs.db_dpath, "data", "..", "data", ".."),
]
for adir in iter(alt_dirs):
for aname in iter(alt_names):
alt_fpath = normpath(join(adir, aname))
logdbg("Checking: " + alt_fpath)
if exists(alt_fpath):
logwarn("Using Alternative Datatable " + alt_fpath)
timestamp = str(time.time())
backup_fpath = normpath(alt_fpath + "." + timestamp + ".bak")
logwarn("Creating Backup: " + backup_fpath)
shutil.copyfile(alt_fpath, backup_fpath)
return alt_fpath
if iom.hs.db_dpath.find(iom.internal_dname) >= 0:
# Disallow Hotspotter directories inside HotSpotter directories
new_db_path = iom.hs.db_dpath[0 : iom.hs.db_dpath.find(iom.internal_dname)]
logwarn("Changing this data dir " + iom.hs.db_dpath)
logwarn("To that data dir " + new_db_path)
iom.hs.db_dpath = new_db_path
return "CSV_Name_not_found"
def load_result(rr, rr_dpath, rr_suffix):
'Loads the result from the given database'
rr_fpath = rr.rr_fpath(rr_dpath, rr_suffix)
try:
npz = np.load(rr_fpath)
for _key in npz.files:
if _key in ['qcx', 'qcid', 'qnid', 'dbid', 'qdbid']:
rr.__dict__[_key] = npz[_key].tolist()
else:
rr.__dict__[_key] = npz[_key]
# Numpy saving is werid. gotta cast
except Exception as ex:
os.remove(rr_fpath)
logwarn('Load Result Exception : ' + str(ex) +
'\nResult was corrupted for CID=%d' % rr.qcid)
def load_features(cm, _cxs=None, force_recomp=False):
if _cxs is None:
cxs = cm.get_valid_cxs()
elif type(_cxs) is types.ListType:
cxs = np.array(_cxs)
elif type(_cxs) in [types.IntType, types.LongType, np.uint32]:
cxs = np.array([_cxs])
else:
cxs = _cxs
count_feat = 0
is_dirty = np.bitwise_or(cm.cx2_dirty_bit[cxs], force_recomp)
num_samp = cxs.size
num_dirty = np.sum(is_dirty)
# HACKS
if not np.iterable(is_dirty):
is_dirty = np.array([is_dirty])
if not np.iterable(cxs):
cxs = np.array([cxs])
load_cx = cxs[is_dirty]
num_clean = num_samp - num_dirty
#logdbg('Loading Features: Dirty=%d ; #Clean=%d' % (num_dirty, num_clean))
if num_dirty == 0:
return
logio('Loading %d Feature Reps' % num_dirty)
am = cm.hs.am
for cx in iter(load_cx):
cid = cm.cx2_cid[cx]
if cid <= 0:
logwarn('WARNING: IX='+str(cx)+' is invalid'); continue
chiprep_fpath = cm.hs.iom.get_chiprep_fpath(cid)
# Ensure that the features exists
if force_recomp or not os.path.exists(chiprep_fpath):
logio('Computing and saving features of cid='+str(cid))
hotspotter.ChipFunctions.precompute_chipreps(cm.hs, [cx], num_procs=1, force_recompute=force_recomp)
# Load the features
logdbg('Loading features in '+chiprep_fpath)
npz = np.load(chiprep_fpath)
fpts = npz['arr_0']
fdsc = npz['arr_1']
npz.close()
cm.cx2_fpts[cx] = fpts
cm.cx2_fdsc[cx] = fdsc
cm.cx2_dirty_bit[cx] = False
count_feat += len(fpts)
logdbg('* Loaded '+str(count_feat)+' keypoints and fdscriptors' )
return True
def end_draw(dm):
#gray()
logdbg('Finalizing Draw with '+str(len(dm.ax_list))+' axes')
fig = dm.get_figure()
#fig.subplots_adjust(hspace=0.2, wspace=0.2)
#fig.tight_layout(pad=.3, h_pad=None, w_pad=None)
#fig.tight_layout()
if dm.draw_prefs.in_qtc_bit:
