def calc_image_stats(pos_db, neg_db, samples=None):
ret = MixedRetriever(Retriever(pos_db), Retriever(neg_db))
if samples is None:
count = ret.get_length()
else:
count = samples
ratio = 1. / 2
sess = tf.Session()
mean = np.zeros((192, 192, 3))
std = np.zeros((192, 192, 3))
k = 1
n = 200
# Calc mean
print("Calculating mean")
for i in xrange(0, ret.get_length(), ret.get_length() // count):
r, l, g = ret.get_random_pairs(sess, n / 2, ratio)
mean = mean * k / (k + n) + (np.sum(r, axis=0) +
np.sum(l, axis=0)) / (k + n)
k += 1
#cv2.imshow("mean", mean)
#cv2.waitKey(0)
k = 1
# Calc std
mean_repeat = np.expand_dims(mean, 0).repeat(n, 0)
print("Calculating standard deviation")
for i in xrange(0, ret.get_length(), ret.get_length() // count):
r, l, g = ret.get_random_pairs(sess, n / 2, ratio)
arr = np.concatenate((r, l), axis=0)
a = (np.sum(np.square(arr - mean_repeat), axis=0)) / (k + n)
std = std * k / (k + n) + a / (k + n)
#cv2.imshow("std", std)
#cv2.waitKey(0)
return mean, std
def main():
TRAIN_DBS, VAL_DBS, TEST_DBS, TRAIN_N_DBS, VAL_N_DBS, TEST_N_DBS = \
load_dbs(sys.argv[1], False)
ret = Retriever(TRAIN_DBS)
sess = tf.Session()
cv2.namedWindow("image", cv2.WINDOW_NORMAL)
cv2.resizeWindow("image", 600, 1200)
l = 1000
div = ret.get_length() / l
pairs = []
for i in range(l):
img1, img2 = ret.get_image_pair(i*div + 1, sess)
#img1, img2 = ret.get_random_pair(sess)
img2 = np.squeeze(img2.astype(np.uint8))
img1 = np.squeeze(img1.astype(np.uint8))
img1 = cv2.cvtColor(img1, cv2.COLOR_BGR2RGB)
#cv2.cvtColor(img1, cv2.COLOR_RGB2BGR)
img2 = cv2.cvtColor(img2, cv2.COLOR_BGR2RGB)
#cv2.cvtColor(img2, cv2.COLOR_RGB2BGR)
#cv2.imwrite("image1.png", img1)
#cv2.imwrite("image2.png", img2)
ss = np.concatenate((img1, img2), axis=1)
cv2.imshow("image", ss)
val = cv2.waitKey(0)
if val == 27:
break
cv2.destroyWindow("image")
sess.close()
def generate_snippet(file_name):
relevant_list = open('cacm.rel', 'r')
query_relevant = {}
for line in relevant_list.readlines():
words = line.split()
if query_relevant.has_key(words[0]):
doc_no = words[2][5:]
doc_no = str(doc_no)
doc = 'CACM-' + (4 - len(doc_no)) * '0' + doc_no
query_relevant[words[0]].append(doc)
else:
query_relevant[words[0]] = []
doc_no = words[2][5:]
doc = 'CACM-' + (4 - len(doc_no)) * '0' + doc_no
query_relevant[words[0]].append(doc)
#Get query_dict from the file cacm.query.txt
f = open('cacm.query.txt', 'r')
soup = BeautifulSoup(f.read(), 'html.parser')
f.close()
rawquery_dict = {}
for i in range(64):
query_no = (soup.find('docno')).text.encode('utf-8')
(soup.find('docno')).decompose()
query = (soup.find('doc')).text.encode('utf-8')
(soup.find('doc')).decompose()
query_no = query_no.strip(" ")
rawquery_dict[query_no] = query
r = Retriever("", "")
query_dict = {}
for query_no, raw_query in rawquery_dict.viewitems():
query_dict[query_no] = r.process_query(raw_query, True)
print "Enter the query no"
no = raw_input()
no = str(no)
query = query_dict[no]
print query
s = SnippetGen(file_name)
query_results = s.get_queryresults(name='bms25')
results = query_results[no]
# pdb.set_trace()
s.get_snippet(query, results)
def __init__(self, car):
self.car = car
self.rules = [
['1', ['signal:RED'], ['acceleration:N']
], # rule base for signal, stop sign and speed limit
['2', ['signal:AMBER'], ['acceleration:N']],
['3', ['signal:GREEN'], ['acceleration:Y']],
['4', ['sign:STOP'], ['acceleration:N']],
['5', ['speed:Y'], ['aceleration:Y']],
['6', ['speed:N'], ['acceleration:N']]
]
self.evtgen = EventGenerator.EventGenerator(
) # creating random event generator object
self.rt = Retriever(
'casebasedplan.txt') # Retriever object for case retrieval
self.exception_event = ExceptionalEvent()
self.laneChanged = False
def load_retrievers(dbtype, viewing=False):
# INIT DATABASE RETRIEVERS
TRAIN_DBS, VAL_DBS, TEST_DBS, TRAIN_N_DBS, VAL_N_DBS, TEST_N_DBS = \
load_dbs(dbtype, viewing)
train_pos = Retriever(TRAIN_DBS)
train_neg = Retriever(TRAIN_N_DBS)
train_ret = MixedRetriever(train_pos, train_neg)
val_pos = Retriever(VAL_DBS)
val_neg = Retriever(VAL_N_DBS)
val_ret = MixedRetriever(val_pos, val_neg)
test_pos = Retriever(TEST_DBS)
test_neg = Retriever(TEST_N_DBS)
test_ret = MixedRetriever(test_pos, test_neg)
return train_ret, val_ret, test_ret
#Get query_dict from the file cacm.query.txt
f = open('cacm.query.txt','r')
soup = BeautifulSoup(f.read(), 'html.parser')
f.close()
rawquery_dict = {}
for i in range(64):
query_no = (soup.find('docno')).text.encode('utf-8')
(soup.find('docno')).decompose()
query = (soup.find('doc')).text.encode('utf-8')
(soup.find('doc')).decompose
query_no = query_no.strip(" ")
rawquery_dict[query_no] = query
r = Retriever("", "")
query_dict = {}
for query_no, raw_query in rawquery_dict.viewitems():
query_dict[query_no] = r.process_query(raw_query, True)
print "Enter the query no"
no = raw_input()
no = str(no)
query = query_dict[no]
print query
s = SnippetGen()
query_results = s.get_queryresults(name = 'bms25')
results = query_results[no]
# pdb.set_trace()
s.get_snippet(query,results)
from Retriever import Retriever
R = Retriever()
# pagerank updates for random names
res = R.fetch_objects(size=1000)
print(res.keys())
n_iterations = 10000
d = 0.7
n = float(len(res.keys()))
for i in range(n_iterations):
# for each name...
for k, v in res.items():
# calculate pagerank...
updated_prob = (1 - d) * 1 / n
# ...by inspecting its parents
for parent_node in v.parents:
# parents with high pageranks but few outbound are best
updated_prob += d * (parent_node.pagerank) / parent_node.n_children
# update node's pagerank
v.update_pagerank(updated_prob)
if i % (n_iterations / 5) == 0:
print("iteration", i)
R.put_objects(res)
