hereismari

import tensorflow as tf

def model_fn(features, labels, mode):
   # Deve conter os seguintes passos:
   # 1. Definir o modelo via TF
   # 2. Definir como gerar predições
   # 3. Definir a loss function para treino e avaliação
   # 4. Definir como otimizar o modelo (optimizer)
   # 5. Definir métricas para avaliação
   # 6. Retornar um EstimatorSpec definindo os passos acima

hereismari

# -*- coding: utf-8 -*-

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf
import numpy as np
 
print ('Versão do TensorFlow:', tf.__version__)

hereismari

# -*- coding: utf-8 -*-

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf
import numpy as np
 
print ('Versão do TensorFlow:', tf.__version__)

hereismari

# -*- coding: utf-8 -*-

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf
import numpy as np

def build_cnn(input_layer, mode):

hereismari

# -*- coding: utf-8 -*-

from __future__ import absolute_import
from __future__ import division
from __future__ import print_function

import tensorflow as tf
import numpy as np

# Input functions

hereismari

import json
from urllib2 import Request, urlopen

html = Request('http://codeforces.com/api/problemset.problems')
response = urlopen(html)
x = response.read()
data = json.loads(x)  
print len(data['result']['problems'])  # dict with data from ~ 3912 problems

html = Request('http://codeforces.com/api/user.ratedList')

hereismari

Setting up a MSI laptop with GPU (gtx1060)

Installing Ubuntu 18.04, CUDA, CDNN, Pytorch and TensorFlow

Installing Ubuntu 18.04

Get Image

https://tutorials.ubuntu.com/tutorial/tutorial-create-a-usb-stick-on-ubuntu#0

Install (solving issues)

hereismari

% funcao auxiliar que corta uma palavra adequadamente para flexiona-la
reduzir(VERBO, VERBO_REDUZIDO, N) :-
	% tamanho do verbo eh TAM_VERBO
	string_length(VERBO, TAM_VERBO), 
	% devemos retirar as ultimas N letras do verbo  
	FIM_VERBO is TAM_VERBO-N,
	% o resultado eh guardado em VERBO_REDUZIDO
	sub_atom(VERBO, 0, FIM_VERBO, _, VERBO_REDUZIDO).

% EU

hereismari

Deploying Flask on Heroku

Here ~/ means the repository main folder.

1. Define ~/requirements.txt with all your Python Dependencies. For instance:

flask
numpy
pandas

hereismari