try:
from IPython.back.display import display
display(fig)
except:
logwarn('Cannot Draw in QTConsole')
fig.show()
dm.hs.uim.redraw_gui()
fig.canvas.draw()
def load_tables(iom):
logmsg('Loading data tables in '+iom.hs.db_dpath)
if not (exists(iom.get_image_table_fpath()) and\
exists(iom.get_name_table_fpath()) and\
exists(iom.get_image_table_fpath())):
if exists(iom.get_oxford_gt_dpath()):
logmsg('You have selected an Oxford style groundtruth')
iom.load_oxford_gt()
logmsg('Succesfully Loaded Oxford style groundtruth')
sys.stdout.flush()
return
logwarn('Trying to load a Legacy Database')
iom.load_image_table()
iom.load_name_table()
iom.load_chip_table()
logmsg('Done loading data tables')
sys.stdout.flush()
def adapt_histeq(img):
try:
from skimage import exposure
# input uint8, output uint16
img_uint8 = img
img_uint16 = uint16(img)*2**8
img_adapteq_uint16 = exposure.equalize_adapthist(img_uint16,\
ntiles_x=8,\
ntiles_y=8,\
clip_limit=0.01,\
nbins=256)
img_adapteq_cropped_uint8 = uint8(img_adapteq_uint16[5:-5][5:-5] / uint16(2)**8 )
return img_adapteq_cropped_uint8
except Exception as ex:
logdbg('Scikits not found: %s' % str(ex))
logwarn('Scikits not found: %s' % str(ex))
return img
def end_draw(dm):
# gray()
logdbg("Finalizing Draw with " + str(len(dm.ax_list)) + " axes")
fig = dm.get_figure()
# fig.subplots_adjust(hspace=0.2, wspace=0.2)
# fig.tight_layout(pad=.3, h_pad=None, w_pad=None)
# fig.tight_layout()
if dm.draw_prefs.in_qtc_bit:
try:
from IPython.back.display import display
display(fig)
except:
logwarn("Cannot Draw in QTConsole")
fig.show()
dm.hs.uim.redraw_gui()
fig.canvas.draw()
def is_valid_db_dpath(hs, db_dpath):
'Checks to see if database conforms to expected conventions'
if not os.path.exists(db_dpath):
logwarn('db_dpath \"'+str(db_dpath)+'\" doesnt exist')
return False
db_dpath_files = os.listdir(db_dpath)
if hs.iom.internal_dname in db_dpath_files:
logmsg('Opening a HotSpotter database: '+db_dpath)
elif 'images' in db_dpath_files or\
'data' in db_dpath_files:
logmsg('Opening a StripSpotter database: '+db_dpath)
elif len(db_dpath_files) == 0:
logmsg('Creating a new database: '+db_dpath)
else:
logwarn('Unknown database type: '+db_dpath)
logdbg('Files in dir: '+str(db_dpath_files))
return False
return True
def bilateral_filter(img):
try:
import skimage.filter
img_uint8 = img
img_float = float32(img_uint8) / 255
#mode = Points outside the boundaries of the input are filled according to the given mode (?constant?, ?nearest?, ?reflect? or ?wrap?). Default is ?constant?.
img_bilat = skimage.filter.denoise_bilateral(img_float,
win_size=20,
sigma_range=1.6,
sigma_spatial=1.6,
bins=256,
mode='reflect',
cval='reflect')
return img_bilat
except Exception as ex:
logdbg('Scikits not found: %s' % str(ex))
logwarn('Scikits not found: %s' % str(ex))
return img
def adapt_histeq(img):
try:
from skimage import exposure
# input uint8, output uint16
img_uint8 = img
img_uint16 = uint16(img) * 2**8
