walkoncross

Netscope: http://ethereon.github.io/netscope/quickstart.html

Netscope CNN Analyzer: https://dgschwend.github.io/netscope/quickstart.html

walkoncross

CenterFace (centerloss)

1. deploy:

• Netscope: http://ethereon.github.io/netscope/#/gist/719d1a0b2ae700598313d6833b04aaac

• Netscope CNN Analyzer: http://dgschwend.github.io/netscope/#/gist/719d1a0b2ae700598313d6833b04aaac

2. train-test

• Netscope:

walkoncross

name: "CenterFace-ResNet"
layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  include { 
    phase: TRAIN
  }
  transform_param {

walkoncross

name: "NormFace-Resnet"
input: "data"
input_dim: 100
input_dim: 3
input_dim: 112
input_dim: 96
layer {
  name: "flip_data"
  type: "Flip"
  bottom: "data"

walkoncross

name: "NormFace-ResNet"
layer {
  name: "data"
  type: "ImageData"
  top: "data"
  top: "label"
  include { 
    phase: TRAIN
  }
  transform_param {

walkoncross

#!/usr/bin/env bash
# referer url is public share links
# file url can be found via browser downloading
referer_url=$1
file_url=$2
save_name=$3

wget --referer=$referer_url -O $save_name "$file_url"

walkoncross

sudo: required
before_install:
  - sudo apt-get install libao-dev
  - sudo apt-get install libcurl4-openssl-dev
  - chmod +x installMPG123.sh
  - ./installMPG123.sh
  
# Enable C++ support
language: cpp

walkoncross

#!/usr/bin/env python
"""
Starts a Tornado static file server in a given directory.
To start the server in the current directory:

    tserv .

Then go to http://localhost:8000 to browse the directory.

Use the --prefix option to add a prefix to the served URL,

walkoncross

#include <opencv2/opencv.hpp>

#include <iostream>
#include <vector>
#include <cmath>
#include <assert.h>

using namespace std;
using namespace cv;

walkoncross

• Set up Visual Studio 2015 and CUDA/CUDNN according to https://gist.github.com/zentralwerkstatt/d4c1cc56b9c99d33411aae3c296b578d
• Download and install cmake from https://cmake.org/download/
• Download dlib from http://dlib.net/
• Download openCV from https://sourceforge.net/projects/opencvlibrary/
• Extract openCV and add opencv\build to user path environment variable
• Extract dlib
• cd dlib-19.4\dlib-19.4\examples
• mkdir build
• cd build
• cmake -G "Visual Studio 14 2015 Win64" ..