twmht

#!/bin/bash
#
# script to extract ImageNet dataset
# ILSVRC2012_img_train.tar (about 138 GB)
# ILSVRC2012_img_val.tar (about 6.3 GB)
# make sure ILSVRC2012_img_train.tar & ILSVRC2012_img_val.tar in your current directory
#
#  https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md
# 
#  train/

twmht

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sn

# only work for matplotlib = 3.1.0


matrix = np.load('/home/acer/confusion.npy')

twmht

PYTHON3_ROOT=/home/acer/.pyenv/versions/3.7.4

# cmake -D CMAKE_BUILD_TYPE=RELEASE \
  # -D BUILD_NEW_PYTHON_SUPPORT=ON \
  # -D BUILD_opencv_python3=ON \
  # -D HAVE_opencv_python3=ON \
  # -D CMAKE_INSTALL_PREFIX=/home/acer/opencv_build \
  # -D PYTHON3_EXECUTABLE=/home/acer/.pyenv/versions/3.7.4/bin/python \
  # -D PYTHON_DEFAULT_EXECUTABLE=${PYTHON3_ROOT}/bin/python \
  # -D PYTHON3_INCLUDE_DIR=${PYTHON3_ROOT}/include/python3.7m \

twmht

#include <iostream>
#ifdef __APPLE__
    #include <OpenCL/cl.hpp>
#else
    #include <CL/cl.hpp>
#endif

int main() {
    // get all platforms (drivers), e.g. NVIDIA
    std::vector<cl::Platform> all_platforms;

twmht

PROJECT := caffe

CONFIG_FILE := Makefile.config
# Explicitly check for the config file, otherwise make -k will proceed anyway.
ifeq ($(wildcard $(CONFIG_FILE)),)
$(error $(CONFIG_FILE) not found. See $(CONFIG_FILE).example.)
endif
include $(CONFIG_FILE)

BUILD_DIR_LINK := $(BUILD_DIR)

twmht

#  import tensorflow as tf
#  # part1
#  #case 2
#  input = tf.Variable(tf.random_normal([3,97,97,10]))
#  filter = tf.Variable(tf.random_normal([3,3,10,20]))
#  x = tf.nn.conv2d(input, filter, strides=[1, 4, 4, 1], padding='SAME')
#  #  y = tf.nn.conv2d_transpose(x, filter, output_shape=[1,5,5,3], strides=[1,2,2,1],padding="SAME")

#  with tf.Session() as sess:
    #  sess.run(tf.initialize_all_variables())

twmht

# reference https://ckmarkoh.github.io/blog/2017/01/01/torch-nn-tutorial-4-backward-propagation/

# we want to learn y=x+1

require 'nn'
y = torch.Tensor(5)
mlp = nn.Sequential()
mlp:add(nn.Add(5))

function gradUpdate(mlp, x, y, criterion, learningRate)

twmht

## Refer to http://caffe.berkeleyvision.org/installation.html
# Contributions simplifying and improving our build system are welcome!

# cuDNN acceleration switch (uncomment to build with cuDNN).
USE_CUDNN := 1

# CPU-only switch (uncomment to build without GPU support).
# CPU_ONLY := 1

# uncomment to disable IO dependencies and corresponding data layers

twmht

Locate the section for your github remote in the .git/config file. It looks like this:

[remote "origin"]
	fetch = +refs/heads/*:refs/remotes/origin/*
	url = git@github.com:joyent/node.git

Now add the line fetch = +refs/pull/*/head:refs/remotes/origin/pr/* to this section. Obviously, change the github url to match your project's URL. It ends up looking like this:

twmht

Deep Learning for Face Recognition (May 2016)

Popular architectures

• FaceNet (Google)
  • They use a triplet loss with the goal of keeping the L2 intra-class distances low and inter-class distances high
• DeepID (Hong Kong University)
  • They use verification and identification signals to train the network. Afer each convolutional layer there is an identity layer connected to the supervisory signals in order to train each layer closely (on top of normal backprop)
• DeepFace (Facebook)
  • Convs followed by locally connected, followed by fully connected