img_adapteq_uint16 = exposure.equalize_adapthist(img_uint16,\
ntiles_x=8,\
ntiles_y=8,\
clip_limit=0.01,\
nbins=256)
img_adapteq_cropped_uint8 = uint8(img_adapteq_uint16[5:-5][5:-5] /
uint16(2)**8)
return img_adapteq_cropped_uint8
except Exception as ex:
logdbg('Scikits not found: %s' % str(ex))
logwarn('Scikits not found: %s' % str(ex))
return img
def _scaled_size(cm, cx, dtype=float, rotated=False):
'''Returns the ChipSpace size of cx. Without considering rotation
Depends on the current algorithm settings
dtype specifies the percision of return type'''
# Compute Unrotated Chip Space
# Get raw size and target sizze
(_, _, rw, rh) = cm.cx2_roi[cx]
target_diag_pxls = cm.hs.am.algo_prefs.preproc.sqrt_num_pxls
# HACK: Double the size like Lowe; instead of normalizing
if target_diag_pxls == -1:
current_num_diag_pxls = np.sqrt(rw**2 + rh**2)
target_diag_pxls = current_num_diag_pxls * 2 # max(, 5000)
ar = np.float(rw) / np.float(rh) # aspect ratio
if ar > 4 or ar < .25:
logwarn('Aspect ratio for cx=%d %.2f may be too extreme' %
(cx, ar))
# Compute Unoriented scaled chip's width and height
ucw = np.sqrt(ar**2 * target_diag_pxls**2 / (ar**2 + 1))
uch = ucw / ar
# Rotate Unrotated Chip Space into Rotated Chip Space
if rotated:
theta = cm.cx2_theta[cx]
rot = np.array(([np.cos(theta), -np.sin(theta)
], [np.sin(theta), np.cos(theta)]),
dtype=np.float)
# Extend of Unrotated Chip Space. Center shifted to the origin
pts_00 = np.array([(0, 0), (ucw, 0), (ucw, uch),
(0, uch)]) - np.array((ucw, uch)) / 2
rot_pts = pts_00.dot(rot)
xymin = rot_pts.min(0)
xymax = rot_pts.max(0)
# Floating point Rotated Chip w/h
cw, ch = xymax - xymin
else:
# Floating point Unrotated Chip w/h
cw, ch = ucw, uch
# Convert to the specified dtype at the end
if dtype is np.float:
return cw, ch
elif np.dtype(dtype).kind == 'f':
return dtype(cw), dtype(ch)
else:
return dtype(round(cw)), dtype(round(ch))
def load_tables(iom):
logmsg("Loading data tables in " + iom.hs.db_dpath)
if not (
exists(iom.get_image_table_fpath())
and exists(iom.get_name_table_fpath())
and exists(iom.get_image_table_fpath())
):
if exists(iom.get_oxford_gt_dpath()):
logmsg("You have selected an Oxford style groundtruth")
iom.load_oxford_gt()
logmsg("Succesfully Loaded Oxford style groundtruth")
sys.stdout.flush()
return
logwarn("Trying to load a Legacy Database")
iom.load_image_table()
iom.load_name_table()
iom.load_chip_table()
logmsg("Done loading data tables")
sys.stdout.flush()
def smartget_db_dpath(hs, db_dpath):
''' Performs a smart update of the db_dpath
Trys a number of various options to get it right
None = Read from preferences
'' = Prompt the User For database
'''
if db_dpath is None: # If requested to read prefs
db_dpath = str(hs.core_prefs.database_dpath)
if db_dpath in [None, 'None'] or\
not os.path.exists(db_dpath): # Check validity
logwarn('db_dpath='+repr(db_dpath)+' is invalid')
db_dpath = ''
if db_dpath == '': # Prompt The User. TODO Move this to Facade/UIManager
logmsg('what database should I open?')
