Chakkrit Termritthikun chakkritte

## input.txt
Cat mouse lion deer Tiger lion Elephant lion deer

## yolov5x.yaml
# parameters
nc: 1  # number of classes
depth_multiple: 1.33  # model depth multiple
width_multiple: 1.25  # layer channel multiple

# anchors
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

## yolov5s.yaml
# parameters
nc: 1  # number of classes
depth_multiple: 0.33  # model depth multiple
width_multiple: 0.50  # layer channel multiple

# anchors
anchors:
  - [10,13, 16,30, 33,23]  # P3/8
  - [30,61, 62,45, 59,119]  # P4/16
  - [116,90, 156,198, 373,326]  # P5/32

## kangaroo.yaml
# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
train: ../demo/train
val: ../demo/val
test: ../demo/test

# number of classes
nc: 1

# class names
names: ['kangaroo']

## create_container.sh
#!/bin/sh

# base image docker
BASE=ufoym/deepo
# name of container
NAME=$1
# directory
DIR=/home/$(whoami)

export UID=$(id -u)

## ERC20.sol
pragma solidity ^0.5.0;

// ----------------------------------------------------------------------------
// 'FIXED' 'Example Fixed Supply Token' token contract
//
// Symbol      : FIXED
// Name        : Example Fixed Supply Token
// Total supply: 1,000,000.000000000000000000
// Decimals    : 18
//

## xception.lua
-- Xception model
-- a Torch7 implementation of: https://arxiv.org/abs/1610.02357
-- E. Culurciello, October 2016

require 'nn'
local nClasses = 1000

function nn.SpatialSeparableConvolution(nInputPlane, nOutputPlane, kW, kH)
   local block = nn.Sequential()
   block:add(nn.SpatialConvolutionMap(nn.tables.oneToOne(nInputPlane), kW,kH, 1,1, 1,1))

## readme
1. Install CUDA v8.0 toolkit --> https://developer.nvidia.com/cuda-downloads
2. Install cuDNN v5.1 for CUDA 8.0 --> https://developer.nvidia.com/rdp/cudnn-download
3. Install GIT 64-bit -> https://git-scm.com/download/win
4. Install Anaconda3-4.2.0  --> https://repo.continuum.io/archive/Anaconda3-4.2.0-Windows-x86_64.exe
5. Open windows command terminal
	- conda create -n tensorflow
	- activate tensorflow
	- pip install --ignore-installed --upgrade https://storage.googleapis.com/tensorflow/windows/gpu/tensorflow_gpu-1.0.1-cp35-cp35m-win_amd64.whl

6. Validate your installation (Open windows command terminal )

## readme
#Install tensorflow 1.0 on windows 10

we’re announcing TensorFlow 1.0:
	-It’s faster
	-It’s more flexible
	-It’s more production-ready than ever

#Step 1 install

##CPU-only

## cifar10.py
from __future__ import print_function
from keras.datasets import cifar10
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.utils import np_utils

batch_size = 128
nb_classes = 10
nb_epoch = 20
	# parameters
	nc: 1 # number of classes
	depth_multiple: 1.33 # model depth multiple
	width_multiple: 1.25 # layer channel multiple

	# anchors
	anchors:
	- [10,13, 16,30, 33,23] # P3/8
	- [30,61, 62,45, 59,119] # P4/16
	- [116,90, 156,198, 373,326] # P5/32
	# parameters
	nc: 1 # number of classes
	depth_multiple: 0.33 # model depth multiple
	width_multiple: 0.50 # layer channel multiple

	# anchors
	anchors:
	- [10,13, 16,30, 33,23] # P3/8
	- [30,61, 62,45, 59,119] # P4/16
	- [116,90, 156,198, 373,326] # P5/32
	# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
	train: ../demo/train
	val: ../demo/val
	test: ../demo/test

	# number of classes
	nc: 1

	# class names
	names: ['kangaroo']
	#!/bin/sh

	# base image docker
	BASE=ufoym/deepo
	# name of container
	NAME=$1
	# directory
	DIR=/home/$(whoami)

	export UID=$(id -u)
	pragma solidity ^0.5.0;

	// ----------------------------------------------------------------------------
	// 'FIXED' 'Example Fixed Supply Token' token contract
	//
	// Symbol : FIXED
	// Name : Example Fixed Supply Token
	// Total supply: 1,000,000.000000000000000000
	// Decimals : 18
	//
	-- Xception model
	-- a Torch7 implementation of: https://arxiv.org/abs/1610.02357
	-- E. Culurciello, October 2016

	require 'nn'
	local nClasses = 1000

	function nn.SpatialSeparableConvolution(nInputPlane, nOutputPlane, kW, kH)
	local block = nn.Sequential()
	block:add(nn.SpatialConvolutionMap(nn.tables.oneToOne(nInputPlane), kW,kH, 1,1, 1,1))
	1. Install CUDA v8.0 toolkit --> https://developer.nvidia.com/cuda-downloads
	2. Install cuDNN v5.1 for CUDA 8.0 --> https://developer.nvidia.com/rdp/cudnn-download
	3. Install GIT 64-bit -> https://git-scm.com/download/win
	4. Install Anaconda3-4.2.0 --> https://repo.continuum.io/archive/Anaconda3-4.2.0-Windows-x86_64.exe
	5. Open windows command terminal
	- conda create -n tensorflow
	- activate tensorflow
	- pip install --ignore-installed --upgrade https://storage.googleapis.com/tensorflow/windows/gpu/tensorflow_gpu-1.0.1-cp35-cp35m-win_amd64.whl

	6. Validate your installation (Open windows command terminal )
	#Install tensorflow 1.0 on windows 10

	we’re announcing TensorFlow 1.0:
	-It’s faster
	-It’s more flexible
	-It’s more production-ready than ever

	#Step 1 install

	##CPU-only
	from __future__ import print_function
	from keras.datasets import cifar10
	from keras.models import Sequential
	from keras.layers import Dense, Dropout, Activation, Flatten
	from keras.layers import Convolution2D, MaxPooling2D
	from keras.utils import np_utils

	batch_size = 128
	nb_classes = 10
	nb_epoch = 20