zeakey

import sys, os
sys.path.insert(0, 'path/to/caffe/python')
import caffe
from caffe import layers as L, params as P
from caffe.coord_map import crop
import numpy as np

def conv_relu(bottom, nout, ks=3, stride=1, pad=1, mult=[1,1,2,0]):
    conv = L.Convolution(bottom, kernel_size=ks, stride=stride,
        num_output=nout, pad=pad, weight_filler=dict(type='xavier'), 

zeakey

#!/bin/bash
# install common deps
sudo apt-get update
sudo apt-get upgrade
sudo apt-get install -y build-essential cmake make
sudo apt-get install --no-install-recommends libboost-all-dev
sudo apt-get install libprotobuf-dev libleveldb-dev libsnappy-dev libhdf5-serial-dev protobuf-compiler
sudo apt-get install libgflags-dev libgoogle-glog-dev liblmdb-dev
sudo apt-get install libatlas-base-dev
sudo apt-get install python-dev

zeakey

zeakey

zeakey

### dual top-down path network for instance-level salient object detection
name: "LERG"
layer {
  name: "data"
  type: "Python"
  top: "data"
  top: "label"
  python_param {
    module: "pylayer"
    layer: "ImageLabelMapDataLayer"

zeakey

name: "ResNet-50"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224

layer {
	bottom: "data"
	top: "conv1"

zeakey

# multi-class cross-entropy loss with center-exclusive
from __future__ import print_function
import torch
import torch.nn as nn
import torch.optim as optim
import torch.nn.functional as F
from torch.autograd import Variable
from torch.optim import lr_scheduler
torch.backends.cudnn.bencmark = True
import os, sys, random, datetime, time

zeakey

class ExclusiveLinear(nn.Module):
  
  def __init__(self, feat_dim=512, num_class=10572, norm_data=True, radius=20):
    super(ExclusiveLinear, self).__init__()
    self.num_class = num_class
    self.feat_dim = feat_dim
    self.norm_data = norm_data
    self.radius = float(radius)
    self.weight = nn.Parameter(torch.randn(self.num_class, self.feat_dim))
    self.reset_parameters()