try:
db_dpath = hs.uim.select_database()
except:
logerr(' Was unable to prompt user with QT')
return db_dpath
def _scaled_size(cm, cx, dtype=float, rotated=False):
'''Returns the ChipSpace size of cx. Without considering rotation
Depends on the current algorithm settings
dtype specifies the percision of return type'''
# Compute Unrotated Chip Space
# Get raw size and target sizze
(_, _, rw, rh) = cm.cx2_roi[cx]
target_diag_pxls = cm.hs.am.algo_prefs.preproc.sqrt_num_pxls
# HACK: Double the size like Lowe; instead of normalizing
if target_diag_pxls == -1:
current_num_diag_pxls = np.sqrt(rw**2 + rh**2)
target_diag_pxls = current_num_diag_pxls*2 # max(, 5000)
ar = np.float(rw)/np.float(rh) # aspect ratio
if ar > 4 or ar < .25:
logwarn( 'Aspect ratio for cx=%d %.2f may be too extreme' % (cx, ar))
# Compute Unoriented scaled chip's width and height
ucw = np.sqrt(ar**2 * target_diag_pxls**2 / (ar**2 + 1))
uch = ucw / ar
# Rotate Unrotated Chip Space into Rotated Chip Space
if rotated:
theta = cm.cx2_theta[cx]
rot = np.array(([np.cos(theta), -np.sin(theta)], [np.sin(theta), np.cos(theta)]), dtype=np.float)
# Extend of Unrotated Chip Space. Center shifted to the origin
pts_00 = np.array([(0,0), (ucw,0), (ucw,uch), (0, uch)]) - np.array((ucw, uch))/2
rot_pts = pts_00.dot(rot)
xymin = rot_pts.min(0)
xymax = rot_pts.max(0)
# Floating point Rotated Chip w/h
cw, ch = xymax - xymin
else:
# Floating point Unrotated Chip w/h
cw, ch = ucw, uch
# Convert to the specified dtype at the end
if dtype is np.float:
return cw, ch
elif np.dtype(dtype).kind == 'f':
return dtype(cw), dtype(ch)
else:
return dtype(round(cw)), dtype(round(ch))
def external_feature_computers(am, chip):
'Write chip ; call extern executable ; read output ; return (kpts,desc)'
logdbg('Calling external kpt detector')
iom = am.hs.iom
chip = Image.fromarray(chip)
tmp_chip_fpath = iom.get_temp_fpath('tmp.ppm')
chip.save(tmp_chip_fpath, 'PPM')
perdoch_external = ['heshesaff']
mikolajczyk_external = ['heslapaff', 'dense']
if am.algo_prefs.chiprep.kpts_detector in perdoch_external:
exename = iom.get_hesaff_exec()
outname = tmp_chip_fpath + '.hesaff.sift'
args = '"' + tmp_chip_fpath + '"'
elif am.algo_prefs.chiprep.kpts_detector in mikolajczyk_external:
exename = iom.get_inria_exec()
feature_name = am.algo_prefs.chiprep.kpts_detector
if feature_name == 'heslapaff':
feature_name = 'hesaff'
suffix = 'hesaff'
if feature_name == 'dense':
feature_name = feature_name + ' 6 6'
suffix = 'dense'
outname = tmp_chip_fpath + '.' + suffix + '.sift'
args = '-' + feature_name + ' -sift -i "' + tmp_chip_fpath + '"'
else:
logerr('Method %r + %r is invalid in extern_detect_kpts.m'\
% (am.algo_prefs.chiprep.kpts_detector, am.algo_prefs.chiprep.kpts_extractor))
cmd = exename + ' ' + args
logdbg('External Executing: %r ' % cmd)
try:
proc = subprocess.Popen(cmd,
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.PIPE)
logdbg('External Execution did not throw an error')
(out, err) = proc.communicate()
logdbg(str(out) + ' ' + str(err))
if proc.returncode != 0:
logerr('Failed to execute ' + cmd + '\n OUTPUT: ' + out)
if not os.path.exists(outname):
logerr('The output file doesnt exist: ' + outname)
logdbg('External Output:\n' + out[:-1])
except Exception as ex:
logwarn(
'An Exception occurred while calling the keypoint detector: ' +
str(ex))
try:
ret2 = os.system(cmd)
if ret2 != 0:
logerr(
str(ex) +
'\nThe backup keypoint detector didnt work either!')
