def main():
parser = argparse.ArgumentParser(description='Execute different functions of our system')
parser.add_argument('mode',
choices=[
'window_stats', 'evaluate_metaparams', 'evaluate_jw',
'evaluate_get_pos_windows', 'train_svm',
'extract_sift','extract_assignments','extract_codebook',
'evaluate_jw_grid', 'final_metaparams',
'assemble_dpm_dets','ctfdet','assemble_ctf_dets'
])
parser.add_argument('--test_dataset', choices=['val','test','train'],
default='test', help='dataset to use for testing. the training dataset \
is automatically inferred (val->train and test->trainval).')
parser.add_argument('--first_n', type=int,
help='only take the first N images in the datasets')
parser.add_argument('--bounds', type=str,
help='the start_time and deadline_time for the ImagePolicy and corresponding evaluation. ex: (1,5)')
parser.add_argument('--name', help='name for this run')
parser.add_argument('--priors', default='random', help= \
"list of choice for the policy for selecting the next action. choose from random, oracle,fixed_order, no_smooth, backoff. ex: --priors=random,oracle,no_smooth")
parser.add_argument('--compare_evals', action='store_true',
default=False, help='plot all the priors modes given on same plot'),
parser.add_argument('--detector', choices=['perfect','perfect_with_noise', 'dpm','ctf'],
default='perfect', help='detector type')
parser.add_argument('--force', action='store_true',
default=False, help='force overwrite')
parser.add_argument('--gist', action='store_true',
default=False, help='use GIST as one of the actions')
parser.add_argument('--clear_tmp', action='store_true',
default=False, help='clear the cached windows folder before running'),
parser.add_argument('--feature_type', choices=['sift','dsift'],
default='dsift', help='use this feature type'),
parser.add_argument('--kernel', choices=['chi2','rbf'],
default='chi2', help='kernel to train svm on'),
args = parser.parse_args()
if args.priors:
args.priors = args.priors.split(',')
if args.bounds:
args.bounds = [float(x) for x in re.findall(r'\d+', args.bounds)]
assert(len(args.bounds)==2)
print(args)
# Load the dataset
dataset = Dataset('full_pascal_'+args.test_dataset)
if args.first_n:
dataset.images = dataset.images[:args.first_n]
# Infer train_dataset
if args.test_dataset=='test':
train_dataset = Dataset('full_pascal_trainval')
elif args.test_dataset=='val':
train_dataset = Dataset('full_pascal_train')
else:
print("Impossible, setting train_dataset to dataset")
train_dataset = dataset
# Create window generator
sw = SlidingWindows(dataset,train_dataset)
if args.clear_tmp:
dirname = config.get_sliding_windows_cached_dir(train_dataset.get_name())
shutil.rmtree(dirname)
dirname = config.get_sliding_windows_cached_dir(dataset.get_name())
shutil.rmtree(dirname)
if args.mode=='assemble_dpm_dets':
policy = DatasetPolicy(dataset,train_dataset,sw)
dets = policy.load_ext_detections(dataset,suffix='dpm_may25')
if args.mode=='assemble_ctf_dets':
policy = DatasetPolicy(dataset,train_dataset,sw)
dets = policy.load_ext_detections(dataset,'ctf','ctf_default')
dets = policy.load_ext_detections(dataset,'ctf','ctf_nohal')
dets = policy.load_ext_detections(dataset,'ctf', 'ctf_halfsize')
if args.mode=='evaluate_get_pos_windows':
evaluate_get_pos_windows(train_dataset)
return
if args.mode=='window_stats':
"Compute and plot the statistics of ground truth window parameters."
results = SlidingWindows.get_dataset_window_stats(train_dataset,plot=True)
if args.mode=='ctfdet':
"""Run Pedersoli's detector on the dataset and assemble into one Table."""
run_pedersoli(dataset)
if args.mode=='evaluate_jw':
"""
Evaluate the jumping window approach by producing plots of recall vs.
#windows.
"""
# TODO hack: both sw and jw should subclass something like WindowGenerator
jw = JumpingWindowsDetector(use_scale=True)
sw.jw = jw
#classes = dataset.classes
classes = ['car']
# classes = ['bicycle' ,'car','horse', 'sofa',\
# 'bird', 'chair', 'motorbike', 'train',\
# 'boat', 'cow', 'person', 'tvmonitor',\
# 'bottle','diningtable', 'pottedplant',\
# 'bus','dog' ,'sheep']
for cls_idx in range(comm_rank, len(classes), comm_size):
#for cls in dataset.classes:
cls = classes[cls_idx]
dirname = config.get_jumping_windows_dir(dataset.get_name())
filename = os.path.join(dirname,'%s'%cls)
sw.evaluate_recall(cls, filename, metaparams=None, mode='jw', plot=True)
if args.mode=='evaluate_jw_grid':
"""
Evaluate the jumping window approach by producing plots of recall vs.
