def is_device_home(url, device):
n = len(device)
_, _, host, path = url.split('/', 3)
addr = socket.getaddrinfo(host, 80)[0][-1]
s = socket.socket()
s.connect(addr)
s.send(bytes('GET /%s HTTP/1.0\r\nHost: %s\r\n\r\n' % (path, host), 'utf8'))
result = False
pairwise = Pairwise()
# return HTTP request to the url text in bytes
while True:
data = s.recv(n)
if not data:
break
pairwise.add_next(data)
if pairwise.contains(device):
result = True
break
s.close()
return result
def setup(self):
nn = self.options['num_nodes']
r_space = self.options['r_space']
pairs = self.options['ignored_pairs']
self.linear_solver = DirectSolver()
self.add_subsystem('t_imp', SumComp(num_nodes=nn, num_arrays=n_traj))
for i in range(n_traj):
self.add_subsystem(name='p%d' % i,
subsys=PlanePath2D(num_nodes=nn))
self.add_subsystem(name='space%d' % i,
subsys=Space(num_nodes=nn, r_space=r_space))
self.add_subsystem(name='pairwise',
subsys=Pairwise(n_traj=n_traj,
ignored_pairs=pairs,
num_nodes=nn))
from __future__ import absolute_import, print_function
import os
import sys
import torch
from torch.utils.data import DataLoader
from got10k.datasets import got10k
from pairwise import Pairwise
from siamfc import TrackerSiamFC
if __name__ == '__main__':
# setup dataset
root_dir = 'data/GOT-10k'
seq_dataset = got10k(root_dir, subset='train')
pair_dataset = Pairwise(seq_dataset)
# setup data loader
# cuda = torch.cuda.is_available()
loader = DataLoader(pair_dataset,
batch_size=8,
shuffle=True,
drop_last=True,
num_workers=2)
# setup tracker
tracker = TrackerSiamFC()
# path for saving checkpoints
net_dir = 'pretrained/siamfc_new'
if not os.path.exists(net_dir):
datapath = '../data/%s.pkl.gz'%dataset
result_path = './result/'
sentence_modeling = 'CNN' # available: 'CBoW' 'LSTM' 'CNN'
CNN_filter_length = 3
LSTM_go_backwards = True
flag_random_lookup_table = False
pair_score = Pairwise(alpha = alpha,
batch_size=batch_size,
n_epochs=n_epochs,
wordVecLen = wordVecLen,
flag_dropout = flag_dropout,
datapath=datapath,
random_seed=random_seed,
dropoutRates = dropoutRates,
optimizer = optimizer,
dispFreq = dispFreq,
beam_size = beam_size,
flag_random_lookup_table = flag_random_lookup_table,
flag_toy_data = flag_toy_data,
size_hidden_layer = size_hidden_layer,
dataset = dataset,
result_path = result_path,
sentence_modeling = sentence_modeling,
CNN_filter_length = CNN_filter_length,
LSTM_go_backwards = LSTM_go_backwards
)
from tqdm import tqdm
from got10k.datasets import *
from pairwise import Pairwise
from siamfc import TrackerSiamFC
from got10k.experiments import *
from config import config
if __name__ == '__main__':
# setup dataset
name = 'GOT-10k'
assert name in ['VID', 'GOT-10k', 'All', 'OTB']
if name == 'GOT-10k':
seq_dataset = GOT10k(config.root_dir_for_GOT_10k, subset='train')
pair_dataset = Pairwise(seq_dataset)
elif name == 'VID':
seq_dataset = ImageNetVID(config.root_dir_for_VID,
subset=('train', 'val'))
elif name == 'All':
seq_got_dataset = GOT10k(config.root_dir_for_GOT_10k, subset='train')
seq_vid_dataset = ImageNetVID(config.root_dir_for_VID,
subset=('train', 'val'))
pair_dataset = Pairwise(seq_got_dataset) + Pairwise(seq_vid_dataset)
print(len(pair_dataset))
# setup data loader
cuda = torch.cuda.is_available()
loader = DataLoader(pair_dataset,