insujeon

def sample_gumbel(shape, eps=1e-20): 
  """Sample from Gumbel(0, 1)"""
  U = tf.random_uniform(shape,minval=0,maxval=1)
  return -tf.log(-tf.log(U + eps) + eps)

def gumbel_softmax_sample(logits, temperature): 
  """ Draw a sample from the Gumbel-Softmax distribution"""
  y = logits + sample_gumbel(tf.shape(logits))
  return tf.nn.softmax( y / temperature)

insujeon

import pdb
class Config(pdb.DefaultConfig):
    sticky_by_default = True

insujeon

function top = nms(boxes, overlap)
% top = nms_fast(boxes, overlap)
% Non-maximum suppression. (FAST VERSION)
% Greedily select high-scoring detections and skip detections
% that are significantly covered by a previously selected
% detection.
% NOTE: This is adapted from Pedro Felzenszwalb's version (nms.m),
% but an inner loop has been eliminated to significantly speed it
% up in the case of a large number of boxes
% Tomasz Malisiewicz ([email protected])

insujeon

class Maxout(nn.Module):

    def __init__(self, d_in, d_out, pool_size):
        super().__init__()
        self.d_in, self.d_out, self.pool_size = d_in, d_out, pool_size
        self.lin = nn.Linear(d_in, d_out * pool_size)


    def forward(self, inputs):
        shape = list(inputs.size())

insujeon

import sys
import torch
import torch.utils
import torch.nn as nn
from torch.autograd import Variable
from torchvision import models

try:
    import gpustat
except ImportError:

insujeon

import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.nn.parameter import Parameter

def debug(debug_open, x, layername):
    if debug_open:
        print x.size(), 'after', layername

class PVANet(nn.Module):

insujeon

import numpy as np
import scipy
import scipy.ndimage
from scipy.ndimage.filters import gaussian_filter
from scipy.ndimage.interpolation import map_coordinates
import collections
from PIL import Image
import numbers

__author__ = "Wei OUYANG"