def ex4(srao_query_string, image_index, gm_method='original', verbose=True):
""" querygen
"""
import image_fetch_core as ifc
import image_fetch_utils as ifu; reload(ifu)
import image_fetch_plot as ifp; reload(ifp)
import image_fetch_querygen as ifq; reload(ifq)
vgd, potentials, platt_mod, bin_mod, queries, ifdata = dp.get_all_data()
query = ifq.gen_srao(srao_query_string)
ifdata.configure(image_index, query)
gm = None
tracker = None
if gm_method == 'original':
gm, tracker = ifc.generate_pgm(ifdata, verbose)
elif gm_method == 'uniform' or gm_method == 'empirical':
gm, tracker = ifc.generate_pgm_all_objects(ifdata, verbose=verbose, method=gm_method)
energy, best_match_ix, marginals = ifc.do_inference(gm)
#ifp.draw_gm(gm)
ifp.draw_best_objects(tracker, best_match_ix, energy, filename = out_path + "mq_i{0}.png".format(image_index))
file_prefix = "mq_i{}_".format(image_index)
ifp.draw_all_heatmaps(tracker, ifdata.object_detections, marginals, gm_method, out_path, file_prefix)
def image_batch(query,
query_id,
if_data,
output_path,
image_ix_subset=[],
gen_plots=True,
gm_method='original'):
""" Run a single query against a batch of images
Attributes:
query (obj): the query to use on the images
query_id (int) : id number of the query
if_data (obj): ImageFetchData object
output_path (str): "/home/econser/School/Thesis/data/inference test/"
image_ix_subset (list): subset of image indices to run in the batch
Returns:
list of energy values from inference
"""
time_list = []
energy_list = []
images = if_data.vg_data
use_subset = False
n_images = len(images)
if len(image_ix_subset) > 0:
use_subset = True
n_images = len(image_ix_subset)
for i in range(0, n_images):
imgnum = i
if use_subset: imgnum = image_ix_subset[i]
gm, tracker, energy, best_matches, marginals, duration = inference_pass(
query, query_id, imgnum, if_data, gm_method)
energy_list.append(energy)
time_list.append(duration)
if gen_plots:
filename = output_path + "q{:03d}".format(
query_id) + "i{:03d}".format(imgnum) + ".png"
ifp.draw_best_objects(tracker, best_matches, energy, filename)
print "total time: {0}, average time: {1}".format(np.sum(time_list),
np.average(time_list))
file = open(output_path + "q{:03d}_energy_values.csv".format(query_id),
"wb")
csv_writer = csv.writer(file)
csv_writer.writerow(("image_ix", "energy"))
for i in range(0, n_images):
imgnum = i
if use_subset: imgnum = image_ix_subset[i]
csv_writer.writerow((imgnum, energy_list[i]))
file.close()
def ex1(query_index,
image_index,
inf_alg='bp',
gm_method='original',
do_suppl_plots=True,
save_gm=False,
verbose=True):
""" generate plots for a query/image pair
"""
import image_fetch_core as ifc
reload(ifc)
import image_fetch_plot as ifp
reload(ifp)
vgd, potentials, platt_mod, bin_mod, queries, ifdata = dp.get_all_data()
query = vgd['vg_data_test'][query_index].annotations
ifdata.configure(image_index, query)
gm = None
tracker = None
if gm_method == 'original':
gm, tracker = ifc.generate_pgm(ifdata, verbose)
elif gm_method == 'uniform' or gm_method == 'empirical':
gm, tracker = ifc.generate_pgm_all_objects(ifdata,
verbose=verbose,
method=gm_method)
file_prefix = "q{0}_i{1}_".format(query_index, image_index)
energy = None
best_match_ix = None
marginals = None
obj_file = None
if inf_alg == 'bp':
obj_file = out_path + file_prefix + gm_method + '_bp_objects.png'
energy, best_match_ix, marginals = ifc.do_inference(gm)
if do_suppl_plots:
ifp.draw_all_heatmaps(tracker, ifdata.object_detections, marginals,
gm_method, out_path, file_prefix)
#ifp.p_compare(tracker, ifdata.object_detections, marginals, out_path+file_prefix+'sctr.png')
elif inf_alg == 'astar':
obj_file = out_path + file_prefix + 'as_objects.png'
energy, best_match_ix = ifc.do_inference_astar(gm)
ifp.draw_best_objects(tracker, best_match_ix, energy, filename=obj_file)
if save_gm: ifp.draw_gm(gm)