except Exception as ex2:
logerr(str(ex2))
fid = file(outname, 'r')
ndims = int(fid.readline())
nkpts = int(fid.readline())
if ndims != 128:
raise Exception(' These are not SIFT dexcriptors ')
kpts = np.zeros((nkpts, 5), dtype=np.float32)
desc = np.zeros((nkpts, ndims), dtype=np.uint8)
lines = fid.readlines()
# SIFT descriptors are computed with a radius of r=3*np.sqrt(3*s)
# s = (det A_i) ^ (-1/2) OR
# s = sqrtm(inv(det(A_i)))
for i in range(nkpts):
nums = lines[i].split(' ')
kpts[i, :] = np.array(map(lambda _: float(_), nums[0:5]),
dtype=np.float32)
desc[i, :] = np.array(map(lambda _: np.uint8(_), nums[5:]),
dtype=np.uint8)
fid.close()
return (kpts, desc)
'''
def external_feature_computers(am, chip):
'Write chip ; call extern executable ; read output ; return (kpts,desc)'
logdbg('Calling external kpt detector')
iom = am.hs.iom
chip = Image.fromarray(chip)
tmp_chip_fpath = iom.get_temp_fpath('tmp.ppm')
chip.save(tmp_chip_fpath,'PPM')
perdoch_external = ['heshesaff']
mikolajczyk_external = ['heslapaff','dense']
if am.algo_prefs.chiprep.kpts_detector in perdoch_external:
exename = iom.get_hesaff_exec()
outname = tmp_chip_fpath+'.hesaff.sift'
args = '"'+tmp_chip_fpath+'"'
elif am.algo_prefs.chiprep.kpts_detector in mikolajczyk_external:
exename = iom.get_inria_exec()
feature_name = am.algo_prefs.chiprep.kpts_detector
if feature_name == 'heslapaff':
feature_name = 'hesaff'
suffix = 'hesaff'
if feature_name == 'dense':
feature_name = feature_name+' 6 6'
suffix = 'dense'
outname = tmp_chip_fpath+'.'+suffix+'.sift'
args = '-'+feature_name+' -sift -i "'+tmp_chip_fpath+'"'
else:
logerr('Method %r + %r is invalid in extern_detect_kpts.m'\
% (am.algo_prefs.chiprep.kpts_detector, am.algo_prefs.chiprep.kpts_extractor))
cmd = exename+' '+args
logdbg('External Executing: %r ' % cmd)
try:
proc = subprocess.Popen(cmd, shell=True, stdout=subprocess.PIPE, stderr=subprocess.PIPE)
logdbg('External Execution did not throw an error')
(out, err) = proc.communicate()
logdbg(str(out)+' '+str(err))
if proc.returncode != 0:
logerr('Failed to execute '+cmd+'\n OUTPUT: '+out)
if not os.path.exists(outname):
logerr('The output file doesnt exist: '+outname)
logdbg('External Output:\n'+out[:-1])
except Exception as ex:
logwarn('An Exception occurred while calling the keypoint detector: '+str(ex))
try:
ret2 = os.system(cmd)
if ret2 != 0:
logerr(str(ex)+'\nThe backup keypoint detector didnt work either!')
except Exception as ex2:
logerr(str(ex2))
fid = file(outname,'r')
ndims = int(fid.readline())
nkpts = int(fid.readline())
if ndims != 128:
raise Exception(' These are not SIFT dexcriptors ')
kpts = np.zeros((nkpts,5), dtype=np.float32)
desc = np.zeros((nkpts,ndims),dtype=np.uint8)
lines = fid.readlines()
# SIFT descriptors are computed with a radius of r=3*np.sqrt(3*s)
# s = (det A_i) ^ (-1/2) OR
# s = sqrtm(inv(det(A_i)))
for i in range(nkpts):
nums = lines[i].split(' ')
kpts[i,:] = np.array(map(lambda _: float(_) , nums[0:5]),dtype=np.float32)
desc[i,:] = np.array(map(lambda _: np.uint8(_), nums[5:]),dtype=np.uint8)
fid.close()
return (kpts, desc)
'''
def load_csv_line(cm, csv_data, csv_headers):
if csv_headers is None:
csv_headers = cm.default_fields
num_unspecified = len(csv_headers) - len(csv_data)
if num_unspecified != 0:
csv_data += ['' for _ in xrange(num_unspecified)]
unspecified_type = ['data', 'headers'][num_unspecified > 0]
logwarn(('\n\nIn chip_file: %d unspecified %s\n'+\
'csv_headers=%r\n'+\
'csv_data=%r\n\n')\
% (abs(num_unspecified), unspecified_type, csv_headers, csv_data))
# Build field name -> field value map
dmap = {k: v for (k, v) in zip(csv_headers, csv_data)}