#windows.
"""
sw = SlidingWindows(dataset,train_dataset)
jw = JumpingWindowsDetectorGrid()
sw.jw = jw
for cls in dataset.classes:
dirname = config.get_jumping_windows_dir(dataset.get_name())
filename = os.path.join(dirname,'%s'%cls)
if os.path.isfile(config.data_dir + 'JumpingWindows/'+cls):
sw.evaluate_recall(cls, filename, metaparams=None, mode='jw', plot=True)
if args.mode=='train_svm':
randomize = not os.path.exists('/home/tobibaum')
d = Dataset('full_pascal_train')
dtest = Dataset('full_pascal_val')
e = Extractor()
classes = config.pascal_classes
num_words = 3000
iters = 5
feature_type = 'dsift'
codebook_samples = 15
num_pos = 'max'
testsize = 'max'
if args.first_n:
num_pos = args.first_n
testsize = 1.5*num_pos
kernel = args.kernel
if comm_rank == 0:
ut.makedirs(config.data_dir + 'features/' + feature_type + '/times/')
ut.makedirs(config.data_dir + 'features/' + feature_type + '/codebooks/times/')
ut.makedirs(config.data_dir + 'features/' + feature_type + '/svms/train_times/')
for cls_idx in range(comm_rank, len(classes), comm_size):
#for cls in classes:
cls = classes[cls_idx]
codebook = e.get_codebook(d, feature_type)
pos_arr = d.get_pos_windows(cls)
neg_arr = d.get_neg_windows(pos_arr.shape[0], cls, max_overlap=0)
if not num_pos == 'max':
if not randomize:
pos_arr = pos_arr[:num_pos]
neg_arr = pos_arr[:num_pos]
else:
rand = np.random.random_integers(0, pos_arr.shape[0] - 1, size=num_pos)
pos_arr = pos_arr[rand]
rand = np.random.random_integers(0, neg_arr.shape[0] - 1, size=num_pos)
neg_arr = neg_arr[rand]
pos_table = Table(pos_arr, ['x','y','w','h','img_ind'])
neg_table = Table(neg_arr, pos_table.cols)
train_with_hard_negatives(d, dtest, num_words,codebook_samples,codebook,\
cls, pos_table, neg_table,feature_type, \
iterations=iters, kernel=kernel, L=2, \
testsize=testsize,randomize=randomize)
if args.mode=='evaluate_metaparams':
"""
Grid search over metaparams values for get_windows_new, with the AUC of
recall vs. # windows evaluation.
"""
sw.grid_search_over_metaparams()
return
if args.mode=='final_metaparams':
dirname = config.get_sliding_windows_metaparams_dir(train_dataset.get_name())
# currently these are the best auc/complexity params
best_params_for_classes = [
(62,15,12,'importance',0), #aeroplane
(83,15,12,'importance',0), #bicycle
(62,15,12,'importance',0), #bird
(62,15,12,'importance',0), #boat
(125,12,12,'importance',0), #bottle
(83,12,9,'importance',0), #bus
(125,15,9,'importance',0), #car
(125,12,12,'linear',0), #cat
(125,15,9,'importance',0), #chair
(125,9,6,'importance',0), #cow
(125,15,6,'linear',0), #diningtable
(62,15,12,'importance',0), #dog
(83,15,6,'importance',0), #horse
(83,12,6,'importance',0), #motorbike
(83,15,12,'importance',0), #person
(83,15,6,'importance',0), #pottedplant
(83,15,12,'importance',0), #sheep
(83,9,6,'importance',0), #sofa
(62,12,6,'importance',0), #train
(62,12,12,'importance',0), #tvmonitor
(125,9,12,'importance',0) #all
]
