etienne87

""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
import numpy as np
import cPickle as pickle
import gym

from chainer import cuda
import cupy as cp
import time, threading

#backend

etienne87

#!/usr/bin/python
# torch_bilateral: bi/trilateral filtering in torch
import torch
from torch import nn
from torch.autograd import Variable
import torch.nn.functional as F
from torch.nn import Parameter
import numpy as np
import pdb
import time

etienne87

#!/usr/bin/python
# torch_bilateral: bi/trilateral filtering in torch
import torch
from torch import nn
from torch.autograd import Variable
import torch.nn.functional as F
from torch.nn import Parameter
import numpy as np
import pdb
import time

etienne87

    #!/usr/bin/python
# torch_bilateral: bi/trilateral filtering in tf
# Copyright: (c) 2017-2018 Prophesee
from __future__ import print_function
import tensorflow as tf
import numpy as np
import pdb
import time

etienne87

from __future__ import print_function
import glob
import sys
import time
import multiprocessing as mp, numpy as np, random
from prophesee_utils.td_video import ChronoVideo
import prophesee_utils.td_processing as tdp
import prophesee_utils.vis_utils as vis
import cv2
from numba import njit as jit

etienne87

# pylint: disable-all
from __future__ import print_function
import torch
import random
import math
import torch
import torch.nn as nn
import torch.nn.functional as F
from box import box_iou, box_clamp
import numpy as np

etienne87

#!/usr/bin/python
# This script runs a random 3d animation & can retrieve:
# - detection
# - flow
# - zbuffer
#
# Copyright: (c) 2017-2018 Chronocam

import numpy as np
import cv2

etienne87

from __future__ import division
import time
import numpy as np

class Timing:
    def __init__(self):
        self.total = 0
        self.ncalls = 0
        self.nevents = 0
        self.last_num = -1

etienne87

import torch
import torch.nn as nn
import torch.nn.functional as F
import math
import time


def timeit(x, func, iter=10):
	torch.cuda.synchronize()
	start = time.time()

etienne87

# pylint: disable-all
import torch.nn as nn
from torch.nn import functional as F
import torch

def time_to_batch(x):
    t, n = x.size()[:2]
    x = x.view(n * t, *x.size()[2:])
    return x, n