if cm.hs.core_prefs.legacy_bit:
# Legacy: Be Backwards Compatible
if 'imgindex' in dmap.keys():
logwarn('Found imgindex')
imgindex = int(dmap['imgindex'])
gname = 'img-%07d.jpg' % imgindex
cm.hs.gm.add_img(int(imgindex), gname, False)
dmap['gid'] = imgindex
dmap['cid'] = imgindex
del dmap['imgindex']
if 'animal_name' in dmap.keys():
logwarn('Found animal_name')
dmap['nid'] = cm.hs.nm.add_name(-1, dmap['animal_name'])
del dmap['animal_name']
if 'instance_id' in dmap.keys():
dmap['cid'] = dmap['instance_id']
del dmap['instance_id']
if 'image_id' in dmap.keys():
dmap['gid'] = dmap['image_id']
del dmap['image_id']
if 'name_id' in dmap.keys():
dmap['nid'] = dmap['name_id']
del dmap['name_id']
# Read IDs
cid = int(dmap['cid'])
del dmap['cid']
gid = int(dmap['gid'])
del dmap['gid']
nid = int(dmap['nid'])
del dmap['nid']
# Read Theta
try:
theta = np.float32(dmap['theta'])
del dmap['theta']
except KeyError as ex:
theta = 0
# Read ROI
roi_str = re.sub(' *', ' ', dmap['roi'].replace(']', '').replace(
'[', '')).strip(' ').rstrip()
roi = map(lambda x: int(round(float(x))), roi_str.split(' '))
del dmap['roi']
# Read User Props, whatever is left in dmap
props = dmap
nx = cm.hs.nm.nid2_nx[nid]
gx = cm.hs.gm.gid2_gx[gid]
if gx == 0 or nx == 0 or gid == 0 or nid == 0:
err_msg = 'Adding Chip: (cid=%d),(nid=%d,nx=%d),(gid=%d,gx=%d)' % (
cid, nid, nx, gid, gx)
err_msg += '\nChip has invalid indexes. (Maybe you deleted an image from the images directory?) '
logwarn(err_msg)
cm.add_chip(cid, nx, gx, roi, theta, props=props, delete_prev=False)
def load_csv_line(cm, csv_data, csv_headers):
if csv_headers is None:
csv_headers = cm.default_fields
num_unspecified = len(csv_headers) - len(csv_data)
if num_unspecified != 0:
csv_data += ['' for _ in xrange(num_unspecified)]
unspecified_type = ['data','headers'][num_unspecified > 0]
logwarn(('\n\nIn chip_file: %d unspecified %s\n'+\
'csv_headers=%r\n'+\
'csv_data=%r\n\n')\
% (abs(num_unspecified), unspecified_type, csv_headers, csv_data))
# Build field name -> field value map
dmap = {k:v for (k,v) in zip(csv_headers,csv_data)}
if cm.hs.core_prefs.legacy_bit:
# Legacy: Be Backwards Compatible
if 'imgindex' in dmap.keys():
logwarn('Found imgindex')
imgindex = int(dmap['imgindex'])
gname = 'img-%07d.jpg' % imgindex
cm.hs.gm.add_img(int(imgindex), gname, False)
dmap['gid'] = imgindex
dmap['cid'] = imgindex
del dmap['imgindex']
if 'animal_name' in dmap.keys():
logwarn('Found animal_name')
dmap['nid'] = cm.hs.nm.add_name(-1, dmap['animal_name'])
del dmap['animal_name']
if 'instance_id' in dmap.keys():
dmap['cid'] = dmap['instance_id']
del dmap['instance_id']
if 'image_id' in dmap.keys():
dmap['gid'] = dmap['image_id']
del dmap['image_id']
if 'name_id' in dmap.keys():
dmap['nid'] = dmap['name_id']
del dmap['name_id']
# Read IDs
cid = int(dmap['cid']); del dmap['cid']
gid = int(dmap['gid']); del dmap['gid']
nid = int(dmap['nid']); del dmap['nid']
# Read Theta
try:
theta = np.float32(dmap['theta'])
del dmap['theta']
except KeyError as ex:
theta = 0
# Read ROI
roi_str = re.sub(' *',' ', dmap['roi'].replace(']','').replace('[','')).strip(' ').rstrip()
roi = map(lambda x: int(round(float(x))),roi_str.split(' '))
del dmap['roi']
# Read User Props, whatever is left in dmap
props = dmap
nx = cm.hs.nm.nid2_nx[nid]
gx = cm.hs.gm.gid2_gx[gid]
if gx == 0 or nx == 0 or gid == 0 or nid == 0:
err_msg = 'Adding Chip: (cid=%d),(nid=%d,nx=%d),(gid=%d,gx=%d)' % (cid, nid, nx, gid, gx)
err_msg += '\nChip has invalid indexes. (Maybe you deleted an image from the images directory?) '
logwarn(err_msg)
cm.add_chip(cid, nx, gx, roi, theta, props=props, delete_prev=False)