# ACTUALLY THEY ARE ALL THE SAME!
cheap_params = (62, 9, 6, 'importance', 0)
for i in range(comm_rank,dataset.num_classes(),comm_size):
cls = dataset.classes[i]
best_params = best_params_for_classes[i]
#samples,num_scales,num_ratios,mode,priority,cls = cheap_params
metaparams = {
'samples_per_500px': samples,
'num_scales': num_scales,
'num_ratios': num_ratios,
'mode': mode,
'priority': 0 }
filename = '%s_%d_%d_%d_%s_%d'%(
cls,
metaparams['samples_per_500px'],
metaparams['num_scales'],
metaparams['num_ratios'],
metaparams['mode'],
metaparams['priority'])
filename = os.path.join(dirname,filename)
tables = sw.evaluate_recall(cls,filename,metaparams,'sw',plot=True,force=False)
metaparams = {
'samples_per_500px': samples,
'num_scales': num_scales,
'num_ratios': num_ratios,
'mode': mode,
'priority': 1 }
filename = '%s_%d_%d_%d_%s_%d'%(
cls,
metaparams['samples_per_500px'],
metaparams['num_scales'],
metaparams['num_ratios'],
metaparams['mode'],
metaparams['priority'])
filename = os.path.join(dirname,filename)
tables = sw.evaluate_recall(cls,filename,metaparams,'sw',plot=True,force=False)
return
if args.mode=='extract_sift':
e=Extractor()
e.extract_all(['sift'], ['full_pascal_trainval','full_pascal_test'], 0, 0)
if args.mode=='extract_assignments':
e=Extractor()
feature_type = 'sift'
for image_set in ['full_pascal_trainval','full_pascal_test']:
d = Dataset(image_set)
codebook = e.get_codebook(d, feature_type)
print 'codebook loaded'
for img_ind in range(comm_rank,len(d.images),comm_size):
img = d.images[img_ind]
#for img in d.images:
e.get_assignments(np.array([0,0,img.size[0],img.size[1]]), feature_type, \
codebook, img)
if args.mode=='extract_codebook':
d = Dataset('full_pascal_trainval')
e = Extractor()
codebook = e.get_codebook(d, args.feature_type)
def get_windows_new(self,
image,
cls,
metaparams=None,
with_time=False,
at_most=200000,
force=False):
"""
Generate windows by using ground truth window stats and metaparams.
metaparams must contain keys 'samples_per_500px', 'num_scales', 'num_ratios', 'mode'
metaparams['mode'] can be 'linear' or 'importance' and refers to the method
of sampling intervals per window parameter.
If with_time=True, return tuple of (windows, time_elapsed).
"""
if not metaparams:
metaparams = {
'samples_per_500px': 83,
'num_scales': 12,
'num_ratios': 6,
'mode': 'importance',
'priority': 0
}
t = time.time()
x_samples = int(image.width / 500. * metaparams['samples_per_500px'])
y_samples = int(image.height / 500. * metaparams['samples_per_500px'])
# check for cached windows and return if found
dirname = config.get_sliding_windows_cached_dir(self.train_name)
filename = '%s_%d_%d_%s_%s_%d_%d_%d.npy' % (
cls, metaparams['samples_per_500px'], metaparams['num_scales'],
metaparams['num_ratios'], metaparams['mode'],
metaparams['priority'], x_samples, y_samples)
filename = os.path.join(dirname, filename)
if os.path.exists(filename) and not force:
windows = np.load(filename)
else:
# fine, we'll figure out the windows again
# load the kde for x_scaled,y_scaled,scale,log_ratio
stats = self.get_stats()
kde = stats['%s_kde' % cls]
x_frac = kde.dataset[0, :]
y_frac = kde.dataset[1, :]
scale = kde.dataset[2, :]
log_ratio = kde.dataset[3, :]
# given the metaparameters, sample points to generate the complete list of
# parameter combinations
if metaparams['mode'] == 'linear':
x_points = np.linspace(x_frac.min(), x_frac.max(), x_samples)
y_points = np.linspace(y_frac.min(), y_frac.max(), y_samples)
scale_points = np.linspace(scale.min(), scale.max(),
metaparams['num_scales'])
ratio_points = np.linspace(log_ratio.min(), log_ratio.max(),
metaparams['num_ratios'])
elif metaparams['mode'] == 'importance':
x_points = ut.importance_sample(
x_frac, x_samples, stats['%s_%s_kde' % (cls, 'x_frac')])
y_points = ut.importance_sample(
y_frac, y_samples, stats['%s_%s_kde' % (cls, 'y_frac')])
scale_points = ut.importance_sample(
scale, metaparams['num_scales'],
stats['%s_%s_kde' % (cls, 'scale')])
ratio_points = ut.importance_sample(
log_ratio, metaparams['num_ratios'],
stats['%s_%s_kde' % (cls, 'log_ratio')])
else:
raise RuntimeError("Invalid mode")
combinations = [
x for x in itertools.product(x_points, y_points, scale_points,
ratio_points)
]
combinations = np.array(combinations).T
# only take the top-scoring detections
if metaparams['priority']:
t22 = time.time()
scores = kde(combinations) # (so slow!)
print("kde took %.3f s" % (time.time() - t22))
sorted_inds = np.argsort(-scores)
max_num = min(at_most, sorted_inds.size)
combinations = combinations[:, sorted_inds[:max_num]]
# convert to x,y,scale,ratio,w,h
scale = combinations[2, :]
# x = x_frac*img_width
x = combinations[0, :] * img_width
# ratio = exp(log_ratio)
ratio = np.exp(combinations[3, :])
# y = y_frac*img_height
y = combinations[1, :] * img_height
# w = scale*min_width
w = scale * SlidingWindows.MIN_WIDTH
# h = w*ratio
h = w * ratio
combinations[0, :] = x
combinations[1, :] = y
combinations[2, :] = w
combinations[3, :] = h
windows = combinations.T
windows = BoundingBox.clipboxes_arr(windows,
(0, 0, img_width, img_height))
np.save(filename, windows
) # does not take more than 0.5 sec even for 10**6 windows
time_elapsed = time.time() - t
print("get_windows_new() got %d windows in %.3fs" %
(windows.shape[0], time_elapsed))
if with_time:
return (windows, time_elapsed)
else:
return windows
def get_windows_new(self, image, cls, metaparams=None, with_time=False, at_most=200000, force=False):
"""
Generate windows by using ground truth window stats and metaparams.
metaparams must contain keys 'samples_per_500px', 'num_scales', 'num_ratios', 'mode'
metaparams['mode'] can be 'linear' or 'importance' and refers to the method
of sampling intervals per window parameter.
If with_time=True, return tuple of (windows, time_elapsed).
"""
if not metaparams:
metaparams = {
'samples_per_500px': 83,
'num_scales': 12,
'num_ratios': 6,
'mode': 'importance',
'priority': 0}
t = time.time()
x_samples = int(image.width/500. * metaparams['samples_per_500px'])
y_samples = int(image.height/500. * metaparams['samples_per_500px'])
# check for cached windows and return if found
dirname = config.get_sliding_windows_cached_dir(self.train_name)
filename = '%s_%d_%d_%s_%s_%d_%d_%d.npy'%(
cls,
metaparams['samples_per_500px'],
metaparams['num_scales'],
metaparams['num_ratios'],
metaparams['mode'],
metaparams['priority'],
x_samples, y_samples)
filename = os.path.join(dirname,filename)
if os.path.exists(filename) and not force:
windows = np.load(filename)
else:
# fine, we'll figure out the windows again
# load the kde for x_scaled,y_scaled,scale,log_ratio
stats = self.get_stats()
kde = stats['%s_kde'%cls]
x_frac = kde.dataset[0,:]
y_frac = kde.dataset[1,:]
scale = kde.dataset[2,:]
log_ratio = kde.dataset[3,:]
# given the metaparameters, sample points to generate the complete list of
# parameter combinations
if metaparams['mode'] == 'linear':
x_points = np.linspace(x_frac.min(),x_frac.max(),x_samples)
y_points = np.linspace(y_frac.min(),y_frac.max(),y_samples)
scale_points = np.linspace(scale.min(),scale.max(),metaparams['num_scales'])
ratio_points = np.linspace(log_ratio.min(),log_ratio.max(),metaparams['num_ratios'])
elif metaparams['mode'] == 'importance':
x_points = ut.importance_sample(x_frac,x_samples,stats['%s_%s_kde'%(cls,'x_frac')])
y_points = ut.importance_sample(y_frac,y_samples,stats['%s_%s_kde'%(cls,'y_frac')])
scale_points = ut.importance_sample(scale,metaparams['num_scales'],stats['%s_%s_kde'%(cls,'scale')])
ratio_points = ut.importance_sample(log_ratio,metaparams['num_ratios'],stats['%s_%s_kde'%(cls,'log_ratio')])
else:
raise RuntimeError("Invalid mode")
combinations = [x for x in itertools.product(x_points,y_points,scale_points,ratio_points)]
combinations = np.array(combinations).T
# only take the top-scoring detections
if metaparams['priority']:
t22=time.time()
scores = kde(combinations) # (so slow!)
print("kde took %.3f s"%(time.time()-t22))
sorted_inds = np.argsort(-scores)
max_num = min(at_most,sorted_inds.size)
combinations = combinations[:,sorted_inds[:max_num]]
# convert to x,y,scale,ratio,w,h
scale = combinations[2,:]
# x = x_frac*img_width
x = combinations[0,:]*img_width
# ratio = exp(log_ratio)
ratio = np.exp(combinations[3,:])
# y = y_frac*img_height
y = combinations[1,:]*img_height
# w = scale*min_width
w = scale*SlidingWindows.MIN_WIDTH
# h = w*ratio
h = w * ratio
combinations[0,:] = x
combinations[1,:] = y
combinations[2,:] = w
combinations[3,:] = h
windows = combinations.T
windows = BoundingBox.clipboxes_arr(windows,(0,0,img_width,img_height))
np.save(filename,windows) # does not take more than 0.5 sec even for 10**6 windows
time_elapsed = time.time()-t
print("get_windows_new() got %d windows in %.3fs"%(windows.shape[0],time_elapsed))
if with_time:
return (windows,time_elapsed)
else:
return windows
